WACV 2024 Open Access Repository

Papers

Object-Centric Video Representation for Long-Term Action Anticipation: Ce Zhang,

Changcheng Fu,

Shijie Wang,

Nakul Agarwal,

Kwonjoon Lee,

Chiho Choi,

Chen Sun; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Ce and Fu, Changcheng and Wang, Shijie and Agarwal, Nakul and Lee, Kwonjoon and Choi, Chiho and Sun, Chen}, title = {Object-Centric Video Representation for Long-Term Action Anticipation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6751-6761} }
CLRerNet: Improving Confidence of Lane Detection With LaneIoU: Hiroto Honda,

Yusuke Uchida; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Honda_2024_WACV, author = {Honda, Hiroto and Uchida, Yusuke}, title = {CLRerNet: Improving Confidence of Lane Detection With LaneIoU}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1176-1185} }
Training Ensembles With Inliers and Outliers for Semi-Supervised Active Learning: Vladan Stojnić,

Zakaria Laskar,

Giorgos Tolias; [pdf] [supp]
[bibtex]
@InProceedings{Stojnic_2024_WACV, author = {Stojni\'c, Vladan and Laskar, Zakaria and Tolias, Giorgos}, title = {Training Ensembles With Inliers and Outliers for Semi-Supervised Active Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {260-269} }
Robust Source-Free Domain Adaptation for Fundus Image Segmentation: Lingrui Li,

Yanfeng Zhou,

Ge Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_WACV, author = {Li, Lingrui and Zhou, Yanfeng and Yang, Ge}, title = {Robust Source-Free Domain Adaptation for Fundus Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7840-7849} }
Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Model: Shoma Iwai,

Tomo Miyazaki,

Shinichiro Omachi; [pdf] [supp]
[bibtex]
@InProceedings{Iwai_2024_WACV, author = {Iwai, Shoma and Miyazaki, Tomo and Omachi, Shinichiro}, title = {Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Model}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2900-2909} }
MetaVers: Meta-Learned Versatile Representations for Personalized Federated Learning: Jin Hyuk Lim,

SeungBum Ha,

Sung Whan Yoon; [pdf] [supp]
[bibtex]
@InProceedings{Lim_2024_WACV, author = {Lim, Jin Hyuk and Ha, SeungBum and Yoon, Sung Whan}, title = {MetaVers: Meta-Learned Versatile Representations for Personalized Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2587-2596} }
Improving Open-Set Semi-Supervised Learning With Self-Supervision: Erik Wallin,

Lennart Svensson,

Fredrik Kahl,

Lars Hammarstrand; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wallin_2024_WACV, author = {Wallin, Erik and Svensson, Lennart and Kahl, Fredrik and Hammarstrand, Lars}, title = {Improving Open-Set Semi-Supervised Learning With Self-Supervision}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2356-2365} }
FOSSIL: Free Open-Vocabulary Semantic Segmentation Through Synthetic References Retrieval: Luca Barsellotti,

Roberto Amoroso,

Lorenzo Baraldi,

Rita Cucchiara; [pdf] [supp]
[bibtex]
@InProceedings{Barsellotti_2024_WACV, author = {Barsellotti, Luca and Amoroso, Roberto and Baraldi, Lorenzo and Cucchiara, Rita}, title = {FOSSIL: Free Open-Vocabulary Semantic Segmentation Through Synthetic References Retrieval}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1464-1473} }
Activity-Based Early Autism Diagnosis Using a Multi-Dataset Supervised Contrastive Learning Approach: Asha Rani,

Yashaswi Verma; [pdf]
[bibtex]
@InProceedings{Rani_2024_WACV, author = {Rani, Asha and Verma, Yashaswi}, title = {Activity-Based Early Autism Diagnosis Using a Multi-Dataset Supervised Contrastive Learning Approach}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7788-7797} }
Label Shift Estimation for Class-Imbalance Problem: A Bayesian Approach: Changkun Ye,

Russell Tsuchida,

Lars Petersson,

Nick Barnes; [pdf] [supp]
[bibtex]
@InProceedings{Ye_2024_WACV, author = {Ye, Changkun and Tsuchida, Russell and Petersson, Lars and Barnes, Nick}, title = {Label Shift Estimation for Class-Imbalance Problem: A Bayesian Approach}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1073-1082} }
SeaTurtleID2022: A Long-Span Dataset for Reliable Sea Turtle Re-Identification: Lukáš Adam,

Vojtěch Čermák,

Kostas Papafitsoros,

Lukas Picek; [pdf] [supp]
[bibtex]
@InProceedings{Adam_2024_WACV, author = {Adam, Luk\'a\v{s} and \v{C}erm\'ak, Vojt\v{e}ch and Papafitsoros, Kostas and Picek, Lukas}, title = {SeaTurtleID2022: A Long-Span Dataset for Reliable Sea Turtle Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7146-7156} }
Self-Supervised Edge Detection Reconstruction for Topology-Informed 3D Axon Segmentation and Centerline Detection: Alec S. Xu,

Nina I. Shamsi,

Lars A. Gjesteby,

Laura J. Brattain; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2024_WACV, author = {Xu, Alec S. and Shamsi, Nina I. and Gjesteby, Lars A. and Brattain, Laura J.}, title = {Self-Supervised Edge Detection Reconstruction for Topology-Informed 3D Axon Segmentation and Centerline Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7831-7839} }
Bi-Directional Training for Composed Image Retrieval via Text Prompt Learning: Zheyuan Liu,

Weixuan Sun,

Yicong Hong,

Damien Teney,

Stephen Gould; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_WACV, author = {Liu, Zheyuan and Sun, Weixuan and Hong, Yicong and Teney, Damien and Gould, Stephen}, title = {Bi-Directional Training for Composed Image Retrieval via Text Prompt Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5753-5762} }
iBARLE: imBalance-Aware Room Layout Estimation: Taotao Jing,

Lichen Wang,

Naji Khosravan,

Zhiqiang Wan,

Zachary Bessinger,

Zhengming Ding,

Sing Bing Kang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jing_2024_WACV, author = {Jing, Taotao and Wang, Lichen and Khosravan, Naji and Wan, Zhiqiang and Bessinger, Zachary and Ding, Zhengming and Kang, Sing Bing}, title = {iBARLE: imBalance-Aware Room Layout Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {914-924} }
FarSight: A Physics-Driven Whole-Body Biometric System at Large Distance and Altitude: Feng Liu,

Ryan Ashbaugh,

Nicholas Chimitt,

Najmul Hassan,

Ali Hassani,

Ajay Jaiswal,

Minchul Kim,

Zhiyuan Mao,

Christopher Perry,

Zhiyuan Ren,

Yiyang Su,

Pegah Varghaei,

Kai Wang,

Xingguang Zhang,

Stanley Chan,

Arun Ross,

Humphrey Shi,

Zhangyang Wang,

Anil Jain,

Xiaoming Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Liu_2024_WACV, author = {Liu, Feng and Ashbaugh, Ryan and Chimitt, Nicholas and Hassan, Najmul and Hassani, Ali and Jaiswal, Ajay and Kim, Minchul and Mao, Zhiyuan and Perry, Christopher and Ren, Zhiyuan and Su, Yiyang and Varghaei, Pegah and Wang, Kai and Zhang, Xingguang and Chan, Stanley and Ross, Arun and Shi, Humphrey and Wang, Zhangyang and Jain, Anil and Liu, Xiaoming}, title = {FarSight: A Physics-Driven Whole-Body Biometric System at Large Distance and Altitude}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6227-6236} }
Time To Shine: Fine-Tuning Object Detection Models With Synthetic Adverse Weather Images: Thomas Rothmeier,

Werner Huber,

Alois C. Knoll; [pdf] [supp]
[bibtex]
@InProceedings{Rothmeier_2024_WACV, author = {Rothmeier, Thomas and Huber, Werner and Knoll, Alois C.}, title = {Time To Shine: Fine-Tuning Object Detection Models With Synthetic Adverse Weather Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4447-4456} }
Unsupervised and Semi-Supervised Co-Salient Object Detection via Segmentation Frequency Statistics: Souradeep Chakraborty,

Shujon Naha,

Muhammet Bastan,

Amit Kumar K. C.,

Dimitris Samaras; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chakraborty_2024_WACV, author = {Chakraborty, Souradeep and Naha, Shujon and Bastan, Muhammet and C., Amit Kumar K. and Samaras, Dimitris}, title = {Unsupervised and Semi-Supervised Co-Salient Object Detection via Segmentation Frequency Statistics}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {332-342} }
3SD: Self-Supervised Saliency Detection With No Labels: Rajeev Yasarla,

Renliang Weng,

Wongun Choi,

Vishal M. Patel,

Amir Sadeghian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yasarla_2024_WACV, author = {Yasarla, Rajeev and Weng, Renliang and Choi, Wongun and Patel, Vishal M. and Sadeghian, Amir}, title = {3SD: Self-Supervised Saliency Detection With No Labels}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {313-322} }
Pixel Matching Network for Cross-Domain Few-Shot Segmentation: Hao Chen,

Yonghan Dong,

Zheming Lu,

Yunlong Yu,

Jungong Han; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2024_WACV, author = {Chen, Hao and Dong, Yonghan and Lu, Zheming and Yu, Yunlong and Han, Jungong}, title = {Pixel Matching Network for Cross-Domain Few-Shot Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {978-987} }
Cross-Domain Few-Shot Incremental Learning for Point-Cloud Recognition: Yuwen Tan,

Xiang Xiang; [pdf]
[bibtex]
@InProceedings{Tan_2024_WACV, author = {Tan, Yuwen and Xiang, Xiang}, title = {Cross-Domain Few-Shot Incremental Learning for Point-Cloud Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2307-2316} }
Robust Unsupervised Domain Adaptation Through Negative-View Regularization: Joonhyeok Jang,

Sunhyeok Lee,

Seonghak Kim,

Jung-un Kim,

Seonghyun Kim,

Daeshik Kim; [pdf] [supp]
[bibtex]
@InProceedings{Jang_2024_WACV, author = {Jang, Joonhyeok and Lee, Sunhyeok and Kim, Seonghak and Kim, Jung-un and Kim, Seonghyun and Kim, Daeshik}, title = {Robust Unsupervised Domain Adaptation Through Negative-View Regularization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2462-2471} }
Soft Curriculum for Learning Conditional GANs With Noisy-Labeled and Uncurated Unlabeled Data: Kai Katsumata,

Duc Minh Vo,

Tatsuya Harada,

Hideki Nakayama; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Katsumata_2024_WACV, author = {Katsumata, Kai and Vo, Duc Minh and Harada, Tatsuya and Nakayama, Hideki}, title = {Soft Curriculum for Learning Conditional GANs With Noisy-Labeled and Uncurated Unlabeled Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5323-5332} }
HMP: Hand Motion Priors for Pose and Shape Estimation From Video: Enes Duran,

Muhammed Kocabas,

Vasileios Choutas,

Zicong Fan,

Michael J. Black; [pdf] [supp]
[bibtex]
@InProceedings{Duran_2024_WACV, author = {Duran, Enes and Kocabas, Muhammed and Choutas, Vasileios and Fan, Zicong and Black, Michael J.}, title = {HMP: Hand Motion Priors for Pose and Shape Estimation From Video}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6353-6363} }
Amodal Intra-Class Instance Segmentation: Synthetic Datasets and Benchmark: Jiayang Ao,

Qiuhong Ke,

Krista A. Ehinger; [pdf] [arXiv]
[bibtex]
@InProceedings{Ao_2024_WACV, author = {Ao, Jiayang and Ke, Qiuhong and Ehinger, Krista A.}, title = {Amodal Intra-Class Instance Segmentation: Synthetic Datasets and Benchmark}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {281-290} }
RMFER: Semi-Supervised Contrastive Learning for Facial Expression Recognition With Reaction Mashup Video: Yunseong Cho,

Chanwoo Kim,

Hoseong Cho,

Yunhoe Ku,

Eunseo Kim,

Muhammadjon Boboev,

Joonseok Lee,

Seungryul Baek; [pdf] [supp]
[bibtex]
@InProceedings{Cho_2024_WACV, author = {Cho, Yunseong and Kim, Chanwoo and Cho, Hoseong and Ku, Yunhoe and Kim, Eunseo and Boboev, Muhammadjon and Lee, Joonseok and Baek, Seungryul}, title = {RMFER: Semi-Supervised Contrastive Learning for Facial Expression Recognition With Reaction Mashup Video}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5913-5922} }
AMEND: Adaptive Margin and Expanded Neighborhood for Efficient Generalized Category Discovery: Anwesha Banerjee,

Liyana Sahir Kallooriyakath,

Soma Biswas; [pdf]
[bibtex]
@InProceedings{Banerjee_2024_WACV, author = {Banerjee, Anwesha and Kallooriyakath, Liyana Sahir and Biswas, Soma}, title = {AMEND: Adaptive Margin and Expanded Neighborhood for Efficient Generalized Category Discovery}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2101-2110} }
Brainomaly: Unsupervised Neurologic Disease Detection Utilizing Unannotated T1-Weighted Brain MR Images: Md Mahfuzur Rahman Siddiquee,

Jay Shah,

Teresa Wu,

Catherine Chong,

Todd J. Schwedt,

Gina Dumkrieger,

Simona Nikolova,

Baoxin Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Siddiquee_2024_WACV, author = {Siddiquee, Md Mahfuzur Rahman and Shah, Jay and Wu, Teresa and Chong, Catherine and Schwedt, Todd J. and Dumkrieger, Gina and Nikolova, Simona and Li, Baoxin}, title = {Brainomaly: Unsupervised Neurologic Disease Detection Utilizing Unannotated T1-Weighted Brain MR Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7573-7582} }
Contrastive Learning for Multi-Object Tracking With Transformers: Pierre-François De Plaen,

Nicola Marinello,

Marc Proesmans,

Tinne Tuytelaars,

Luc Van Gool; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{De_Plaen_2024_WACV, author = {De Plaen, Pierre-Fran\c{c}ois and Marinello, Nicola and Proesmans, Marc and Tuytelaars, Tinne and Van Gool, Luc}, title = {Contrastive Learning for Multi-Object Tracking With Transformers}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6867-6877} }
BEVMap: Map-Aware BEV Modeling for 3D Perception: Mincheol Chang,

Seokha Moon,

Reza Mahjourian,

Jinkyu Kim; [pdf]
[bibtex]
@InProceedings{Chang_2024_WACV, author = {Chang, Mincheol and Moon, Seokha and Mahjourian, Reza and Kim, Jinkyu}, title = {BEVMap: Map-Aware BEV Modeling for 3D Perception}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7419-7428} }
PreciseDebias: An Automatic Prompt Engineering Approach for Generative AI To Mitigate Image Demographic Biases: Colton Clemmer,

Junhua Ding,

Yunhe Feng; [pdf] [supp]
[bibtex]
@InProceedings{Clemmer_2024_WACV, author = {Clemmer, Colton and Ding, Junhua and Feng, Yunhe}, title = {PreciseDebias: An Automatic Prompt Engineering Approach for Generative AI To Mitigate Image Demographic Biases}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8596-8605} }
Benchmark Generation Framework With Customizable Distortions for Image Classifier Robustness: Soumyendu Sarkar,

Ashwin Ramesh Babu,

Sajad Mousavi,

Zachariah Carmichael,

Vineet Gundecha,

Sahand Ghorbanpour,

Ricardo Luna Gutierrez,

Antonio Guillen,

Avisek Naug; [pdf] [arXiv]
[bibtex]
@InProceedings{Sarkar_2024_WACV, author = {Sarkar, Soumyendu and Babu, Ashwin Ramesh and Mousavi, Sajad and Carmichael, Zachariah and Gundecha, Vineet and Ghorbanpour, Sahand and Gutierrez, Ricardo Luna and Guillen, Antonio and Naug, Avisek}, title = {Benchmark Generation Framework With Customizable Distortions for Image Classifier Robustness}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4418-4427} }
Shape-Biased CNNs Are Not Always Superior in Out-of-Distribution Robustness: Xinkuan Qiu,

Meina Kan,

Yongbin Zhou,

Yanchao Bi,

Shiguang Shan; [pdf] [supp]
[bibtex]
@InProceedings{Qiu_2024_WACV, author = {Qiu, Xinkuan and Kan, Meina and Zhou, Yongbin and Bi, Yanchao and Shan, Shiguang}, title = {Shape-Biased CNNs Are Not Always Superior in Out-of-Distribution Robustness}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2326-2335} }
Towards Visual Saliency Explanations of Face Verification: Yuhang Lu,

Zewei Xu,

Touradj Ebrahimi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lu_2024_WACV, author = {Lu, Yuhang and Xu, Zewei and Ebrahimi, Touradj}, title = {Towards Visual Saliency Explanations of Face Verification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4726-4735} }
Bias and Diversity in Synthetic-Based Face Recognition: Marco Huber,

Anh Thi Luu,

Fadi Boutros,

Arjan Kuijper,

Naser Damer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huber_2024_WACV, author = {Huber, Marco and Luu, Anh Thi and Boutros, Fadi and Kuijper, Arjan and Damer, Naser}, title = {Bias and Diversity in Synthetic-Based Face Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6215-6226} }
Textual Alchemy: CoFormer for Scene Text Understanding: Gayatri Deshmukh,

Onkar Susladkar,

Dhruv Makwana,

Sparsh Mittal,

Sai Chandra Teja R.; [pdf] [supp]
[bibtex]
@InProceedings{Deshmukh_2024_WACV, author = {Deshmukh, Gayatri and Susladkar, Onkar and Makwana, Dhruv and Mittal, Sparsh and R., Sai Chandra Teja}, title = {Textual Alchemy: CoFormer for Scene Text Understanding}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2931-2941} }
Data-Centric Debugging: Mitigating Model Failures via Targeted Image Retrieval: Sahil Singla,

Atoosa Malemir Chegini,

Mazda Moayeri,

Soheil Feizi; [pdf] [supp]
[bibtex]
@InProceedings{Singla_2024_WACV, author = {Singla, Sahil and Chegini, Atoosa Malemir and Moayeri, Mazda and Feizi, Soheil}, title = {Data-Centric Debugging: Mitigating Model Failures via Targeted Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {63-74} }
DTrOCR: Decoder-Only Transformer for Optical Character Recognition: Masato Fujitake; [pdf] [arXiv]
[bibtex]
@InProceedings{Fujitake_2024_WACV, author = {Fujitake, Masato}, title = {DTrOCR: Decoder-Only Transformer for Optical Character Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8025-8035} }
Efficient Transferability Assessment for Selection of Pre-Trained Detectors: Zhao Wang,

Aoxue Li,

Zhenguo Li,

Qi Dou; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2024_WACV, author = {Wang, Zhao and Li, Aoxue and Li, Zhenguo and Dou, Qi}, title = {Efficient Transferability Assessment for Selection of Pre-Trained Detectors}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1679-1689} }
NVAutoNet: Fast and Accurate 360deg 3D Visual Perception for Self Driving: Trung Pham,

Mehran Maghoumi,

Wanli Jiang,

Bala Siva Sashank Jujjavarapu,

Mehdi Sajjadi,

Xin Liu,

Hsuan-Chu Lin,

Bor-Jeng Chen,

Giang Truong,

Chao Fang,

Junghyun Kwon,

Minwoo Park; [pdf] [supp]
[bibtex]
@InProceedings{Pham_2024_WACV, author = {Pham, Trung and Maghoumi, Mehran and Jiang, Wanli and Jujjavarapu, Bala Siva Sashank and Sajjadi, Mehdi and Liu, Xin and Lin, Hsuan-Chu and Chen, Bor-Jeng and Truong, Giang and Fang, Chao and Kwon, Junghyun and Park, Minwoo}, title = {NVAutoNet: Fast and Accurate 360deg 3D Visual Perception for Self Driving}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7376-7385} }
VideoFACT: Detecting Video Forgeries Using Attention, Scene Context, and Forensic Traces: Tai D. Nguyen,

Shengbang Fang,

Matthew C. Stamm; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nguyen_2024_WACV, author = {Nguyen, Tai D. and Fang, Shengbang and Stamm, Matthew C.}, title = {VideoFACT: Detecting Video Forgeries Using Attention, Scene Context, and Forensic Traces}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8563-8573} }
TEGLO: High Fidelity Canonical Texture Mapping From Single-View Images: Vishal Vinod,

Tanmay Shah,

Dmitry Lagun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Vinod_2024_WACV, author = {Vinod, Vishal and Shah, Tanmay and Lagun, Dmitry}, title = {TEGLO: High Fidelity Canonical Texture Mapping From Single-View Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3585-3595} }
Prototypical Contrastive Network for Imbalanced Aerial Image Segmentation: Keiller Nogueira,

Mayara Maezano Faita-Pinheiro,

Ana Paula Marques Ramos,

Wesley Nunes Gonçalves,

José Marcato Junior,

Jefersson A. dos Santos; [pdf]
[bibtex]
@InProceedings{Nogueira_2024_WACV, author = {Nogueira, Keiller and Faita-Pinheiro, Mayara Maezano and Ramos, Ana Paula Marques and Gon\c{c}alves, Wesley Nunes and Junior, Jos\'e Marcato and dos Santos, Jefersson A.}, title = {Prototypical Contrastive Network for Imbalanced Aerial Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8366-8376} }
BoostRad: Enhancing Object Detection by Boosting Radar Reflections: Yuval Haitman,

Oded Bialer; [pdf] [supp]
[bibtex]
@InProceedings{Haitman_2024_WACV, author = {Haitman, Yuval and Bialer, Oded}, title = {BoostRad: Enhancing Object Detection by Boosting Radar Reflections}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1638-1647} }
Frequency Attention for Knowledge Distillation: Cuong Pham,

Van-Anh Nguyen,

Trung Le,

Dinh Phung,

Gustavo Carneiro,

Thanh-Toan Do; [pdf] [supp]
[bibtex]
@InProceedings{Pham_2024_WACV, author = {Pham, Cuong and Nguyen, Van-Anh and Le, Trung and Phung, Dinh and Carneiro, Gustavo and Do, Thanh-Toan}, title = {Frequency Attention for Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2277-2286} }
Lost Your Style? Navigating With Semantic-Level Approach for Text-To-Outfit Retrieval: Junkyu Jang,

Eugene Hwang,

Sung-Hyuk Park; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jang_2024_WACV, author = {Jang, Junkyu and Hwang, Eugene and Park, Sung-Hyuk}, title = {Lost Your Style? Navigating With Semantic-Level Approach for Text-To-Outfit Retrieval}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8066-8075} }
MoRF: Mobile Realistic Fullbody Avatars From a Monocular Video: Renat Bashirov,

Alexey Larionov,

Evgeniya Ustinova,

Mikhail Sidorenko,

David Svitov,

Ilya Zakharkin,

Victor Lempitsky; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bashirov_2024_WACV, author = {Bashirov, Renat and Larionov, Alexey and Ustinova, Evgeniya and Sidorenko, Mikhail and Svitov, David and Zakharkin, Ilya and Lempitsky, Victor}, title = {MoRF: Mobile Realistic Fullbody Avatars From a Monocular Video}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3545-3555} }
dacl10k: Benchmark for Semantic Bridge Damage Segmentation: Johannes Flotzinger,

Philipp J. Rösch,

Thomas Braml; [pdf] [supp]
[bibtex]
@InProceedings{Flotzinger_2024_WACV, author = {Flotzinger, Johannes and R\"osch, Philipp J. and Braml, Thomas}, title = {dacl10k: Benchmark for Semantic Bridge Damage Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8626-8635} }
What's Outside the Intersection? Fine-Grained Error Analysis for Semantic Segmentation Beyond IoU: Maximilian Bernhard,

Roberto Amoroso,

Yannic Kindermann,

Lorenzo Baraldi,

Rita Cucchiara,

Volker Tresp,

Matthias Schubert; [pdf] [supp]
[bibtex]
@InProceedings{Bernhard_2024_WACV, author = {Bernhard, Maximilian and Amoroso, Roberto and Kindermann, Yannic and Baraldi, Lorenzo and Cucchiara, Rita and Tresp, Volker and Schubert, Matthias}, title = {What's Outside the Intersection? Fine-Grained Error Analysis for Semantic Segmentation Beyond IoU}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {968-977} }
Co-Speech Gesture Detection Through Multi-Phase Sequence Labeling: Esam Ghaleb,

Ilya Burenko,

Marlou Rasenberg,

Wim Pouw,

Peter Uhrig,

Judith Holler,

Ivan Toni,

Aslı Özyürek,

Raquel Fernández; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ghaleb_2024_WACV, author = {Ghaleb, Esam and Burenko, Ilya and Rasenberg, Marlou and Pouw, Wim and Uhrig, Peter and Holler, Judith and Toni, Ivan and \"Ozy\"urek, Asl{\i} and Fern\'andez, Raquel}, title = {Co-Speech Gesture Detection Through Multi-Phase Sequence Labeling}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4007-4015} }
Missing Modality Robustness in Semi-Supervised Multi-Modal Semantic Segmentation: Harsh Maheshwari,

Yen-Cheng Liu,

Zsolt Kira; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Maheshwari_2024_WACV, author = {Maheshwari, Harsh and Liu, Yen-Cheng and Kira, Zsolt}, title = {Missing Modality Robustness in Semi-Supervised Multi-Modal Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1020-1030} }
Adversarial Likelihood Estimation With One-Way Flows: Omri Ben-Dov,

Pravir Singh Gupta,

Victoria Abrevaya,

Michael J. Black,

Partha Ghosh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ben-Dov_2024_WACV, author = {Ben-Dov, Omri and Gupta, Pravir Singh and Abrevaya, Victoria and Black, Michael J. and Ghosh, Partha}, title = {Adversarial Likelihood Estimation With One-Way Flows}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3779-3788} }
Fast Sun-Aligned Outdoor Scene Relighting Based on TensoRF: Yeonjin Chang,

Yearim Kim,

Seunghyeon Seo,

Jung Yi,

Nojun Kwak; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chang_2024_WACV, author = {Chang, Yeonjin and Kim, Yearim and Seo, Seunghyeon and Yi, Jung and Kwak, Nojun}, title = {Fast Sun-Aligned Outdoor Scene Relighting Based on TensoRF}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3626-3636} }
Robust Eye Blink Detection Using Dual Embedding Video Vision Transformer: Jeongmin Hong,

Joseph Shin,

Juhee Choi,

Minsam Ko; [pdf]
[bibtex]
@InProceedings{Hong_2024_WACV, author = {Hong, Jeongmin and Shin, Joseph and Choi, Juhee and Ko, Minsam}, title = {Robust Eye Blink Detection Using Dual Embedding Video Vision Transformer}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6374-6384} }
Domain Generalisation via Risk Distribution Matching: Toan Nguyen,

Kien Do,

Bao Duong,

Thin Nguyen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nguyen_2024_WACV, author = {Nguyen, Toan and Do, Kien and Duong, Bao and Nguyen, Thin}, title = {Domain Generalisation via Risk Distribution Matching}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2790-2799} }
Panelformer: Sewing Pattern Reconstruction From 2D Garment Images: Cheng-Hsiu Chen,

Jheng-Wei Su,

Min-Chun Hu,

Chih-Yuan Yao,

Hung-Kuo Chu; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2024_WACV, author = {Chen, Cheng-Hsiu and Su, Jheng-Wei and Hu, Min-Chun and Yao, Chih-Yuan and Chu, Hung-Kuo}, title = {Panelformer: Sewing Pattern Reconstruction From 2D Garment Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {454-463} }
Unsupervised Domain Adaptation of MRI Skull-Stripping Trained on Adult Data to Newborns: Abbas Omidi,

Aida Mohammadshahi,

Neha Gianchandani,

Regan King,

Lara Leijser,

Roberto Souza; [pdf]
[bibtex]
@InProceedings{Omidi_2024_WACV, author = {Omidi, Abbas and Mohammadshahi, Aida and Gianchandani, Neha and King, Regan and Leijser, Lara and Souza, Roberto}, title = {Unsupervised Domain Adaptation of MRI Skull-Stripping Trained on Adult Data to Newborns}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7718-7727} }
Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models: Minxing Zhang,

Ning Yu,

Rui Wen,

Michael Backes,

Yang Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Minxing and Yu, Ning and Wen, Rui and Backes, Michael and Zhang, Yang}, title = {Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4839-4849} }
Multitask Vision-Language Prompt Tuning: Sheng Shen,

Shijia Yang,

Tianjun Zhang,

Bohan Zhai,

Joseph E. Gonzalez,

Kurt Keutzer,

Trevor Darrell; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shen_2024_WACV, author = {Shen, Sheng and Yang, Shijia and Zhang, Tianjun and Zhai, Bohan and Gonzalez, Joseph E. and Keutzer, Kurt and Darrell, Trevor}, title = {Multitask Vision-Language Prompt Tuning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5656-5667} }
ProcSim: Proxy-Based Confidence for Robust Similarity Learning: Oriol Barbany,

Xiaofan Lin,

Muhammet Bastan,

Arnab Dhua; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Barbany_2024_WACV, author = {Barbany, Oriol and Lin, Xiaofan and Bastan, Muhammet and Dhua, Arnab}, title = {ProcSim: Proxy-Based Confidence for Robust Similarity Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1308-1317} }
Hard-Label Based Small Query Black-Box Adversarial Attack: Jeonghwan Park,

Paul Miller,

Niall McLaughlin; [pdf] [supp]
[bibtex]
@InProceedings{Park_2024_WACV, author = {Park, Jeonghwan and Miller, Paul and McLaughlin, Niall}, title = {Hard-Label Based Small Query Black-Box Adversarial Attack}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3986-3995} }
Learning to Detour: Shortcut Mitigating Augmentation for Weakly Supervised Semantic Segmentation: JuneHyoung Kwon,

Eunju Lee,

Yunsung Cho,

YoungBin Kim; [pdf] [supp]
[bibtex]
@InProceedings{Kwon_2024_WACV, author = {Kwon, JuneHyoung and Lee, Eunju and Cho, Yunsung and Kim, YoungBin}, title = {Learning to Detour: Shortcut Mitigating Augmentation for Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {819-828} }
3D Super-Resolution Model for Vehicle Flow Field Enrichment: Thanh Luan Trinh,

Fangge Chen,

Takuya Nanri,

Kei Akasaka; [pdf] [supp]
[bibtex]
@InProceedings{Trinh_2024_WACV, author = {Trinh, Thanh Luan and Chen, Fangge and Nanri, Takuya and Akasaka, Kei}, title = {3D Super-Resolution Model for Vehicle Flow Field Enrichment}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5826-5835} }
Multi-View 3D Object Reconstruction and Uncertainty Modelling With Neural Shape Prior: Ziwei Liao,

Steven L. Waslander; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liao_2024_WACV, author = {Liao, Ziwei and Waslander, Steven L.}, title = {Multi-View 3D Object Reconstruction and Uncertainty Modelling With Neural Shape Prior}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3098-3107} }
Do VSR Models Generalize Beyond LRS3?: Yasser Abdelaziz Dahou Djilali,

Sanath Narayan,

Eustache LeBihan,

Haithem Boussaid,

Ebtesam Almazrouei,

Merouane Debbah; [pdf] [supp]
[bibtex]
@InProceedings{Djilali_2024_WACV, author = {Djilali, Yasser Abdelaziz Dahou and Narayan, Sanath and LeBihan, Eustache and Boussaid, Haithem and Almazrouei, Ebtesam and Debbah, Merouane}, title = {Do VSR Models Generalize Beyond LRS3?}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6635-6644} }
Context in Human Action Through Motion Complementarity: Eadom Dessalene,

Michael Maynord,

Cornelia Fermüller,

Yiannis Aloimonos; [pdf]
[bibtex]
@InProceedings{Dessalene_2024_WACV, author = {Dessalene, Eadom and Maynord, Michael and Ferm\"uller, Cornelia and Aloimonos, Yiannis}, title = {Context in Human Action Through Motion Complementarity}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6531-6540} }
D4: Detection of Adversarial Diffusion Deepfakes Using Disjoint Ensembles: Ashish Hooda,

Neal Mangaokar,

Ryan Feng,

Kassem Fawaz,

Somesh Jha,

Atul Prakash; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hooda_2024_WACV, author = {Hooda, Ashish and Mangaokar, Neal and Feng, Ryan and Fawaz, Kassem and Jha, Somesh and Prakash, Atul}, title = {D4: Detection of Adversarial Diffusion Deepfakes Using Disjoint Ensembles}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3812-3822} }
ProS: Facial Omni-Representation Learning via Prototype-Based Self-Distillation: Xing Di,

Yiyu Zheng,

Xiaoming Liu,

Yu Cheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Di_2024_WACV, author = {Di, Xing and Zheng, Yiyu and Liu, Xiaoming and Cheng, Yu}, title = {ProS: Facial Omni-Representation Learning via Prototype-Based Self-Distillation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6087-6098} }
TCP: Triplet Contrastive-Relationship Preserving for Class-Incremental Learning: Shiyao Li,

Xuefei Ning,

Shanghang Zhang,

Lidong Guo,

Tianchen Zhao,

Huazhong Yang,

Yu Wang; [pdf] [supp]
[bibtex]
@InProceedings{Li_2024_WACV, author = {Li, Shiyao and Ning, Xuefei and Zhang, Shanghang and Guo, Lidong and Zhao, Tianchen and Yang, Huazhong and Wang, Yu}, title = {TCP: Triplet Contrastive-Relationship Preserving for Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2031-2040} }
Self-Supervised Learning for Place Representation Generalization Across Appearance Changes: Mohamed Adel Musallam,

Vincent Gaudillière,

Djamila Aouada; [pdf] [supp]
[bibtex]
@InProceedings{Musallam_2024_WACV, author = {Musallam, Mohamed Adel and Gaudilli\`ere, Vincent and Aouada, Djamila}, title = {Self-Supervised Learning for Place Representation Generalization Across Appearance Changes}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7448-7458} }
Patch-Based Selection and Refinement for Early Object Detection: Tianyi Zhang,

Kishore Kasichainula,

Yaoxin Zhuo,

Baoxin Li,

Jae-Sun Seo,

Yu Cao; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Tianyi and Kasichainula, Kishore and Zhuo, Yaoxin and Li, Baoxin and Seo, Jae-Sun and Cao, Yu}, title = {Patch-Based Selection and Refinement for Early Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {729-738} }
Guided Distillation for Semi-Supervised Instance Segmentation: Tariq Berrada,

Camille Couprie,

Karteek Alahari,

Jakob Verbeek; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Berrada_2024_WACV, author = {Berrada, Tariq and Couprie, Camille and Alahari, Karteek and Verbeek, Jakob}, title = {Guided Distillation for Semi-Supervised Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {475-483} }
Optimizing Long-Term Robot Tracking With Multi-Platform Sensor Fusion: Giuliano Albanese,

Arka Mitra,

Jan-Nico Zaech,

Yupeng Zhao,

Ajad Chhatkuli,

Luc Van Gool; [pdf]
[bibtex]
@InProceedings{Albanese_2024_WACV, author = {Albanese, Giuliano and Mitra, Arka and Zaech, Jan-Nico and Zhao, Yupeng and Chhatkuli, Ajad and Van Gool, Luc}, title = {Optimizing Long-Term Robot Tracking With Multi-Platform Sensor Fusion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6992-7002} }
HyperMix: Out-of-Distribution Detection and Classification in Few-Shot Settings: Nikhil Mehta,

Kevin J. Liang,

Jing Huang,

Fu-Jen Chu,

Li Yin,

Tal Hassner; [pdf] [supp]
[bibtex]
@InProceedings{Mehta_2024_WACV, author = {Mehta, Nikhil and Liang, Kevin J. and Huang, Jing and Chu, Fu-Jen and Yin, Li and Hassner, Tal}, title = {HyperMix: Out-of-Distribution Detection and Classification in Few-Shot Settings}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2410-2420} }
TriPlaneNet: An Encoder for EG3D Inversion: Ananta R. Bhattarai,

Matthias Nießner,

Artem Sevastopolsky; [pdf] [supp]
[bibtex]
@InProceedings{Bhattarai_2024_WACV, author = {Bhattarai, Ananta R. and Nie{\ss}ner, Matthias and Sevastopolsky, Artem}, title = {TriPlaneNet: An Encoder for EG3D Inversion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3055-3065} }
Elusive Images: Beyond Coarse Analysis for Fine-Grained Recognition: Connor Anderson,

Matt Gwilliam,

Evelyn Gaskin,

Ryan Farrell; [pdf] [supp]
[bibtex]
@InProceedings{Anderson_2024_WACV, author = {Anderson, Connor and Gwilliam, Matt and Gaskin, Evelyn and Farrell, Ryan}, title = {Elusive Images: Beyond Coarse Analysis for Fine-Grained Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {829-839} }
Tracking Skiers From the Top to the Bottom: Matteo Dunnhofer,

Luca Sordi,

Niki Martinel,

Christian Micheloni; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dunnhofer_2024_WACV, author = {Dunnhofer, Matteo and Sordi, Luca and Martinel, Niki and Micheloni, Christian}, title = {Tracking Skiers From the Top to the Bottom}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8511-8521} }
BPKD: Boundary Privileged Knowledge Distillation for Semantic Segmentation: Liyang Liu,

Zihan Wang,

Minh Hieu Phan,

Bowen Zhang,

Jinchao Ge,

Yifan Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_WACV, author = {Liu, Liyang and Wang, Zihan and Phan, Minh Hieu and Zhang, Bowen and Ge, Jinchao and Liu, Yifan}, title = {BPKD: Boundary Privileged Knowledge Distillation for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1062-1072} }
DREAM: Visual Decoding From Reversing Human Visual System: Weihao Xia,

Raoul de Charette,

Cengiz Oztireli,

Jing-Hao Xue; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xia_2024_WACV, author = {Xia, Weihao and de Charette, Raoul and Oztireli, Cengiz and Xue, Jing-Hao}, title = {DREAM: Visual Decoding From Reversing Human Visual System}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8226-8235} }
Seeing Stars: Learned Star Localization for Narrow-Field Astrometry: Violet Felt,

Justin Fletcher; [pdf]
[bibtex]
@InProceedings{Felt_2024_WACV, author = {Felt, Violet and Fletcher, Justin}, title = {Seeing Stars: Learned Star Localization for Narrow-Field Astrometry}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8297-8305} }
How Do Deepfakes Move? Motion Magnification for Deepfake Source Detection: Ilke Demir,

Umur Aybars Çiftçi; [pdf] [supp]
[bibtex]
@InProceedings{Demir_2024_WACV, author = {Demir, Ilke and \c{C}ift\c{c}i, Umur Aybars}, title = {How Do Deepfakes Move? Motion Magnification for Deepfake Source Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4780-4790} }
Separable Self and Mixed Attention Transformers for Efficient Object Tracking: Goutam Yelluru Gopal,

Maria A. Amer; [pdf] [arXiv]
[bibtex]
@InProceedings{Gopal_2024_WACV, author = {Gopal, Goutam Yelluru and Amer, Maria A.}, title = {Separable Self and Mixed Attention Transformers for Efficient Object Tracking}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6708-6717} }
CLIPAG: Towards Generator-Free Text-to-Image Generation: Roy Ganz,

Michael Elad; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ganz_2024_WACV, author = {Ganz, Roy and Elad, Michael}, title = {CLIPAG: Towards Generator-Free Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3843-3853} }
Source-Guided Similarity Preservation for Online Person Re-Identification: Hamza Rami,

Jhony H. Giraldo,

Nicolas Winckler,

Stéphane Lathuilière; [pdf] [supp]
[bibtex]
@InProceedings{Rami_2024_WACV, author = {Rami, Hamza and Giraldo, Jhony H. and Winckler, Nicolas and Lathuili\`ere, St\'ephane}, title = {Source-Guided Similarity Preservation for Online Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1711-1720} }
Uncertainty-Weighted Loss Functions for Improved Adversarial Attacks on Semantic Segmentation: Kira Maag,

Asja Fischer; [pdf] [arXiv]
[bibtex]
@InProceedings{Maag_2024_WACV, author = {Maag, Kira and Fischer, Asja}, title = {Uncertainty-Weighted Loss Functions for Improved Adversarial Attacks on Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3906-3914} }
Towards Realistic Generative 3D Face Models: Aashish Rai,

Hiresh Gupta,

Ayush Pandey,

Francisco Vicente Carrasco,

Shingo Jason Takagi,

Amaury Aubel,

Daeil Kim,

Aayush Prakash,

Fernando De la Torre; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rai_2024_WACV, author = {Rai, Aashish and Gupta, Hiresh and Pandey, Ayush and Carrasco, Francisco Vicente and Takagi, Shingo Jason and Aubel, Amaury and Kim, Daeil and Prakash, Aayush and De la Torre, Fernando}, title = {Towards Realistic Generative 3D Face Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3738-3748} }
Domain Generalization by Rejecting Extreme Augmentations: Masih Aminbeidokhti,

Fidel A. Guerrero Peña,

Heitor Rapela Medeiros,

Thomas Dubail,

Eric Granger,

Marco Pedersoli; [pdf] [supp]
[bibtex]
@InProceedings{Aminbeidokhti_2024_WACV, author = {Aminbeidokhti, Masih and Pe\~na, Fidel A. Guerrero and Medeiros, Heitor Rapela and Dubail, Thomas and Granger, Eric and Pedersoli, Marco}, title = {Domain Generalization by Rejecting Extreme Augmentations}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2215-2225} }
Towards Accurate Disease Segmentation in Plant Images: A Comprehensive Dataset Creation and Network Evaluation: Komuravelli Prashanth,

Jaladi Sri Harsha,

Sivapuram Arun Kumar,

Jaladi Srilekha; [pdf] [supp]
[bibtex]
@InProceedings{Prashanth_2024_WACV, author = {Prashanth, Komuravelli and Harsha, Jaladi Sri and Kumar, Sivapuram Arun and Srilekha, Jaladi}, title = {Towards Accurate Disease Segmentation in Plant Images: A Comprehensive Dataset Creation and Network Evaluation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7086-7094} }
Deep Subdomain Alignment for Cross-Domain Image Classification: Yewei Zhao,

Hu Han,

Shiguang Shan,

Xilin Chen; [pdf]
[bibtex]
@InProceedings{Zhao_2024_WACV, author = {Zhao, Yewei and Han, Hu and Shan, Shiguang and Chen, Xilin}, title = {Deep Subdomain Alignment for Cross-Domain Image Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2820-2829} }
Classifying Cable Tendency With Semantic Segmentation by Utilizing Real and Simulated RGB Data: Pei-Chun Chien,

Powei Liao,

Eiji Fukuzawa,

Jun Ohya; [pdf]
[bibtex]
@InProceedings{Chien_2024_WACV, author = {Chien, Pei-Chun and Liao, Powei and Fukuzawa, Eiji and Ohya, Jun}, title = {Classifying Cable Tendency With Semantic Segmentation by Utilizing Real and Simulated RGB Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8430-8438} }
Visual Narratives: Large-Scale Hierarchical Classification of Art-Historical Images: Matthias Springstein,

Stefanie Schneider,

Javad Rahnama,

Julian Stalter,

Maximilian Kristen,

Eric Müller-Budack,

Ralph Ewerth; [pdf] [supp]
[bibtex]
@InProceedings{Springstein_2024_WACV, author = {Springstein, Matthias and Schneider, Stefanie and Rahnama, Javad and Stalter, Julian and Kristen, Maximilian and M\"uller-Budack, Eric and Ewerth, Ralph}, title = {Visual Narratives: Large-Scale Hierarchical Classification of Art-Historical Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7220-7230} }
Real-Time Weakly Supervised Video Anomaly Detection: Hamza Karim,

Keval Doshi,

Yasin Yilmaz; [pdf]
[bibtex]
@InProceedings{Karim_2024_WACV, author = {Karim, Hamza and Doshi, Keval and Yilmaz, Yasin}, title = {Real-Time Weakly Supervised Video Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6848-6856} }
C2AIR: Consolidated Compact Aerial Image Haze Removal: Ashutosh Kulkarni,

Shruti S. Phutke,

Santosh Kumar Vipparthi,

Subrahmanyam Murala; [pdf] [supp]
[bibtex]
@InProceedings{Kulkarni_2024_WACV, author = {Kulkarni, Ashutosh and Phutke, Shruti S. and Vipparthi, Santosh Kumar and Murala, Subrahmanyam}, title = {C2AIR: Consolidated Compact Aerial Image Haze Removal}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {749-758} }
Permutation-Aware Activity Segmentation via Unsupervised Frame-To-Segment Alignment: Quoc-Huy Tran,

Ahmed Mehmood,

Muhammad Ahmed,

Muhammad Naufil,

Anas Zafar,

Andrey Konin,

Zeeshan Zia; [pdf] [supp]
[bibtex]
@InProceedings{Tran_2024_WACV, author = {Tran, Quoc-Huy and Mehmood, Ahmed and Ahmed, Muhammad and Naufil, Muhammad and Zafar, Anas and Konin, Andrey and Zia, Zeeshan}, title = {Permutation-Aware Activity Segmentation via Unsupervised Frame-To-Segment Alignment}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6426-6436} }
Prototype Learning for Explainable Brain Age Prediction: Linde S. Hesse,

Nicola K. Dinsdale,

Ana I. L. Namburete; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hesse_2024_WACV, author = {Hesse, Linde S. and Dinsdale, Nicola K. and Namburete, Ana I. L.}, title = {Prototype Learning for Explainable Brain Age Prediction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7903-7913} }
Exploiting CLIP for Zero-Shot HOI Detection Requires Knowledge Distillation at Multiple Levels: Bo Wan,

Tinne Tuytelaars; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wan_2024_WACV, author = {Wan, Bo and Tuytelaars, Tinne}, title = {Exploiting CLIP for Zero-Shot HOI Detection Requires Knowledge Distillation at Multiple Levels}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1805-1815} }
SDNet: An Extremely Efficient Portrait Matting Model via Self-Distillation: Ziwen Li,

Bo Xu,

Jiake Xie,

Yong Tang,

Cheng Lu; [pdf]
[bibtex]
@InProceedings{Li_2024_WACV, author = {Li, Ziwen and Xu, Bo and Xie, Jiake and Tang, Yong and Lu, Cheng}, title = {SDNet: An Extremely Efficient Portrait Matting Model via Self-Distillation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5625-5634} }
Hybrid Neural Diffeomorphic Flow for Shape Representation and Generation via Triplane: Kun Han,

Shanlin Sun,

Thanh-Tung Le,

Xiangyi Yan,

Haoyu Ma,

Chenyu You,

Xiaohui Xie; [pdf] [supp]
[bibtex]
@InProceedings{Han_2024_WACV, author = {Han, Kun and Sun, Shanlin and Le, Thanh-Tung and Yan, Xiangyi and Ma, Haoyu and You, Chenyu and Xie, Xiaohui}, title = {Hybrid Neural Diffeomorphic Flow for Shape Representation and Generation via Triplane}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7707-7717} }
Volumetric Disentanglement for 3D Scene Manipulation: Sagie Benaim,

Frederik Warburg,

Peter Ebert Christensen,

Serge Belongie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Benaim_2024_WACV, author = {Benaim, Sagie and Warburg, Frederik and Christensen, Peter Ebert and Belongie, Serge}, title = {Volumetric Disentanglement for 3D Scene Manipulation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8667-8677} }
CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learning: Zhaoheng Zheng,

Haidong Zhu,

Ram Nevatia; [pdf] [arXiv]
[bibtex]
@InProceedings{Zheng_2024_WACV, author = {Zheng, Zhaoheng and Zhu, Haidong and Nevatia, Ram}, title = {CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1721-1731} }
ClusterFix: A Cluster-Based Debiasing Approach Without Protected-Group Supervision: Giacomo Capitani,

Federico Bolelli,

Angelo Porrello,

Simone Calderara,

Elisa Ficarra; [pdf] [supp]
[bibtex]
@InProceedings{Capitani_2024_WACV, author = {Capitani, Giacomo and Bolelli, Federico and Porrello, Angelo and Calderara, Simone and Ficarra, Elisa}, title = {ClusterFix: A Cluster-Based Debiasing Approach Without Protected-Group Supervision}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4870-4879} }
Simple Post-Training Robustness Using Test Time Augmentations and Random Forest: Gilad Cohen,

Raja Giryes; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cohen_2024_WACV, author = {Cohen, Gilad and Giryes, Raja}, title = {Simple Post-Training Robustness Using Test Time Augmentations and Random Forest}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3996-4006} }
Learning Low-Rank Latent Spaces With Simple Deterministic Autoencoder: Theoretical and Empirical Insights: Alokendu Mazumder,

Tirthajit Baruah,

Bhartendu Kumar,

Rishab Sharma,

Vishwajeet Pattanaik,

Punit Rathore; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mazumder_2024_WACV, author = {Mazumder, Alokendu and Baruah, Tirthajit and Kumar, Bhartendu and Sharma, Rishab and Pattanaik, Vishwajeet and Rathore, Punit}, title = {Learning Low-Rank Latent Spaces With Simple Deterministic Autoencoder: Theoretical and Empirical Insights}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2851-2860} }
A Hybrid Graph Network for Complex Activity Detection in Video: Salman Khan,

Izzeddin Teeti,

Andrew Bradley,

Mohamed Elhoseiny,

Fabio Cuzzolin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Khan_2024_WACV, author = {Khan, Salman and Teeti, Izzeddin and Bradley, Andrew and Elhoseiny, Mohamed and Cuzzolin, Fabio}, title = {A Hybrid Graph Network for Complex Activity Detection in Video}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6762-6772} }
Movie Genre Classification by Language Augmentation and Shot Sampling: Zhongping Zhang,

Yiwen Gu,

Bryan A. Plummer,

Xin Miao,

Jiayi Liu,

Huayan Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Zhongping and Gu, Yiwen and Plummer, Bryan A. and Miao, Xin and Liu, Jiayi and Wang, Huayan}, title = {Movie Genre Classification by Language Augmentation and Shot Sampling}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7275-7285} }
Automated Camera Calibration via Homography Estimation With GNNs: Giacomo D'Amicantonio,

Egor Bondarev,

Peter H.N. de With; [pdf] [arXiv]
[bibtex]
@InProceedings{D'Amicantonio_2024_WACV, author = {D'Amicantonio, Giacomo and Bondarev, Egor and de With, Peter H.N.}, title = {Automated Camera Calibration via Homography Estimation With GNNs}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5876-5883} }
Randomized Adversarial Style Perturbations for Domain Generalization: Taehoon Kim,

Bohyung Han; [pdf] [arXiv]
[bibtex]
@InProceedings{Kim_2024_WACV, author = {Kim, Taehoon and Han, Bohyung}, title = {Randomized Adversarial Style Perturbations for Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2317-2325} }
C-CLIP: Contrastive Image-Text Encoders To Close the Descriptive-Commentative Gap: William Theisen,

Walter J. Scheirer; [pdf]
[bibtex]
@InProceedings{Theisen_2024_WACV, author = {Theisen, William and Scheirer, Walter J.}, title = {C-CLIP: Contrastive Image-Text Encoders To Close the Descriptive-Commentative Gap}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7241-7250} }
LInKs "Lifting Independent Keypoints" - Partial Pose Lifting for Occlusion Handling With Improved Accuracy in 2D-3D Human Pose Estimation: Peter Hardy,

Hansung Kim; [pdf] [supp]
[bibtex]
@InProceedings{Hardy_2024_WACV, author = {Hardy, Peter and Kim, Hansung}, title = {LInKs ''Lifting Independent Keypoints'' - Partial Pose Lifting for Occlusion Handling With Improved Accuracy in 2D-3D Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3426-3435} }
Beyond Classification: Definition and Density-Based Estimation of Calibration in Object Detection: Teodora Popordanoska,

Aleksei Tiulpin,

Matthew B. Blaschko; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Popordanoska_2024_WACV, author = {Popordanoska, Teodora and Tiulpin, Aleksei and Blaschko, Matthew B.}, title = {Beyond Classification: Definition and Density-Based Estimation of Calibration in Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {585-594} }
PrivObfNet: A Weakly Supervised Semantic Segmentation Model for Data Protection: ChiatPin Tay,

Vigneshwaran Subbaraju,

Thivya Kandappu; [pdf]
[bibtex]
@InProceedings{Tay_2024_WACV, author = {Tay, ChiatPin and Subbaraju, Vigneshwaran and Kandappu, Thivya}, title = {PrivObfNet: A Weakly Supervised Semantic Segmentation Model for Data Protection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2421-2431} }
Toward Planet-Wide Traffic Camera Calibration: Khiem Vuong,

Robert Tamburo,

Srinivasa G. Narasimhan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Vuong_2024_WACV, author = {Vuong, Khiem and Tamburo, Robert and Narasimhan, Srinivasa G.}, title = {Toward Planet-Wide Traffic Camera Calibration}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8553-8562} }
3D Human Pose Estimation With Two-Step Mixed-Training Strategy: Yingfeng Wang,

Zhengwei Wang,

Muyu Li,

Hong Yan; [pdf]
[bibtex]
@InProceedings{Wang_2024_WACV, author = {Wang, Yingfeng and Wang, Zhengwei and Li, Muyu and Yan, Hong}, title = {3D Human Pose Estimation With Two-Step Mixed-Training Strategy}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3332-3341} }
Learning-Based Spotlight Position Optimization for Non-Line-of-Sight Human Localization and Posture Classification: Sreenithy Chandran,

Tatsuya Yatagawa,

Hiroyuki Kubo,

Suren Jayasuriya; [pdf] [supp]
[bibtex]
@InProceedings{Chandran_2024_WACV, author = {Chandran, Sreenithy and Yatagawa, Tatsuya and Kubo, Hiroyuki and Jayasuriya, Suren}, title = {Learning-Based Spotlight Position Optimization for Non-Line-of-Sight Human Localization and Posture Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4218-4227} }
Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic Segmentation: Joshua Niemeijer,

Manuel Schwonberg,

Jan-Aike Termöhlen,

Nico M. Schmidt,

Tim Fingscheidt; [pdf] [supp]
[bibtex]
@InProceedings{Niemeijer_2024_WACV, author = {Niemeijer, Joshua and Schwonberg, Manuel and Term\"ohlen, Jan-Aike and Schmidt, Nico M. and Fingscheidt, Tim}, title = {Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2830-2840} }
Temporally-Consistent Video Semantic Segmentation With Bidirectional Occlusion-Guided Feature Propagation: Razieh Kaviani Baghbaderani,

Yuanxin Li,

Shuangquan Wang,

Hairong Qi; [pdf] [supp]
[bibtex]
@InProceedings{Baghbaderani_2024_WACV, author = {Baghbaderani, Razieh Kaviani and Li, Yuanxin and Wang, Shuangquan and Qi, Hairong}, title = {Temporally-Consistent Video Semantic Segmentation With Bidirectional Occlusion-Guided Feature Propagation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {685-695} }
MICS: Midpoint Interpolation To Learn Compact and Separated Representations for Few-Shot Class-Incremental Learning: Solang Kim,

Yuho Jeong,

Joon Sung Park,

Sung Whan Yoon; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2024_WACV, author = {Kim, Solang and Jeong, Yuho and Park, Joon Sung and Yoon, Sung Whan}, title = {MICS: Midpoint Interpolation To Learn Compact and Separated Representations for Few-Shot Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2236-2245} }
ParticleNeRF: A Particle-Based Encoding for Online Neural Radiance Fields: Jad Abou-Chakra,

Feras Dayoub,

Niko Sünderhauf; [pdf] [supp]
[bibtex]
@InProceedings{Abou-Chakra_2024_WACV, author = {Abou-Chakra, Jad and Dayoub, Feras and S\"underhauf, Niko}, title = {ParticleNeRF: A Particle-Based Encoding for Online Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5975-5984} }
Residual Graph Convolutional Network for Bird's-Eye-View Semantic Segmentation: Qiuxiao Chen,

Xiaojun Qi; [pdf]
[bibtex]
@InProceedings{Chen_2024_WACV, author = {Chen, Qiuxiao and Qi, Xiaojun}, title = {Residual Graph Convolutional Network for Bird's-Eye-View Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3324-3331} }
Group-Wise Contrastive Bottleneck for Weakly-Supervised Visual Representation Learning: Boon Peng Yap,

Beng Koon Ng; [pdf] [supp]
[bibtex]
@InProceedings{Yap_2024_WACV, author = {Yap, Boon Peng and Ng, Beng Koon}, title = {Group-Wise Contrastive Bottleneck for Weakly-Supervised Visual Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2246-2255} }
Leveraging Synthetic Data To Learn Video Stabilization Under Adverse Conditions: Abdulrahman Kerim,

Washington L. S. Ramos,

Leandro Soriano Marcolino,

Erickson R. Nascimento,

Richard Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kerim_2024_WACV, author = {Kerim, Abdulrahman and Ramos, Washington L. S. and Marcolino, Leandro Soriano and Nascimento, Erickson R. and Jiang, Richard}, title = {Leveraging Synthetic Data To Learn Video Stabilization Under Adverse Conditions}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6931-6940} }
Generation of Upright Panoramic Image From Non-Upright Panoramic Image: Jingguo Liu,

Heyu Chen,

Shigang Li,

Jianfeng Li; [pdf]
[bibtex]
@InProceedings{Liu_2024_WACV, author = {Liu, Jingguo and Chen, Heyu and Li, Shigang and Li, Jianfeng}, title = {Generation of Upright Panoramic Image From Non-Upright Panoramic Image}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5261-5270} }
RADIO: Reference-Agnostic Dubbing Video Synthesis: Dongyeun Lee,

Chaewon Kim,

Sangjoon Yu,

Jaejun Yoo,

Gyeong-Moon Park; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2024_WACV, author = {Lee, Dongyeun and Kim, Chaewon and Yu, Sangjoon and Yoo, Jaejun and Park, Gyeong-Moon}, title = {RADIO: Reference-Agnostic Dubbing Video Synthesis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4168-4178} }
A Coarse-To-Fine Pseudo-Labeling (C2FPL) Framework for Unsupervised Video Anomaly Detection: Anas Al-lahham,

Nurbek Tastan,

Muhammad Zaigham Zaheer,

Karthik Nandakumar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Al-lahham_2024_WACV, author = {Al-lahham, Anas and Tastan, Nurbek and Zaheer, Muhammad Zaigham and Nandakumar, Karthik}, title = {A Coarse-To-Fine Pseudo-Labeling (C2FPL) Framework for Unsupervised Video Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6793-6802} }
Occlusion Sensitivity Analysis With Augmentation Subspace Perturbation in Deep Feature Space: Pedro H. V. Valois,

Koichiro Niinuma,

Kazuhiro Fukui; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Valois_2024_WACV, author = {Valois, Pedro H. V. and Niinuma, Koichiro and Fukui, Kazuhiro}, title = {Occlusion Sensitivity Analysis With Augmentation Subspace Perturbation in Deep Feature Space}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4829-4838} }
PhISH-Net: Physics Inspired System for High Resolution Underwater Image Enhancement: Aditya Chandrasekar,

Manogna Sreenivas,

Soma Biswas; [pdf] [supp]
[bibtex]
@InProceedings{Chandrasekar_2024_WACV, author = {Chandrasekar, Aditya and Sreenivas, Manogna and Biswas, Soma}, title = {PhISH-Net: Physics Inspired System for High Resolution Underwater Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1506-1516} }
MixtureGrowth: Growing Neural Networks by Recombining Learned Parameters: Chau Pham,

Piotr Teterwak,

Soren Nelson,

Bryan A. Plummer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pham_2024_WACV, author = {Pham, Chau and Teterwak, Piotr and Nelson, Soren and Plummer, Bryan A.}, title = {MixtureGrowth: Growing Neural Networks by Recombining Learned Parameters}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2800-2809} }
Zero-Shot Building Attribute Extraction From Large-Scale Vision and Language Models: Fei Pan,

Sangryul Jeon,

Brian Wang,

Frank Mckenna,

Stella X. Yu; [pdf]
[bibtex]
@InProceedings{Pan_2024_WACV, author = {Pan, Fei and Jeon, Sangryul and Wang, Brian and Mckenna, Frank and Yu, Stella X.}, title = {Zero-Shot Building Attribute Extraction From Large-Scale Vision and Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8647-8656} }
SimA: Simple Softmax-Free Attention for Vision Transformers: Soroush Abbasi Koohpayegani,

Hamed Pirsiavash; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Koohpayegani_2024_WACV, author = {Koohpayegani, Soroush Abbasi and Pirsiavash, Hamed}, title = {SimA: Simple Softmax-Free Attention for Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2607-2617} }
POP-VQA - Privacy Preserving, On-Device, Personalized Visual Question Answering: Pragya Paramita Sahu,

Abhishek Raut,

Jagdish Singh Samant,

Mahesh Gorijala,

Vignesh Lakshminarayanan,

Pinaki Bhaskar; [pdf] [supp]
[bibtex]
@InProceedings{Sahu_2024_WACV, author = {Sahu, Pragya Paramita and Raut, Abhishek and Samant, Jagdish Singh and Gorijala, Mahesh and Lakshminarayanan, Vignesh and Bhaskar, Pinaki}, title = {POP-VQA - Privacy Preserving, On-Device, Personalized Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8470-8479} }
Complementary-Contradictory Feature Regularization Against Multimodal Overfitting: Antonio Tejero-de-Pablos; [pdf] [supp]
[bibtex]
@InProceedings{Tejero-de-Pablos_2024_WACV, author = {Tejero-de-Pablos, Antonio}, title = {Complementary-Contradictory Feature Regularization Against Multimodal Overfitting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5679-5688} }
Appearance-Based Curriculum for Semi-Supervised Learning With Multi-Angle Unlabeled Data: Yuki Tanaka,

Shuhei M. Yoshida,

Takashi Shibata,

Makoto Terao,

Takayuki Okatani,

Masashi Sugiyama; [pdf] [supp]
[bibtex]
@InProceedings{Tanaka_2024_WACV, author = {Tanaka, Yuki and Yoshida, Shuhei M. and Shibata, Takashi and Terao, Makoto and Okatani, Takayuki and Sugiyama, Masashi}, title = {Appearance-Based Curriculum for Semi-Supervised Learning With Multi-Angle Unlabeled Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2780-2789} }
Incorporating Physics Principles for Precise Human Motion Prediction: Yufei Zhang,

Jeffrey O. Kephart,

Qiang Ji; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Yufei and Kephart, Jeffrey O. and Ji, Qiang}, title = {Incorporating Physics Principles for Precise Human Motion Prediction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6164-6174} }
MuSHRoom: Multi-Sensor Hybrid Room Dataset for Joint 3D Reconstruction and Novel View Synthesis: Xuqian Ren,

Wenjia Wang,

Dingding Cai,

Tuuli Tuominen,

Juho Kannala,

Esa Rahtu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ren_2024_WACV, author = {Ren, Xuqian and Wang, Wenjia and Cai, Dingding and Tuominen, Tuuli and Kannala, Juho and Rahtu, Esa}, title = {MuSHRoom: Multi-Sensor Hybrid Room Dataset for Joint 3D Reconstruction and Novel View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4508-4517} }
POISE: Pose Guided Human Silhouette Extraction Under Occlusions: Arindam Dutta,

Rohit Lal,

Dripta S. Raychaudhuri,

Calvin-Khang Ta,

Amit K. Roy-Chowdhury; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dutta_2024_WACV, author = {Dutta, Arindam and Lal, Rohit and Raychaudhuri, Dripta S. and Ta, Calvin-Khang and Roy-Chowdhury, Amit K.}, title = {POISE: Pose Guided Human Silhouette Extraction Under Occlusions}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6153-6163} }
Shape-Guided Diffusion With Inside-Outside Attention: Dong Huk Park,

Grace Luo,

Clayton Toste,

Samaneh Azadi,

Xihui Liu,

Maka Karalashvili,

Anna Rohrbach,

Trevor Darrell; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2024_WACV, author = {Park, Dong Huk and Luo, Grace and Toste, Clayton and Azadi, Samaneh and Liu, Xihui and Karalashvili, Maka and Rohrbach, Anna and Darrell, Trevor}, title = {Shape-Guided Diffusion With Inside-Outside Attention}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4198-4207} }
Learning Visual Body-Shape-Aware Embeddings for Fashion Compatibility: Kaicheng Pang,

Xingxing Zou,

Waikeung Wong; [pdf] [supp]
[bibtex]
@InProceedings{Pang_2024_WACV, author = {Pang, Kaicheng and Zou, Xingxing and Wong, Waikeung}, title = {Learning Visual Body-Shape-Aware Embeddings for Fashion Compatibility}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8056-8065} }
Unsupervised Exemplar-Based Image-to-Image Translation and Cascaded Vision Transformers for Tagged and Untagged Cardiac Cine MRI Registration: Meng Ye,

Mikael Kanski,

Dong Yang,

Leon Axel,

Dimitris Metaxas; [pdf] [supp]
[bibtex]
@InProceedings{Ye_2024_WACV, author = {Ye, Meng and Kanski, Mikael and Yang, Dong and Axel, Leon and Metaxas, Dimitris}, title = {Unsupervised Exemplar-Based Image-to-Image Translation and Cascaded Vision Transformers for Tagged and Untagged Cardiac Cine MRI Registration}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7644-7654} }
Spectroformer: Multi-Domain Query Cascaded Transformer Network for Underwater Image Enhancement: Raqib Khan,

Priyanka Mishra,

Nancy Mehta,

Shruti S. Phutke,

Santosh Kumar Vipparthi,

Sukumar Nandi,

Subrahmanyam Murala; [pdf] [supp]
[bibtex]
@InProceedings{Khan_2024_WACV, author = {Khan, Raqib and Mishra, Priyanka and Mehta, Nancy and Phutke, Shruti S. and Vipparthi, Santosh Kumar and Nandi, Sukumar and Murala, Subrahmanyam}, title = {Spectroformer: Multi-Domain Query Cascaded Transformer Network for Underwater Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1454-1463} }
Removing the Quality Tax in Controllable Face Generation: Yiwen Huang,

Zhiqiu Yu,

Xinjie Yi,

Yue Wang,

James Tompkin; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2024_WACV, author = {Huang, Yiwen and Yu, Zhiqiu and Yi, Xinjie and Wang, Yue and Tompkin, James}, title = {Removing the Quality Tax in Controllable Face Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5364-5373} }
On Manipulating Scene Text in the Wild With Diffusion Models: Joshua Santoso,

Christian Simon,

Williem; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Santoso_2024_WACV, author = {Santoso, Joshua and Simon, Christian and Williem}, title = {On Manipulating Scene Text in the Wild With Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5202-5211} }
Improved Techniques for Quantizing Deep Networks With Adaptive Bit-Widths: Ximeng Sun,

Rameswar Panda,

Chun-Fu Richard Chen,

Naigang Wang,

Bowen Pan,

Aude Oliva,

Rogerio Feris,

Kate Saenko; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2024_WACV, author = {Sun, Ximeng and Panda, Rameswar and Chen, Chun-Fu Richard and Wang, Naigang and Pan, Bowen and Oliva, Aude and Feris, Rogerio and Saenko, Kate}, title = {Improved Techniques for Quantizing Deep Networks With Adaptive Bit-Widths}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {957-967} }
Mining and Unifying Heterogeneous Contrastive Relations for Weakly-Supervised Actor-Action Segmentation: Bin Duan,

Hao Tang,

Changchang Sun,

Ye Zhu,

Yan Yan; [pdf]
[bibtex]
@InProceedings{Duan_2024_WACV, author = {Duan, Bin and Tang, Hao and Sun, Changchang and Zhu, Ye and Yan, Yan}, title = {Mining and Unifying Heterogeneous Contrastive Relations for Weakly-Supervised Actor-Action Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {494-503} }
Rethinking Knowledge Distillation With Raw Features for Semantic Segmentation: Tao Liu,

Chenshu Chen,

Xi Yang,

Wenming Tan; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2024_WACV, author = {Liu, Tao and Chen, Chenshu and Yang, Xi and Tan, Wenming}, title = {Rethinking Knowledge Distillation With Raw Features for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1155-1164} }
Fully-Automatic Reflection Removal for 360-Degree Images: Jonghyuk Park,

Hyeona Kim,

Eunpil Park,

Jae-Young Sim; [pdf] [supp]
[bibtex]
@InProceedings{Park_2024_WACV, author = {Park, Jonghyuk and Kim, Hyeona and Park, Eunpil and Sim, Jae-Young}, title = {Fully-Automatic Reflection Removal for 360-Degree Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1609-1617} }
MITFAS: Mutual Information Based Temporal Feature Alignment and Sampling for Aerial Video Action Recognition: Ruiqi Xian,

Xijun Wang,

Dinesh Manocha; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xian_2024_WACV, author = {Xian, Ruiqi and Wang, Xijun and Manocha, Dinesh}, title = {MITFAS: Mutual Information Based Temporal Feature Alignment and Sampling for Aerial Video Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6625-6634} }
Multimodal Deep Learning for Remote Stress Estimation Using CCT-LSTM: Sayyedjavad Ziaratnia,

Tipporn Laohakangvalvit,

Midori Sugaya,

Peeraya Sripian; [pdf]
[bibtex]
@InProceedings{Ziaratnia_2024_WACV, author = {Ziaratnia, Sayyedjavad and Laohakangvalvit, Tipporn and Sugaya, Midori and Sripian, Peeraya}, title = {Multimodal Deep Learning for Remote Stress Estimation Using CCT-LSTM}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8336-8344} }
Let the Beat Follow You - Creating Interactive Drum Sounds From Body Rhythm: Xiulong Liu,

Kun Su,

Eli Shlizerman; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2024_WACV, author = {Liu, Xiulong and Su, Kun and Shlizerman, Eli}, title = {Let the Beat Follow You - Creating Interactive Drum Sounds From Body Rhythm}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7187-7197} }
A Visual Active Search Framework for Geospatial Exploration: Anindya Sarkar,

Michael Lanier,

Scott Alfeld,

Jiarui Feng,

Roman Garnett,

Nathan Jacobs,

Yevgeniy Vorobeychik; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sarkar_2024_WACV, author = {Sarkar, Anindya and Lanier, Michael and Alfeld, Scott and Feng, Jiarui and Garnett, Roman and Jacobs, Nathan and Vorobeychik, Yevgeniy}, title = {A Visual Active Search Framework for Geospatial Exploration}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8316-8325} }
ShARc: Shape and Appearance Recognition for Person Identification In-the-Wild: Haidong Zhu,

Wanrong Zheng,

Zhaoheng Zheng,

Ram Nevatia; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhu_2024_WACV, author = {Zhu, Haidong and Zheng, Wanrong and Zheng, Zhaoheng and Nevatia, Ram}, title = {ShARc: Shape and Appearance Recognition for Person Identification In-the-Wild}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6290-6300} }
DocReal: Robust Document Dewarping of Real-Life Images via Attention-Enhanced Control Point Prediction: Fangchen Yu,

Yina Xie,

Lei Wu,

Yafei Wen,

Guozhi Wang,

Shuai Ren,

Xiaoxin Chen,

Jianfeng Mao,

Wenye Li; [pdf] [supp]
[bibtex]
@InProceedings{Yu_2024_WACV, author = {Yu, Fangchen and Xie, Yina and Wu, Lei and Wen, Yafei and Wang, Guozhi and Ren, Shuai and Chen, Xiaoxin and Mao, Jianfeng and Li, Wenye}, title = {DocReal: Robust Document Dewarping of Real-Life Images via Attention-Enhanced Control Point Prediction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {665-674} }
Multi-Level Attention Aggregation for Aesthetic Face Relighting: Hemanth Pidaparthy,

Abhay Chauhan,

Pavan Sudheendra; [pdf] [supp]
[bibtex]
@InProceedings{Pidaparthy_2024_WACV, author = {Pidaparthy, Hemanth and Chauhan, Abhay and Sudheendra, Pavan}, title = {Multi-Level Attention Aggregation for Aesthetic Face Relighting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4057-4066} }
Learning Residual Elastic Warps for Image Stitching Under Dirichlet Boundary Condition: Minsu Kim,

Yongjun Lee,

Woo Kyoung Han,

Kyong Hwan Jin; [pdf] [arXiv]
[bibtex]
@InProceedings{Kim_2024_WACV, author = {Kim, Minsu and Lee, Yongjun and Han, Woo Kyoung and Jin, Kyong Hwan}, title = {Learning Residual Elastic Warps for Image Stitching Under Dirichlet Boundary Condition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4016-4024} }
Interactive Segmentation for Diverse Gesture Types Without Context: Josh Myers-Dean,

Yifei Fan,

Brian Price,

Wilson Chan,

Danna Gurari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Myers-Dean_2024_WACV, author = {Myers-Dean, Josh and Fan, Yifei and Price, Brian and Chan, Wilson and Gurari, Danna}, title = {Interactive Segmentation for Diverse Gesture Types Without Context}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7198-7208} }
Customizing 360-Degree Panoramas Through Text-to-Image Diffusion Models: Hai Wang,

Xiaoyu Xiang,

Yuchen Fan,

Jing-Hao Xue; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_WACV, author = {Wang, Hai and Xiang, Xiaoyu and Fan, Yuchen and Xue, Jing-Hao}, title = {Customizing 360-Degree Panoramas Through Text-to-Image Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4933-4943} }
Temporal Context Enhanced Referring Video Object Segmentation: Xiao Hu,

Basavaraj Hampiholi,

Heiko Neumann,

Jochen Lang; [pdf] [supp]
[bibtex]
@InProceedings{Hu_2024_WACV, author = {Hu, Xiao and Hampiholi, Basavaraj and Neumann, Heiko and Lang, Jochen}, title = {Temporal Context Enhanced Referring Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5574-5583} }
Revisiting Token Pruning for Object Detection and Instance Segmentation: Yifei Liu,

Mathias Gehrig,

Nico Messikommer,

Marco Cannici,

Davide Scaramuzza; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_WACV, author = {Liu, Yifei and Gehrig, Mathias and Messikommer, Nico and Cannici, Marco and Scaramuzza, Davide}, title = {Revisiting Token Pruning for Object Detection and Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2658-2668} }
AssemblyNet: A Point Cloud Dataset and Benchmark for Predicting Part Directions in an Exploded Layout: Jesper Gaarsdal,

Joakim Bruslund Haurum,

Sune Wolff,

Claus Brøndgaard Madsen; [pdf] [supp]
[bibtex]
@InProceedings{Gaarsdal_2024_WACV, author = {Gaarsdal, Jesper and Haurum, Joakim Bruslund and Wolff, Sune and Madsen, Claus Br{\o}ndgaard}, title = {AssemblyNet: A Point Cloud Dataset and Benchmark for Predicting Part Directions in an Exploded Layout}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5836-5845} }
Location-Aware Self-Supervised Transformers for Semantic Segmentation: Mathilde Caron,

Neil Houlsby,

Cordelia Schmid; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Caron_2024_WACV, author = {Caron, Mathilde and Houlsby, Neil and Schmid, Cordelia}, title = {Location-Aware Self-Supervised Transformers for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {117-127} }
Self-Supervised Learning for Visual Relationship Detection Through Masked Bounding Box Reconstruction: Zacharias Anastasakis,

Dimitrios Mallis,

Markos Diomataris,

George Alexandridis,

Stefanos Kollias,

Vassilis Pitsikalis; [pdf] [arXiv]
[bibtex]
@InProceedings{Anastasakis_2024_WACV, author = {Anastasakis, Zacharias and Mallis, Dimitrios and Diomataris, Markos and Alexandridis, George and Kollias, Stefanos and Pitsikalis, Vassilis}, title = {Self-Supervised Learning for Visual Relationship Detection Through Masked Bounding Box Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1206-1215} }
Real-Time 6-DoF Pose Estimation by an Event-Based Camera Using Active LED Markers: Gerald Ebmer,

Adam Loch,

Minh Nhat Vu,

Roberto Mecca,

Germain Haessig,

Christian Hartl-Nesic,

Markus Vincze,

Andreas Kugi; [pdf]
[bibtex]
@InProceedings{Ebmer_2024_WACV, author = {Ebmer, Gerald and Loch, Adam and Vu, Minh Nhat and Mecca, Roberto and Haessig, Germain and Hartl-Nesic, Christian and Vincze, Markus and Kugi, Andreas}, title = {Real-Time 6-DoF Pose Estimation by an Event-Based Camera Using Active LED Markers}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8137-8146} }
P-Age: Pexels Dataset for Robust Spatio-Temporal Apparent Age Classification: Abid Ali,

Ashish Marisetty,

François Brémond; [pdf] [supp]
[bibtex]
@InProceedings{Ali_2024_WACV, author = {Ali, Abid and Marisetty, Ashish and Br\'emond, Fran\c{c}ois}, title = {P-Age: Pexels Dataset for Robust Spatio-Temporal Apparent Age Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8606-8615} }
SSVOD: Semi-Supervised Video Object Detection With Sparse Annotations: Tanvir Mahmud,

Chun-Hao Liu,

Burhaneddin Yaman,

Diana Marculescu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mahmud_2024_WACV, author = {Mahmud, Tanvir and Liu, Chun-Hao and Yaman, Burhaneddin and Marculescu, Diana}, title = {SSVOD: Semi-Supervised Video Object Detection With Sparse Annotations}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6773-6782} }
Deep Optics for Optomechanical Control Policy Design: Justin Fletcher; [pdf]
[bibtex]
@InProceedings{Fletcher_2024_WACV, author = {Fletcher, Justin}, title = {Deep Optics for Optomechanical Control Policy Design}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8306-8315} }
A Generative Multi-Resolution Pyramid and Normal-Conditioning 3D Cloth Draping: Hunor Laczkó,

Meysam Madadi,

Sergio Escalera,

Jordi Gonzalez; [pdf] [supp]
[bibtex]
@InProceedings{Laczko_2024_WACV, author = {Laczk\'o, Hunor and Madadi, Meysam and Escalera, Sergio and Gonzalez, Jordi}, title = {A Generative Multi-Resolution Pyramid and Normal-Conditioning 3D Cloth Draping}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8709-8718} }
MAdVerse: A Hierarchical Dataset of Multi-Lingual Ads From Diverse Sources and Categories: Amruth Sagar,

Rishabh Srivastava,

Rakshitha R. T.,

Venkata Kesav Venna,

Ravi Kiran Sarvadevabhatla; [pdf] [supp]
[bibtex]
@InProceedings{Sagar_2024_WACV, author = {Sagar, Amruth and Srivastava, Rishabh and T., Rakshitha R. and Venna, Venkata Kesav and Sarvadevabhatla, Ravi Kiran}, title = {MAdVerse: A Hierarchical Dataset of Multi-Lingual Ads From Diverse Sources and Categories}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8087-8096} }
Identifying Label Errors in Object Detection Datasets by Loss Inspection: Marius Schubert,

Tobias Riedlinger,

Karsten Kahl,

Daniel Kröll,

Sebastian Schoenen,

Siniša Šegvić,

Matthias Rottmann; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Schubert_2024_WACV, author = {Schubert, Marius and Riedlinger, Tobias and Kahl, Karsten and Kr\"oll, Daniel and Schoenen, Sebastian and \v{S}egvi\'c, Sini\v{s}a and Rottmann, Matthias}, title = {Identifying Label Errors in Object Detection Datasets by Loss Inspection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4582-4591} }
Reference-Based Restoration of Digitized Analog Videotapes: Lorenzo Agnolucci,

Leonardo Galteri,

Marco Bertini,

Alberto Del Bimbo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Agnolucci_2024_WACV, author = {Agnolucci, Lorenzo and Galteri, Leonardo and Bertini, Marco and Del Bimbo, Alberto}, title = {Reference-Based Restoration of Digitized Analog Videotapes}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1659-1668} }
BigSmall: Efficient Multi-Task Learning for Disparate Spatial and Temporal Physiological Measurements: Girish Narayanswamy,

Yujia Liu,

Yuzhe Yang,

Chengqian Ma,

Xin Liu,

Daniel McDuff,

Shwetak Patel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Narayanswamy_2024_WACV, author = {Narayanswamy, Girish and Liu, Yujia and Yang, Yuzhe and Ma, Chengqian and Liu, Xin and McDuff, Daniel and Patel, Shwetak}, title = {BigSmall: Efficient Multi-Task Learning for Disparate Spatial and Temporal Physiological Measurements}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7914-7924} }
Robust Feature Learning and Global Variance-Driven Classifier Alignment for Long-Tail Class Incremental Learning: Jayateja Kalla,

Soma Biswas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kalla_2024_WACV, author = {Kalla, Jayateja and Biswas, Soma}, title = {Robust Feature Learning and Global Variance-Driven Classifier Alignment for Long-Tail Class Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {32-41} }
MagneticPillars: Efficient Point Cloud Registration Through Hierarchized Birds-Eye-View Cell Correspondence Refinement: Kai Fischer,

Martin Simon,

Stefan Milz,

Patrick Mäder; [pdf] [supp]
[bibtex]
@InProceedings{Fischer_2024_WACV, author = {Fischer, Kai and Simon, Martin and Milz, Stefan and M\"ader, Patrick}, title = {MagneticPillars: Efficient Point Cloud Registration Through Hierarchized Birds-Eye-View Cell Correspondence Refinement}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7386-7395} }
Fast Diffusion EM: A Diffusion Model for Blind Inverse Problems With Application to Deconvolution: Charles Laroche,

Andrés Almansa,

Eva Coupeté; [pdf] [supp]
[bibtex]
@InProceedings{Laroche_2024_WACV, author = {Laroche, Charles and Almansa, Andr\'es and Coupet\'e, Eva}, title = {Fast Diffusion EM: A Diffusion Model for Blind Inverse Problems With Application to Deconvolution}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5271-5281} }
Active Transfer Learning for Efficient Video-Specific Human Pose Estimation: Hiromu Taketsugu,

Norimichi Ukita; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Taketsugu_2024_WACV, author = {Taketsugu, Hiromu and Ukita, Norimichi}, title = {Active Transfer Learning for Efficient Video-Specific Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1880-1890} }
Training-Free Layout Control With Cross-Attention Guidance: Minghao Chen,

Iro Laina,

Andrea Vedaldi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_WACV, author = {Chen, Minghao and Laina, Iro and Vedaldi, Andrea}, title = {Training-Free Layout Control With Cross-Attention Guidance}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5343-5353} }
Learning Transferable Representations for Image Anomaly Localization Using Dense Pretraining: Haitian He,

Sarah Erfani,

Mingming Gong,

Qiuhong Ke; [pdf] [supp]
[bibtex]
@InProceedings{He_2024_WACV, author = {He, Haitian and Erfani, Sarah and Gong, Mingming and Ke, Qiuhong}, title = {Learning Transferable Representations for Image Anomaly Localization Using Dense Pretraining}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1113-1122} }
Embedding Task Structure for Action Detection: Michael Peven,

Gregory D. Hager; [pdf]
[bibtex]
@InProceedings{Peven_2024_WACV, author = {Peven, Michael and Hager, Gregory D.}, title = {Embedding Task Structure for Action Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6604-6613} }
RIMeshGNN: A Rotation-Invariant Graph Neural Network for Mesh Classification: Bahareh Shakibajahromi,

Edward Kim,

David E. Breen; [pdf] [supp]
[bibtex]
@InProceedings{Shakibajahromi_2024_WACV, author = {Shakibajahromi, Bahareh and Kim, Edward and Breen, David E.}, title = {RIMeshGNN: A Rotation-Invariant Graph Neural Network for Mesh Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3150-3160} }
Stereo Matching in Time: 100+ FPS Video Stereo Matching for Extended Reality: Ziang Cheng,

Jiayu Yang,

Hongdong Li; [pdf]
[bibtex]
@InProceedings{Cheng_2024_WACV, author = {Cheng, Ziang and Yang, Jiayu and Li, Hongdong}, title = {Stereo Matching in Time: 100+ FPS Video Stereo Matching for Extended Reality}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8719-8728} }
Learning the What and How of Annotation in Video Object Segmentation: Thanos Delatolas,

Vicky Kalogeiton,

Dim P. Papadopoulos; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Delatolas_2024_WACV, author = {Delatolas, Thanos and Kalogeiton, Vicky and Papadopoulos, Dim P.}, title = {Learning the What and How of Annotation in Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6951-6961} }
Reverse Knowledge Distillation: Training a Large Model Using a Small One for Retinal Image Matching on Limited Data: Sahar Almahfouz Nasser,

Nihar Gupte,

Amit Sethi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nasser_2024_WACV, author = {Nasser, Sahar Almahfouz and Gupte, Nihar and Sethi, Amit}, title = {Reverse Knowledge Distillation: Training a Large Model Using a Small One for Retinal Image Matching on Limited Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7778-7787} }
Edge Inference With Fully Differentiable Quantized Mixed Precision Neural Networks: Clemens JS Schaefer,

Siddharth Joshi,

Shan Li,

Raul Blazquez; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Schaefer_2024_WACV, author = {Schaefer, Clemens JS and Joshi, Siddharth and Li, Shan and Blazquez, Raul}, title = {Edge Inference With Fully Differentiable Quantized Mixed Precision Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8460-8469} }
CAD - Contextual Multi-Modal Alignment for Dynamic AVQA: Asmar Nadeem,

Adrian Hilton,

Robert Dawes,

Graham Thomas,

Armin Mustafa; [pdf] [supp]
[bibtex]
@InProceedings{Nadeem_2024_WACV, author = {Nadeem, Asmar and Hilton, Adrian and Dawes, Robert and Thomas, Graham and Mustafa, Armin}, title = {CAD - Contextual Multi-Modal Alignment for Dynamic AVQA}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7251-7263} }
Discriminator-Free Unsupervised Domain Adaptation for Multi-Label Image Classification: Inder Pal Singh,

Enjie Ghorbel,

Anis Kacem,

Arunkumar Rathinam,

Djamila Aouada; [pdf] [arXiv]
[bibtex]
@InProceedings{Singh_2024_WACV, author = {Singh, Inder Pal and Ghorbel, Enjie and Kacem, Anis and Rathinam, Arunkumar and Aouada, Djamila}, title = {Discriminator-Free Unsupervised Domain Adaptation for Multi-Label Image Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3936-3945} }
Continual Test-Time Domain Adaptation via Dynamic Sample Selection: Yanshuo Wang,

Jie Hong,

Ali Cheraghian,

Shafin Rahman,

David Ahmedt-Aristizabal,

Lars Petersson,

Mehrtash Harandi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_WACV, author = {Wang, Yanshuo and Hong, Jie and Cheraghian, Ali and Rahman, Shafin and Ahmedt-Aristizabal, David and Petersson, Lars and Harandi, Mehrtash}, title = {Continual Test-Time Domain Adaptation via Dynamic Sample Selection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1701-1710} }
FuseCap: Leveraging Large Language Models for Enriched Fused Image Captions: Noam Rotstein,

David Bensaïd,

Shaked Brody,

Roy Ganz,

Ron Kimmel; [pdf] [supp]
[bibtex]
@InProceedings{Rotstein_2024_WACV, author = {Rotstein, Noam and Bensa{\"\i}d, David and Brody, Shaked and Ganz, Roy and Kimmel, Ron}, title = {FuseCap: Leveraging Large Language Models for Enriched Fused Image Captions}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5689-5700} }
Learning To Adapt CLIP for Few-Shot Monocular Depth Estimation: Xueting Hu,

Ce Zhang,

Yi Zhang,

Bowen Hai,

Ke Yu,

Zhihai He; [pdf] [arXiv]
[bibtex]
@InProceedings{Hu_2024_WACV, author = {Hu, Xueting and Zhang, Ce and Zhang, Yi and Hai, Bowen and Yu, Ke and He, Zhihai}, title = {Learning To Adapt CLIP for Few-Shot Monocular Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5594-5603} }
Asymmetric Image Retrieval With Cross Model Compatible Ensembles: Alon Shoshan,

Ori Linial,

Nadav Bhonker,

Elad Hirsch,

Lior Zamir,

Igor Kviatkovsky,

Gérard Medioni; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shoshan_2024_WACV, author = {Shoshan, Alon and Linial, Ori and Bhonker, Nadav and Hirsch, Elad and Zamir, Lior and Kviatkovsky, Igor and Medioni, G\'erard}, title = {Asymmetric Image Retrieval With Cross Model Compatible Ensembles}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1-11} }
Progressive Hypothesis Transformer for 3D Human Mesh Recovery: Huang-Ru Liao,

Jen-Chun Lin,

Chun-Yi Lee; [pdf] [supp]
[bibtex]
@InProceedings{Liao_2024_WACV, author = {Liao, Huang-Ru and Lin, Jen-Chun and Lee, Chun-Yi}, title = {Progressive Hypothesis Transformer for 3D Human Mesh Recovery}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6323-6332} }
MPT: Mesh Pre-Training With Transformers for Human Pose and Mesh Reconstruction: Kevin Lin,

Chung-Ching Lin,

Lin Liang,

Zicheng Liu,

Lijuan Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2024_WACV, author = {Lin, Kevin and Lin, Chung-Ching and Liang, Lin and Liu, Zicheng and Wang, Lijuan}, title = {MPT: Mesh Pre-Training With Transformers for Human Pose and Mesh Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3415-3425} }
Training-Free Content Injection Using H-Space in Diffusion Models: Jaeseok Jeong,

Mingi Kwon,

Youngjung Uh; [pdf] [supp]
[bibtex]
@InProceedings{Jeong_2024_WACV, author = {Jeong, Jaeseok and Kwon, Mingi and Uh, Youngjung}, title = {Training-Free Content Injection Using H-Space in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5151-5161} }
Hard Sample-Aware Consistency for Low-Resolution Facial Expression Recognition: Bokyeung Lee,

Kyungdeuk Ko,

Jonghwan Hong,

Hanseok Ko; [pdf]
[bibtex]
@InProceedings{Lee_2024_WACV, author = {Lee, Bokyeung and Ko, Kyungdeuk and Hong, Jonghwan and Ko, Hanseok}, title = {Hard Sample-Aware Consistency for Low-Resolution Facial Expression Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {199-208} }
ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot End-to-End Temporal Action Detection: Thinh Phan,

Khoa Vo,

Duy Le,

Gianfranco Doretto,

Donald Adjeroh,

Ngan Le; [pdf] [arXiv]
[bibtex]
@InProceedings{Phan_2024_WACV, author = {Phan, Thinh and Vo, Khoa and Le, Duy and Doretto, Gianfranco and Adjeroh, Donald and Le, Ngan}, title = {ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot End-to-End Temporal Action Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7046-7055} }
Army of Thieves: Enhancing Black-Box Model Extraction via Ensemble Based Sample Selection: Akshit Jindal,

Vikram Goyal,

Saket Anand,

Chetan Arora; [pdf] [arXiv]
[bibtex]
@InProceedings{Jindal_2024_WACV, author = {Jindal, Akshit and Goyal, Vikram and Anand, Saket and Arora, Chetan}, title = {Army of Thieves: Enhancing Black-Box Model Extraction via Ensemble Based Sample Selection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3823-3832} }
GC-MVSNet: Multi-View, Multi-Scale, Geometrically-Consistent Multi-View Stereo: Vibhas K. Vats,

Sripad Joshi,

David J. Crandall,

Md. Alimoor Reza,

Soon-heung Jung; [pdf] [supp]
[bibtex]
@InProceedings{Vats_2024_WACV, author = {Vats, Vibhas K. and Joshi, Sripad and Crandall, David J. and Reza, Md. Alimoor and Jung, Soon-heung}, title = {GC-MVSNet: Multi-View, Multi-Scale, Geometrically-Consistent Multi-View Stereo}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3242-3252} }
Active Batch Sampling for Multi-Label Classification With Binary User Feedback: Debanjan Goswami,

Shayok Chakraborty; [pdf] [supp]
[bibtex]
@InProceedings{Goswami_2024_WACV, author = {Goswami, Debanjan and Chakraborty, Shayok}, title = {Active Batch Sampling for Multi-Label Classification With Binary User Feedback}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2534-2543} }
Efficient MAE Towards Large-Scale Vision Transformers: Qiu Han,

Gongjie Zhang,

Jiaxing Huang,

Peng Gao,

Zhang Wei,

Shijian Lu; [pdf] [supp]
[bibtex]
@InProceedings{Han_2024_WACV, author = {Han, Qiu and Zhang, Gongjie and Huang, Jiaxing and Gao, Peng and Wei, Zhang and Lu, Shijian}, title = {Efficient MAE Towards Large-Scale Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {606-615} }
M33D: Learning 3D Priors Using Multi-Modal Masked Autoencoders for 2D Image and Video Understanding: Muhammad Abdullah Jamal,

Omid Mohareri; [pdf] [supp]
[bibtex]
@InProceedings{Jamal_2024_WACV, author = {Jamal, Muhammad Abdullah and Mohareri, Omid}, title = {M33D: Learning 3D Priors Using Multi-Modal Masked Autoencoders for 2D Image and Video Understanding}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2544-2554} }
Graph(Graph): A Nested Graph-Based Framework for Early Accident Anticipation: Nupur Thakur,

PrasanthSai Gouripeddi,

Baoxin Li; [pdf]
[bibtex]
@InProceedings{Thakur_2024_WACV, author = {Thakur, Nupur and Gouripeddi, PrasanthSai and Li, Baoxin}, title = {Graph(Graph): A Nested Graph-Based Framework for Early Accident Anticipation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7533-7541} }
Iterative Multi-Granular Image Editing Using Diffusion Models: K. J. Joseph,

Prateksha Udhayanan,

Tripti Shukla,

Aishwarya Agarwal,

Srikrishna Karanam,

Koustava Goswami,

Balaji Vasan Srinivasan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Joseph_2024_WACV, author = {Joseph, K. J. and Udhayanan, Prateksha and Shukla, Tripti and Agarwal, Aishwarya and Karanam, Srikrishna and Goswami, Koustava and Srinivasan, Balaji Vasan}, title = {Iterative Multi-Granular Image Editing Using Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8107-8116} }
Efficient Feature Distillation for Zero-Shot Annotation Object Detection: Zhuoming Liu,

Xuefeng Hu,

Ram Nevatia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_WACV, author = {Liu, Zhuoming and Hu, Xuefeng and Nevatia, Ram}, title = {Efficient Feature Distillation for Zero-Shot Annotation Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {893-902} }
SpectralCLIP: Preventing Artifacts in Text-Guided Style Transfer From a Spectral Perspective: Zipeng Xu,

Songlong Xing,

Enver Sangineto,

Nicu Sebe; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2024_WACV, author = {Xu, Zipeng and Xing, Songlong and Sangineto, Enver and Sebe, Nicu}, title = {SpectralCLIP: Preventing Artifacts in Text-Guided Style Transfer From a Spectral Perspective}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5121-5130} }
Harnessing the Power of Multi-Lingual Datasets for Pre-Training: Towards Enhancing Text Spotting Performance: Alloy Das,

Sanket Biswas,

Ayan Banerjee,

Josep Lladós,

Umapada Pal,

Saumik Bhattacharya; [pdf] [supp]
[bibtex]
@InProceedings{Das_2024_WACV, author = {Das, Alloy and Biswas, Sanket and Banerjee, Ayan and Llad\'os, Josep and Pal, Umapada and Bhattacharya, Saumik}, title = {Harnessing the Power of Multi-Lingual Datasets for Pre-Training: Towards Enhancing Text Spotting Performance}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {718-728} }
Rethink Cross-Modal Fusion in Weakly-Supervised Audio-Visual Video Parsing: Yating Xu,

Conghui Hu,

Gim Hee Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2024_WACV, author = {Xu, Yating and Hu, Conghui and Lee, Gim Hee}, title = {Rethink Cross-Modal Fusion in Weakly-Supervised Audio-Visual Video Parsing}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5615-5624} }
Refine and Redistribute: Multi-Domain Fusion and Dynamic Label Assignment for Unbiased Scene Graph Generation: Yujie Zang,

Yaochen Li,

Yuan Gao,

Yimou Guo,

Wenneng Tang,

Yanxue Li,

Meklit Atlaw; [pdf] [supp]
[bibtex]
@InProceedings{Zang_2024_WACV, author = {Zang, Yujie and Li, Yaochen and Gao, Yuan and Guo, Yimou and Tang, Wenneng and Li, Yanxue and Atlaw, Meklit}, title = {Refine and Redistribute: Multi-Domain Fusion and Dynamic Label Assignment for Unbiased Scene Graph Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1318-1327} }
Semantic Transfer From Head to Tail: Enlarging Tail Margin for Long-Tailed Visual Recognition: Shan Zhang,

Yao Ni,

Jinhao Du,

Yanxia Liu,

Piotr Koniusz; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Shan and Ni, Yao and Du, Jinhao and Liu, Yanxia and Koniusz, Piotr}, title = {Semantic Transfer From Head to Tail: Enlarging Tail Margin for Long-Tailed Visual Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1350-1360} }
PoseDiff: Pose-Conditioned Multimodal Diffusion Model for Unbounded Scene Synthesis From Sparse Inputs: Seoyoung Lee,

Joonseok Lee; [pdf]
[bibtex]
@InProceedings{Lee_2024_WACV, author = {Lee, Seoyoung and Lee, Joonseok}, title = {PoseDiff: Pose-Conditioned Multimodal Diffusion Model for Unbounded Scene Synthesis From Sparse Inputs}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5007-5017} }
Leveraging Task-Specific Pre-Training To Reason Across Images and Videos: Arka Sadhu,

Ram Nevatia; [pdf] [supp]
[bibtex]
@InProceedings{Sadhu_2024_WACV, author = {Sadhu, Arka and Nevatia, Ram}, title = {Leveraging Task-Specific Pre-Training To Reason Across Images and Videos}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5794-5804} }
Recognition of Unseen Bird Species by Learning From Field Guides: Andrés C. Rodríguez,

Stefano D'Aronco,

Rodrigo Caye Daudt,

Jan D. Wegner,

Konrad Schindler; [pdf] [supp]
[bibtex]
@InProceedings{Rodriguez_2024_WACV, author = {Rodr{\'\i}guez, Andr\'es C. and D'Aronco, Stefano and Daudt, Rodrigo Caye and Wegner, Jan D. and Schindler, Konrad}, title = {Recognition of Unseen Bird Species by Learning From Field Guides}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1742-1751} }
LidarCLIP or: How I Learned To Talk to Point Clouds: Georg Hess,

Adam Tonderski,

Christoffer Petersson,

Kalle Åström,

Lennart Svensson; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hess_2024_WACV, author = {Hess, Georg and Tonderski, Adam and Petersson, Christoffer and \r{A}str\"om, Kalle and Svensson, Lennart}, title = {LidarCLIP or: How I Learned To Talk to Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7438-7447} }
Enhancing Multimodal Compositional Reasoning of Visual Language Models With Generative Negative Mining: Ugur Sahin,

Hang Li,

Qadeer Khan,

Daniel Cremers,

Volker Tresp; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sahin_2024_WACV, author = {Sahin, Ugur and Li, Hang and Khan, Qadeer and Cremers, Daniel and Tresp, Volker}, title = {Enhancing Multimodal Compositional Reasoning of Visual Language Models With Generative Negative Mining}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5563-5573} }
LaughTalk: Expressive 3D Talking Head Generation With Laughter: Kim Sung-Bin,

Lee Hyun,

Da Hye Hong,

Suekyeong Nam,

Janghoon Ju,

Tae-Hyun Oh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sung-Bin_2024_WACV, author = {Sung-Bin, Kim and Hyun, Lee and Hong, Da Hye and Nam, Suekyeong and Ju, Janghoon and Oh, Tae-Hyun}, title = {LaughTalk: Expressive 3D Talking Head Generation With Laughter}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6404-6413} }
Effects of Markers in Training Datasets on the Accuracy of 6D Pose Estimation: Janis Rosskamp,

Rene Weller,

Gabriel Zachmann; [pdf]
[bibtex]
@InProceedings{Rosskamp_2024_WACV, author = {Rosskamp, Janis and Weller, Rene and Zachmann, Gabriel}, title = {Effects of Markers in Training Datasets on the Accuracy of 6D Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4457-4466} }
Alleviating Foreground Sparsity for Semi-Supervised Monocular 3D Object Detection: Weijia Zhang,

Dongnan Liu,

Chao Ma,

Weidong Cai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Weijia and Liu, Dongnan and Ma, Chao and Cai, Weidong}, title = {Alleviating Foreground Sparsity for Semi-Supervised Monocular 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7542-7552} }
MFT: Long-Term Tracking of Every Pixel: Michal Neoral,

Jonáš Šerých,

Jiří Matas; [pdf] [supp]
[bibtex]
@InProceedings{Neoral_2024_WACV, author = {Neoral, Michal and \v{S}er\'ych, Jon\'a\v{s} and Matas, Ji\v{r}{\'\i}}, title = {MFT: Long-Term Tracking of Every Pixel}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6837-6847} }
Out-of-Distribution Detection With Logical Reasoning: Konstantin Kirchheim,

Tim Gonschorek,

Frank Ortmeier; [pdf]
[bibtex]
@InProceedings{Kirchheim_2024_WACV, author = {Kirchheim, Konstantin and Gonschorek, Tim and Ortmeier, Frank}, title = {Out-of-Distribution Detection With Logical Reasoning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2122-2131} }
WalkFormer: Point Cloud Completion via Guided Walks: Mohang Zhang,

Yushi Li,

Rong Chen,

Yushan Pan,

Jia Wang,

Yunzhe Wang,

Rong Xiang; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Mohang and Li, Yushi and Chen, Rong and Pan, Yushan and Wang, Jia and Wang, Yunzhe and Xiang, Rong}, title = {WalkFormer: Point Cloud Completion via Guided Walks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3293-3302} }
Driving Through the Concept Gridlock: Unraveling Explainability Bottlenecks in Automated Driving: Jessica Echterhoff,

An Yan,

Kyungtae Han,

Amr Abdelraouf,

Rohit Gupta,

Julian McAuley; [pdf] [arXiv]
[bibtex]
@InProceedings{Echterhoff_2024_WACV, author = {Echterhoff, Jessica and Yan, An and Han, Kyungtae and Abdelraouf, Amr and Gupta, Rohit and McAuley, Julian}, title = {Driving Through the Concept Gridlock: Unraveling Explainability Bottlenecks in Automated Driving}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7346-7355} }
Single-Image Deblurring, Trajectory and Shape Recovery of Fast Moving Objects With Denoising Diffusion Probabilistic Models: Radim Spetlik,

Denys Rozumnyi,

Jiří Matas; [pdf] [supp]
[bibtex]
@InProceedings{Spetlik_2024_WACV, author = {Spetlik, Radim and Rozumnyi, Denys and Matas, Ji\v{r}{\'\i}}, title = {Single-Image Deblurring, Trajectory and Shape Recovery of Fast Moving Objects With Denoising Diffusion Probabilistic Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6857-6866} }
IDD-AW: A Benchmark for Safe and Robust Segmentation of Drive Scenes in Unstructured Traffic and Adverse Weather: Furqan Ahmed Shaik,

Abhishek Reddy,

Nikhil Reddy Billa,

Kunal Chaudhary,

Sunny Manchanda,

Girish Varma; [pdf] [supp]
[bibtex]
@InProceedings{Shaik_2024_WACV, author = {Shaik, Furqan Ahmed and Reddy, Abhishek and Billa, Nikhil Reddy and Chaudhary, Kunal and Manchanda, Sunny and Varma, Girish}, title = {IDD-AW: A Benchmark for Safe and Robust Segmentation of Drive Scenes in Unstructured Traffic and Adverse Weather}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4614-4623} }
Semantic Generative Augmentations for Few-Shot Counting: Perla Doubinsky,

Nicolas Audebert,

Michel Crucianu,

Hervé Le Borgne; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Doubinsky_2024_WACV, author = {Doubinsky, Perla and Audebert, Nicolas and Crucianu, Michel and Le Borgne, Herv\'e}, title = {Semantic Generative Augmentations for Few-Shot Counting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5443-5452} }
Text-to-Image Models for Counterfactual Explanations: A Black-Box Approach: Guillaume Jeanneret,

Loïc Simon,

Frédéric Jurie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jeanneret_2024_WACV, author = {Jeanneret, Guillaume and Simon, Lo{\"\i}c and Jurie, Fr\'ed\'eric}, title = {Text-to-Image Models for Counterfactual Explanations: A Black-Box Approach}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4757-4767} }
Physical-Space Multi-Body Mesh Detection Achieved by Local Alignment and Global Dense Learning: Haoye Dong,

Tiange Xiang,

Sravan Chittupalli,

Jun Liu,

Dong Huang; [pdf] [supp]
[bibtex]
@InProceedings{Dong_2024_WACV, author = {Dong, Haoye and Xiang, Tiange and Chittupalli, Sravan and Liu, Jun and Huang, Dong}, title = {Physical-Space Multi-Body Mesh Detection Achieved by Local Alignment and Global Dense Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1267-1276} }
Guided Cluster Aggregation: A Hierarchical Approach to Generalized Category Discovery: Jona Otholt,

Christoph Meinel,

Haojin Yang; [pdf]
[bibtex]
@InProceedings{Otholt_2024_WACV, author = {Otholt, Jona and Meinel, Christoph and Yang, Haojin}, title = {Guided Cluster Aggregation: A Hierarchical Approach to Generalized Category Discovery}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2618-2627} }
Masked Event Modeling: Self-Supervised Pretraining for Event Cameras: Simon Klenk,

David Bonello,

Lukas Koestler,

Nikita Araslanov,

Daniel Cremers; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Klenk_2024_WACV, author = {Klenk, Simon and Bonello, David and Koestler, Lukas and Araslanov, Nikita and Cremers, Daniel}, title = {Masked Event Modeling: Self-Supervised Pretraining for Event Cameras}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2378-2388} }
Real-Time Polyp Detection in Colonoscopy Using Lightweight Transformer: Youngbeom Yoo,

Jae Young Lee,

Dong-Jae Lee,

Jiwoon Jeon,

Junmo Kim; [pdf] [supp]
[bibtex]
@InProceedings{Yoo_2024_WACV, author = {Yoo, Youngbeom and Lee, Jae Young and Lee, Dong-Jae and Jeon, Jiwoon and Kim, Junmo}, title = {Real-Time Polyp Detection in Colonoscopy Using Lightweight Transformer}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7809-7819} }
Top-Down Beats Bottom-Up in 3D Instance Segmentation: Maksim Kolodiazhnyi,

Anna Vorontsova,

Anton Konushin,

Danila Rukhovich; [pdf] [arXiv]
[bibtex]
@InProceedings{Kolodiazhnyi_2024_WACV, author = {Kolodiazhnyi, Maksim and Vorontsova, Anna and Konushin, Anton and Rukhovich, Danila}, title = {Top-Down Beats Bottom-Up in 3D Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3566-3574} }
Open-Set Object Detection by Aligning Known Class Representations: Hiran Sarkar,

Vishal Chudasama,

Naoyuki Onoe,

Pankaj Wasnik,

Vineeth N. Balasubramanian; [pdf] [supp]
[bibtex]
@InProceedings{Sarkar_2024_WACV, author = {Sarkar, Hiran and Chudasama, Vishal and Onoe, Naoyuki and Wasnik, Pankaj and Balasubramanian, Vineeth N.}, title = {Open-Set Object Detection by Aligning Known Class Representations}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {219-228} }
DR2: Disentangled Recurrent Representation Learning for Data-Efficient Speech Video Synthesis: Chenxu Zhang,

Chao Wang,

Yifan Zhao,

Shuo Cheng,

Linjie Luo,

Xiaohu Guo; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Chenxu and Wang, Chao and Zhao, Yifan and Cheng, Shuo and Luo, Linjie and Guo, Xiaohu}, title = {DR2: Disentangled Recurrent Representation Learning for Data-Efficient Speech Video Synthesis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6204-6214} }
EvDNeRF: Reconstructing Event Data With Dynamic Neural Radiance Fields: Anish Bhattacharya,

Ratnesh Madaan,

Fernando Cladera,

Sai Vemprala,

Rogerio Bonatti,

Kostas Daniilidis,

Ashish Kapoor,

Vijay Kumar,

Nikolai Matni,

Jayesh K. Gupta; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bhattacharya_2024_WACV, author = {Bhattacharya, Anish and Madaan, Ratnesh and Cladera, Fernando and Vemprala, Sai and Bonatti, Rogerio and Daniilidis, Kostas and Kapoor, Ashish and Kumar, Vijay and Matni, Nikolai and Gupta, Jayesh K.}, title = {EvDNeRF: Reconstructing Event Data With Dynamic Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5846-5855} }
DISCO: Distributed Inference With Sparse Communications: Minghai Qin,

Chao Sun,

Jaco Hofmann,

Dejan Vucinic; [pdf] [arXiv]
[bibtex]
@InProceedings{Qin_2024_WACV, author = {Qin, Minghai and Sun, Chao and Hofmann, Jaco and Vucinic, Dejan}, title = {DISCO: Distributed Inference With Sparse Communications}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2432-2440} }
EmoStyle: One-Shot Facial Expression Editing Using Continuous Emotion Parameters: Bita Azari,

Angelica Lim; [pdf] [supp]
[bibtex]
@InProceedings{Azari_2024_WACV, author = {Azari, Bita and Lim, Angelica}, title = {EmoStyle: One-Shot Facial Expression Editing Using Continuous Emotion Parameters}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6385-6394} }
FinderNet: A Data Augmentation Free Canonicalization Aided Loop Detection and Closure Technique for Point Clouds in 6-DOF Separation.: Sudarshan S. Harithas,

Gurkirat Singh,

Aneesh Chavan,

Sarthak Sharma,

Suraj Patni,

Chetan Arora,

Madhava Krishna; [pdf] [supp]
[bibtex]
@InProceedings{Harithas_2024_WACV, author = {Harithas, Sudarshan S. and Singh, Gurkirat and Chavan, Aneesh and Sharma, Sarthak and Patni, Suraj and Arora, Chetan and Krishna, Madhava}, title = {FinderNet: A Data Augmentation Free Canonicalization Aided Loop Detection and Closure Technique for Point Clouds in 6-DOF Separation.}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8399-8408} }
Distortion-Disentangled Contrastive Learning: Jinfeng Wang,

Sifan Song,

Jionglong Su,

S. Kevin Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_WACV, author = {Wang, Jinfeng and Song, Sifan and Su, Jionglong and Zhou, S. Kevin}, title = {Distortion-Disentangled Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {75-85} }
Boosting Weakly Supervised Object Detection Using Fusion and Priors From Hallucinated Depth: Cagri Gungor,

Adriana Kovashka; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gungor_2024_WACV, author = {Gungor, Cagri and Kovashka, Adriana}, title = {Boosting Weakly Supervised Object Detection Using Fusion and Priors From Hallucinated Depth}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {739-748} }
MS-EVS: Multispectral Event-Based Vision for Deep Learning Based Face Detection: Saad Himmi,

Vincent Parret,

Ajad Chhatkuli,

Luc Van Gool; [pdf] [supp]
[bibtex]
@InProceedings{Himmi_2024_WACV, author = {Himmi, Saad and Parret, Vincent and Chhatkuli, Ajad and Van Gool, Luc}, title = {MS-EVS: Multispectral Event-Based Vision for Deep Learning Based Face Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {616-625} }
Adaptive Latent Diffusion Model for 3D Medical Image to Image Translation: Multi-Modal Magnetic Resonance Imaging Study: Jonghun Kim,

Hyunjin Park; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2024_WACV, author = {Kim, Jonghun and Park, Hyunjin}, title = {Adaptive Latent Diffusion Model for 3D Medical Image to Image Translation: Multi-Modal Magnetic Resonance Imaging Study}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7604-7613} }
Let's Observe Them Over Time: An Improved Pedestrian Attribute Recognition Approach: Kamalakar Vijay Thakare,

Debi Prosad Dogra,

Heeseung Choi,

Haksub Kim,

Ig-Jae Kim; [pdf] [supp]
[bibtex]
@InProceedings{Thakare_2024_WACV, author = {Thakare, Kamalakar Vijay and Dogra, Debi Prosad and Choi, Heeseung and Kim, Haksub and Kim, Ig-Jae}, title = {Let's Observe Them Over Time: An Improved Pedestrian Attribute Recognition Approach}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {708-717} }
AnyStar: Domain Randomized Universal Star-Convex 3D Instance Segmentation: Neel Dey,

Mazdak Abulnaga,

Benjamin Billot,

Esra Abaci Turk,

Ellen Grant,

Adrian V. Dalca,

Polina Golland; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dey_2024_WACV, author = {Dey, Neel and Abulnaga, Mazdak and Billot, Benjamin and Turk, Esra Abaci and Grant, Ellen and Dalca, Adrian V. and Golland, Polina}, title = {AnyStar: Domain Randomized Universal Star-Convex 3D Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7593-7603} }
Solving the Plane-Sphere Ambiguity in Top-Down Structure-From-Motion: Lars Haalck,

Benjamin Risse; [pdf] [supp]
[bibtex]
@InProceedings{Haalck_2024_WACV, author = {Haalck, Lars and Risse, Benjamin}, title = {Solving the Plane-Sphere Ambiguity in Top-Down Structure-From-Motion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3485-3493} }
PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers Using Synthetic Scene Data: Roei Herzig,

Ofir Abramovich,

Elad Ben Avraham,

Assaf Arbelle,

Leonid Karlinsky,

Ariel Shamir,

Trevor Darrell,

Amir Globerson; [pdf] [supp]
[bibtex]
@InProceedings{Herzig_2024_WACV, author = {Herzig, Roei and Abramovich, Ofir and Ben Avraham, Elad and Arbelle, Assaf and Karlinsky, Leonid and Shamir, Ariel and Darrell, Trevor and Globerson, Amir}, title = {PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers Using Synthetic Scene Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6803-6815} }
Improving the Leaking of Augmentations in Data-Efficient GANs via Adaptive Negative Data Augmentation: Zhaoyu Zhang,

Yang Hua,

Guanxiong Sun,

Hui Wang,

Seán McLoone; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Zhaoyu and Hua, Yang and Sun, Guanxiong and Wang, Hui and McLoone, Se\'an}, title = {Improving the Leaking of Augmentations in Data-Efficient GANs via Adaptive Negative Data Augmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5412-5421} }
Enhancing Diverse Intra-Identity Representation for Visible-Infrared Person Re-Identification: Sejun Kim,

Soonyong Gwon,

Kisung Seo; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2024_WACV, author = {Kim, Sejun and Gwon, Soonyong and Seo, Kisung}, title = {Enhancing Diverse Intra-Identity Representation for Visible-Infrared Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2513-2522} }
Synergizing Contrastive Learning and Optimal Transport for 3D Point Cloud Domain Adaptation: Siddharth Katageri,

Arkadipta De,

Chaitanya Devaguptapu,

VSSV Prasad,

Charu Sharma,

Manohar Kaul; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Katageri_2024_WACV, author = {Katageri, Siddharth and De, Arkadipta and Devaguptapu, Chaitanya and Prasad, VSSV and Sharma, Charu and Kaul, Manohar}, title = {Synergizing Contrastive Learning and Optimal Transport for 3D Point Cloud Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2942-2951} }
Video Instance Matting: Jiachen Li,

Roberto Henschel,

Vidit Goel,

Marianna Ohanyan,

Shant Navasardyan,

Humphrey Shi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_WACV, author = {Li, Jiachen and Henschel, Roberto and Goel, Vidit and Ohanyan, Marianna and Navasardyan, Shant and Shi, Humphrey}, title = {Video Instance Matting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6668-6677} }
DPPMask: Masked Image Modeling With Determinantal Point Processes: Junde Xu,

Zikai Lin,

Donghao Zhou,

Yaodong Yang,

Xiangyun Liao,

Qiong Wang,

Bian Wu,

Guangyong Chen,

Pheng-Ann Heng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2024_WACV, author = {Xu, Junde and Lin, Zikai and Zhou, Donghao and Yang, Yaodong and Liao, Xiangyun and Wang, Qiong and Wu, Bian and Chen, Guangyong and Heng, Pheng-Ann}, title = {DPPMask: Masked Image Modeling With Determinantal Point Processes}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2266-2276} }
ShadowSense: Unsupervised Domain Adaptation and Feature Fusion for Shadow-Agnostic Tree Crown Detection From RGB-Thermal Drone Imagery: Rudraksh Kapil,

Seyed Mojtaba Marvasti-Zadeh,

Nadir Erbilgin,

Nilanjan Ray; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kapil_2024_WACV, author = {Kapil, Rudraksh and Marvasti-Zadeh, Seyed Mojtaba and Erbilgin, Nadir and Ray, Nilanjan}, title = {ShadowSense: Unsupervised Domain Adaptation and Feature Fusion for Shadow-Agnostic Tree Crown Detection From RGB-Thermal Drone Imagery}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8266-8276} }
Pruning From Scratch via Shared Pruning Module and Nuclear Norm-Based Regularization: Donghyeon Lee,

Eunho Lee,

Youngbae Hwang; [pdf]
[bibtex]
@InProceedings{Lee_2024_WACV, author = {Lee, Donghyeon and Lee, Eunho and Hwang, Youngbae}, title = {Pruning From Scratch via Shared Pruning Module and Nuclear Norm-Based Regularization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1393-1402} }
Semantic Labels-Aware Transformer Model for Searching Over a Large Collection of Lecture-Slides: K. V. Jobin,

Anand Mishra,

C. V. Jawahar; [pdf] [supp]
[bibtex]
@InProceedings{Jobin_2024_WACV, author = {Jobin, K. V. and Mishra, Anand and Jawahar, C. V.}, title = {Semantic Labels-Aware Transformer Model for Searching Over a Large Collection of Lecture-Slides}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6016-6025} }
Multimodal Channel-Mixing: Channel and Spatial Masked AutoEncoder on Facial Action Unit Detection: Xiang Zhang,

Huiyuan Yang,

Taoyue Wang,

Xiaotian Li,

Lijun Yin; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Xiang and Yang, Huiyuan and Wang, Taoyue and Li, Xiaotian and Yin, Lijun}, title = {Multimodal Channel-Mixing: Channel and Spatial Masked AutoEncoder on Facial Action Unit Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6077-6086} }
ZIGNeRF: Zero-Shot 3D Scene Representation With Invertible Generative Neural Radiance Fields: Kanghyeok Ko,

Minhyeok Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ko_2024_WACV, author = {Ko, Kanghyeok and Lee, Minhyeok}, title = {ZIGNeRF: Zero-Shot 3D Scene Representation With Invertible Generative Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4986-4995} }
SLoSH: Set Locality Sensitive Hashing via Sliced-Wasserstein Embeddings: Yuzhe Lu,

Xinran Liu,

Andrea Soltoggio,

Soheil Kolouri; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lu_2024_WACV, author = {Lu, Yuzhe and Liu, Xinran and Soltoggio, Andrea and Kolouri, Soheil}, title = {SLoSH: Set Locality Sensitive Hashing via Sliced-Wasserstein Embeddings}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2566-2576} }
StreamMapNet: Streaming Mapping Network for Vectorized Online HD Map Construction: Tianyuan Yuan,

Yicheng Liu,

Yue Wang,

Yilun Wang,

Hang Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yuan_2024_WACV, author = {Yuan, Tianyuan and Liu, Yicheng and Wang, Yue and Wang, Yilun and Zhao, Hang}, title = {StreamMapNet: Streaming Mapping Network for Vectorized Online HD Map Construction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7356-7365} }
Blurry Video Compression: A Trade-Off Between Visual Enhancement and Data Compression: Dawit Mureja Argaw,

Junsik Kim,

In So Kweon; [pdf] [arXiv]
[bibtex]
@InProceedings{Argaw_2024_WACV, author = {Argaw, Dawit Mureja and Kim, Junsik and Kweon, In So}, title = {Blurry Video Compression: A Trade-Off Between Visual Enhancement and Data Compression}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4280-4290} }
Correlation-Aware Active Learning for Surgery Video Segmentation: Fei Wu,

Pablo Márquez-Neila,

Mingyi Zheng,

Hedyeh Rafii-Tari,

Raphael Sznitman; [pdf]
[bibtex]
@InProceedings{Wu_2024_WACV, author = {Wu, Fei and M\'arquez-Neila, Pablo and Zheng, Mingyi and Rafii-Tari, Hedyeh and Sznitman, Raphael}, title = {Correlation-Aware Active Learning for Surgery Video Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2010-2020} }
EResFD: Rediscovery of the Effectiveness of Standard Convolution for Lightweight Face Detection: Joonhyun Jeong,

Beomyoung Kim,

Joonsang Yu,

YoungJoon Yoo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jeong_2024_WACV, author = {Jeong, Joonhyun and Kim, Beomyoung and Yu, Joonsang and Yoo, YoungJoon}, title = {EResFD: Rediscovery of the Effectiveness of Standard Convolution for Lightweight Face Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {988-998} }
Neural Echos: Depthwise Convolutional Filters Replicate Biological Receptive Fields: Zahra Babaiee,

Peyman M. Kiasari,

Daniela Rus,

Radu Grosu; [pdf]
[bibtex]
@InProceedings{Babaiee_2024_WACV, author = {Babaiee, Zahra and Kiasari, Peyman M. and Rus, Daniela and Grosu, Radu}, title = {Neural Echos: Depthwise Convolutional Filters Replicate Biological Receptive Fields}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8216-8225} }
Estimating Blood Alcohol Level Through Facial Features for Driver Impairment Assessment: Ensiyeh Keshtkaran,

Brodie von Berg,

Grant Regan,

David Suter,

Syed Zulqarnain Gilani; [pdf] [supp]
[bibtex]
@InProceedings{Keshtkaran_2024_WACV, author = {Keshtkaran, Ensiyeh and von Berg, Brodie and Regan, Grant and Suter, David and Gilani, Syed Zulqarnain}, title = {Estimating Blood Alcohol Level Through Facial Features for Driver Impairment Assessment}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4539-4548} }
Auto-BPA: An Enhanced Ball-Pivoting Algorithm With Adaptive Radius Using Contextual Bandits: Houda Saffi,

Naima Otberdout,

Youssef Hmamouche,

Amal El Fallah Seghrouchni; [pdf] [supp]
[bibtex]
@InProceedings{Saffi_2024_WACV, author = {Saffi, Houda and Otberdout, Naima and Hmamouche, Youssef and El Fallah Seghrouchni, Amal}, title = {Auto-BPA: An Enhanced Ball-Pivoting Algorithm With Adaptive Radius Using Contextual Bandits}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3729-3737} }
MIDAS: Mixing Ambiguous Data With Soft Labels for Dynamic Facial Expression Recognition: Ryosuke Kawamura,

Hideaki Hayashi,

Noriko Takemura,

Hajime Nagahara; [pdf] [supp]
[bibtex]
@InProceedings{Kawamura_2024_WACV, author = {Kawamura, Ryosuke and Hayashi, Hideaki and Takemura, Noriko and Nagahara, Hajime}, title = {MIDAS: Mixing Ambiguous Data With Soft Labels for Dynamic Facial Expression Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6552-6562} }
MobileNVC: Real-Time 1080p Neural Video Compression on a Mobile Device: Ties van Rozendaal,

Tushar Singhal,

Hoang Le,

Guillaume Sautiere,

Amir Said,

Krishna Buska,

Anjuman Raha,

Dimitris Kalatzis,

Hitarth Mehta,

Frank Mayer,

Liang Zhang,

Markus Nagel,

Auke Wiggers; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{van_Rozendaal_2024_WACV, author = {van Rozendaal, Ties and Singhal, Tushar and Le, Hoang and Sautiere, Guillaume and Said, Amir and Buska, Krishna and Raha, Anjuman and Kalatzis, Dimitris and Mehta, Hitarth and Mayer, Frank and Zhang, Liang and Nagel, Markus and Wiggers, Auke}, title = {MobileNVC: Real-Time 1080p Neural Video Compression on a Mobile Device}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4323-4333} }
Improving the Effectiveness of Deep Generative Data: Ruyu Wang,

Sabrina Schmedding,

Marco F. Huber; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_WACV, author = {Wang, Ruyu and Schmedding, Sabrina and Huber, Marco F.}, title = {Improving the Effectiveness of Deep Generative Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4922-4932} }
Learning Better Keypoints for Multi-Object 6DoF Pose Estimation: Yangzheng Wu,

Michael Greenspan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2024_WACV, author = {Wu, Yangzheng and Greenspan, Michael}, title = {Learning Better Keypoints for Multi-Object 6DoF Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {564-574} }
Unsupervised Graphic Layout Grouping With Transformers: Jialiang Zhu,

Danqing Huang,

Chunyu Wang,

Mingxi Cheng,

Ji Li,

Han Hu,

Xin Geng,

Baining Guo; [pdf] [supp]
[bibtex]
@InProceedings{Zhu_2024_WACV, author = {Zhu, Jialiang and Huang, Danqing and Wang, Chunyu and Cheng, Mingxi and Li, Ji and Hu, Han and Geng, Xin and Guo, Baining}, title = {Unsupervised Graphic Layout Grouping With Transformers}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1031-1040} }
Can Vision-Language Models Be a Good Guesser? Exploring VLMs for Times and Location Reasoning: Gengyuan Zhang,

Yurui Zhang,

Kerui Zhang,

Volker Tresp; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Gengyuan and Zhang, Yurui and Zhang, Kerui and Tresp, Volker}, title = {Can Vision-Language Models Be a Good Guesser? Exploring VLMs for Times and Location Reasoning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {636-645} }
What Decreases Editing Capability? Domain-Specific Hybrid Refinement for Improved GAN Inversion: Pu Cao,

Lu Yang,

Dongxv Liu,

Xiaoya Yang,

Tianrui Huang,

Qing Song; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2024_WACV, author = {Cao, Pu and Yang, Lu and Liu, Dongxv and Yang, Xiaoya and Huang, Tianrui and Song, Qing}, title = {What Decreases Editing Capability? Domain-Specific Hybrid Refinement for Improved GAN Inversion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4240-4249} }
Longformer: Longitudinal Transformer for Alzheimer's Disease Classification With Structural MRIs: Qiuhui Chen,

Qiang Fu,

Hao Bai,

Yi Hong; [pdf]
[bibtex]
@InProceedings{Chen_2024_WACV, author = {Chen, Qiuhui and Fu, Qiang and Bai, Hao and Hong, Yi}, title = {Longformer: Longitudinal Transformer for Alzheimer's Disease Classification With Structural MRIs}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3575-3584} }
Grafting Vision Transformers: Jongwoo Park,

Kumara Kahatapitiya,

Donghyun Kim,

Shivchander Sudalairaj,

Quanfu Fan,

Michael S. Ryoo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2024_WACV, author = {Park, Jongwoo and Kahatapitiya, Kumara and Kim, Donghyun and Sudalairaj, Shivchander and Fan, Quanfu and Ryoo, Michael S.}, title = {Grafting Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1145-1154} }
Hardware Aware Evolutionary Neural Architecture Search Using Representation Similarity Metric: Nilotpal Sinha,

Abd El Rahman Shabayek,

Anis Kacem,

Peyman Rostami,

Carl Shneider,

Djamila Aouada; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sinha_2024_WACV, author = {Sinha, Nilotpal and El Rahman Shabayek, Abd and Kacem, Anis and Rostami, Peyman and Shneider, Carl and Aouada, Djamila}, title = {Hardware Aware Evolutionary Neural Architecture Search Using Representation Similarity Metric}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2628-2637} }
DECDM: Document Enhancement Using Cycle-Consistent Diffusion Models: Jiaxin Zhang,

Joy Rimchala,

Lalla Mouatadid,

Kamalika Das,

Sricharan Kumar; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Jiaxin and Rimchala, Joy and Mouatadid, Lalla and Das, Kamalika and Kumar, Sricharan}, title = {DECDM: Document Enhancement Using Cycle-Consistent Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8036-8045} }
Watch Where You Head: A View-Biased Domain Gap in Gait Recognition and Unsupervised Adaptation: Gavriel Habib,

Noa Barzilay,

Or Shimshi,

Rami Ben-Ari,

Nir Darshan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Habib_2024_WACV, author = {Habib, Gavriel and Barzilay, Noa and Shimshi, Or and Ben-Ari, Rami and Darshan, Nir}, title = {Watch Where You Head: A View-Biased Domain Gap in Gait Recognition and Unsupervised Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6109-6119} }
Show Your Face: Restoring Complete Facial Images From Partial Observations for VR Meeting: Zheng Chen,

Zhiqi Zhang,

Junsong Yuan,

Yi Xu,

Lantao Liu; [pdf]
[bibtex]
@InProceedings{Chen_2024_WACV, author = {Chen, Zheng and Zhang, Zhiqi and Yuan, Junsong and Xu, Yi and Liu, Lantao}, title = {Show Your Face: Restoring Complete Facial Images From Partial Observations for VR Meeting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8688-8697} }
Shape From Shading for Robotic Manipulation: Arkadeep Narayan Chaudhury,

Leonid Keselman,

Christopher G. Atkeson; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chaudhury_2024_WACV, author = {Chaudhury, Arkadeep Narayan and Keselman, Leonid and Atkeson, Christopher G.}, title = {Shape From Shading for Robotic Manipulation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8389-8398} }
Self-Supervised Denoising Transformer With Gaussian Process: Rajeev Yasarla,

Jeya Maria Jose Valanarasu,

Vishwanath Sindagi,

Vishal M. Patel; [pdf] [supp]
[bibtex]
@InProceedings{Yasarla_2024_WACV, author = {Yasarla, Rajeev and Valanarasu, Jeya Maria Jose and Sindagi, Vishwanath and Patel, Vishal M.}, title = {Self-Supervised Denoising Transformer With Gaussian Process}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1474-1484} }
SemST: Semantically Consistent Multi-Scale Image Translation via Structure-Texture Alignment: Ganning Zhao,

Wenhui Cui,

Suya You,

C.-C. Jay Kuo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2024_WACV, author = {Zhao, Ganning and Cui, Wenhui and You, Suya and Kuo, C.-C. Jay}, title = {SemST: Semantically Consistent Multi-Scale Image Translation via Structure-Texture Alignment}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7209-7219} }
Bag of Tricks for Fully Test-Time Adaptation: Saypraseuth Mounsaveng,

Florent Chiaroni,

Malik Boudiaf,

Marco Pedersoli,

Ismail Ben Ayed; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mounsaveng_2024_WACV, author = {Mounsaveng, Saypraseuth and Chiaroni, Florent and Boudiaf, Malik and Pedersoli, Marco and Ben Ayed, Ismail}, title = {Bag of Tricks for Fully Test-Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1936-1945} }
OE-CTST: Outlier-Embedded Cross Temporal Scale Transformer for Weakly-Supervised Video Anomaly Detection: Snehashis Majhi,

Rui Dai,

Quan Kong,

Lorenzo Garattoni,

Gianpiero Francesca,

François Brémond; [pdf] [supp]
[bibtex]
@InProceedings{Majhi_2024_WACV, author = {Majhi, Snehashis and Dai, Rui and Kong, Quan and Garattoni, Lorenzo and Francesca, Gianpiero and Br\'emond, Fran\c{c}ois}, title = {OE-CTST: Outlier-Embedded Cross Temporal Scale Transformer for Weakly-Supervised Video Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8574-8583} }
Bridging Generalization Gaps in High Content Imaging Through Online Self-Supervised Domain Adaptation: Johan Fredin Haslum,

Christos Matsoukas,

Karl-Johan Leuchowius,

Kevin Smith; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Haslum_2024_WACV, author = {Haslum, Johan Fredin and Matsoukas, Christos and Leuchowius, Karl-Johan and Smith, Kevin}, title = {Bridging Generalization Gaps in High Content Imaging Through Online Self-Supervised Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7738-7747} }
Using Early Readouts To Mediate Featural Bias in Distillation: Rishabh Tiwari,

Durga Sivasubramanian,

Anmol Mekala,

Ganesh Ramakrishnan,

Pradeep Shenoy; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tiwari_2024_WACV, author = {Tiwari, Rishabh and Sivasubramanian, Durga and Mekala, Anmol and Ramakrishnan, Ganesh and Shenoy, Pradeep}, title = {Using Early Readouts To Mediate Featural Bias in Distillation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2638-2647} }
Continuous Adaptation for Interactive Segmentation Using Teacher-Student Architecture: Barsegh Atanyan,

Levon Khachatryan,

Shant Navasardyan,

Yunchao Wei,

Humphrey Shi; [pdf] [supp]
[bibtex]
@InProceedings{Atanyan_2024_WACV, author = {Atanyan, Barsegh and Khachatryan, Levon and Navasardyan, Shant and Wei, Yunchao and Shi, Humphrey}, title = {Continuous Adaptation for Interactive Segmentation Using Teacher-Student Architecture}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {789-799} }
Causal Feature Alignment: Learning To Ignore Spurious Background Features: Rahul Venkataramani,

Parag Dutta,

Vikram Melapudi,

Ambedkar Dukkipati; [pdf] [supp]
[bibtex]
@InProceedings{Venkataramani_2024_WACV, author = {Venkataramani, Rahul and Dutta, Parag and Melapudi, Vikram and Dukkipati, Ambedkar}, title = {Causal Feature Alignment: Learning To Ignore Spurious Background Features}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4666-4674} }
VD-GR: Boosting Visual Dialog With Cascaded Spatial-Temporal Multi-Modal Graphs: Adnen Abdessaied,

Lei Shi,

Andreas Bulling; [pdf] [supp]
[bibtex]
@InProceedings{Abdessaied_2024_WACV, author = {Abdessaied, Adnen and Shi, Lei and Bulling, Andreas}, title = {VD-GR: Boosting Visual Dialog With Cascaded Spatial-Temporal Multi-Modal Graphs}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5805-5814} }
Fingervein Verification Using Convolutional Multi-Head Attention Network: Raghavendra Ramachandra,

Sushma Venkatesh; [pdf] [arXiv]
[bibtex]
@InProceedings{Ramachandra_2024_WACV, author = {Ramachandra, Raghavendra and Venkatesh, Sushma}, title = {Fingervein Verification Using Convolutional Multi-Head Attention Network}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6175-6184} }
Foundation Model Assisted Weakly Supervised Semantic Segmentation: Xiaobo Yang,

Xiaojin Gong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2024_WACV, author = {Yang, Xiaobo and Gong, Xiaojin}, title = {Foundation Model Assisted Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {523-532} }
Describe Images in a Boring Way: Towards Cross-Modal Sarcasm Generation: Jie Ruan,

Yue Wu,

Xiaojun Wan,

Yuesheng Zhu; [pdf] [supp]
[bibtex]
@InProceedings{Ruan_2024_WACV, author = {Ruan, Jie and Wu, Yue and Wan, Xiaojun and Zhu, Yuesheng}, title = {Describe Images in a Boring Way: Towards Cross-Modal Sarcasm Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5701-5710} }
Offline-to-Online Knowledge Distillation for Video Instance Segmentation: Hojin Kim,

Seunghun Lee,

Hyeon Kang,

Sunghoon Im; [pdf]
[bibtex]
@InProceedings{Kim_2024_WACV, author = {Kim, Hojin and Lee, Seunghun and Kang, Hyeon and Im, Sunghoon}, title = {Offline-to-Online Knowledge Distillation for Video Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {159-168} }
Rethinking Multimodal Content Moderation From an Asymmetric Angle With Mixed-Modality: Jialin Yuan,

Ye Yu,

Gaurav Mittal,

Matthew Hall,

Sandra Sajeev,

Mei Chen; [pdf] [arXiv]
[bibtex]
@InProceedings{Yuan_2024_WACV, author = {Yuan, Jialin and Yu, Ye and Mittal, Gaurav and Hall, Matthew and Sajeev, Sandra and Chen, Mei}, title = {Rethinking Multimodal Content Moderation From an Asymmetric Angle With Mixed-Modality}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8532-8542} }
Active Learning With Task Consistency and Diversity in Multi-Task Networks: Aral Hekimoglu,

Michael Schmidt,

Alvaro Marcos-Ramiro; [pdf] [supp]
[bibtex]
@InProceedings{Hekimoglu_2024_WACV, author = {Hekimoglu, Aral and Schmidt, Michael and Marcos-Ramiro, Alvaro}, title = {Active Learning With Task Consistency and Diversity in Multi-Task Networks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2503-2512} }
Single Domain Generalization via Normalised Cross-Correlation Based Convolutions: WeiQin Chuah,

Ruwan Tennakoon,

Reza Hoseinnezhad,

David Suter,

Alireza Bab-Hadiashar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chuah_2024_WACV, author = {Chuah, WeiQin and Tennakoon, Ruwan and Hoseinnezhad, Reza and Suter, David and Bab-Hadiashar, Alireza}, title = {Single Domain Generalization via Normalised Cross-Correlation Based Convolutions}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1752-1761} }
Intrinsic Hand Avatar: Illumination-Aware Hand Appearance and Shape Reconstruction From Monocular RGB Video: Pratik Kalshetti,

Parag Chaudhuri; [pdf] [supp]
[bibtex]
@InProceedings{Kalshetti_2024_WACV, author = {Kalshetti, Pratik and Chaudhuri, Parag}, title = {Intrinsic Hand Avatar: Illumination-Aware Hand Appearance and Shape Reconstruction From Monocular RGB Video}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6120-6130} }
Object Re-Identification From Point Clouds: Benjamin Thérien,

Chengjie Huang,

Adrian Chow,

Krzysztof Czarnecki; [pdf] [supp]
[bibtex]
@InProceedings{Therien_2024_WACV, author = {Th\'erien, Benjamin and Huang, Chengjie and Chow, Adrian and Czarnecki, Krzysztof}, title = {Object Re-Identification From Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8377-8388} }
MotionGPT: Human Motion Synthesis With Improved Diversity and Realism via GPT-3 Prompting: Jose Ribeiro-Gomes,

Tianhui Cai,

Zoltán Á. Milacski,

Chen Wu,

Aayush Prakash,

Shingo Takagi,

Amaury Aubel,

Daeil Kim,

Alexandre Bernardino,

Fernando De la Torre; [pdf]
[bibtex]
@InProceedings{Ribeiro-Gomes_2024_WACV, author = {Ribeiro-Gomes, Jose and Cai, Tianhui and Milacski, Zolt\'an \'A. and Wu, Chen and Prakash, Aayush and Takagi, Shingo and Aubel, Amaury and Kim, Daeil and Bernardino, Alexandre and De la Torre, Fernando}, title = {MotionGPT: Human Motion Synthesis With Improved Diversity and Realism via GPT-3 Prompting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5070-5080} }
Training-Based Model Refinement and Representation Disagreement for Semi-Supervised Object Detection: Seyed Mojtaba Marvasti-Zadeh,

Nilanjan Ray,

Nadir Erbilgin; [pdf] [arXiv]
[bibtex]
@InProceedings{Marvasti-Zadeh_2024_WACV, author = {Marvasti-Zadeh, Seyed Mojtaba and Ray, Nilanjan and Erbilgin, Nadir}, title = {Training-Based Model Refinement and Representation Disagreement for Semi-Supervised Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2256-2265} }
Efficient Layout-Guided Image Inpainting for Mobile Use: Wenbo Li,

Yi Wei,

Yilin Shen,

Hongxia Jin; [pdf] [supp]
[bibtex]
@InProceedings{Li_2024_WACV, author = {Li, Wenbo and Wei, Yi and Shen, Yilin and Jin, Hongxia}, title = {Efficient Layout-Guided Image Inpainting for Mobile Use}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8450-8459} }
SigmML: Metric Meta-Learning for Writer Independent Offline Signature Verification in the Space of SPD Matrices: Alexios Giazitzis,

Elias N. Zois; [pdf] [supp]
[bibtex]
@InProceedings{Giazitzis_2024_WACV, author = {Giazitzis, Alexios and Zois, Elias N.}, title = {SigmML: Metric Meta-Learning for Writer Independent Offline Signature Verification in the Space of SPD Matrices}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6312-6322} }
Mini but Mighty: Finetuning ViTs With Mini Adapters: Imad Eddine Marouf,

Enzo Tartaglione,

Stéphane Lathuilière; [pdf] [supp]
[bibtex]
@InProceedings{Marouf_2024_WACV, author = {Marouf, Imad Eddine and Tartaglione, Enzo and Lathuili\`ere, St\'ephane}, title = {Mini but Mighty: Finetuning ViTs With Mini Adapters}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1732-1741} }
Dynamic Multimodal Information Bottleneck for Multimodality Classification: Yingying Fang,

Shuang Wu,

Sheng Zhang,

Chaoyan Huang,

Tieyong Zeng,

Xiaodan Xing,

Simon Walsh,

Guang Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fang_2024_WACV, author = {Fang, Yingying and Wu, Shuang and Zhang, Sheng and Huang, Chaoyan and Zeng, Tieyong and Xing, Xiaodan and Walsh, Simon and Yang, Guang}, title = {Dynamic Multimodal Information Bottleneck for Multimodality Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7696-7706} }
Learning Generalizable Perceptual Representations for Data-Efficient No-Reference Image Quality Assessment: Suhas Srinath,

Shankhanil Mitra,

Shika Rao,

Rajiv Soundararajan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Srinath_2024_WACV, author = {Srinath, Suhas and Mitra, Shankhanil and Rao, Shika and Soundararajan, Rajiv}, title = {Learning Generalizable Perceptual Representations for Data-Efficient No-Reference Image Quality Assessment}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {22-31} }
Real Time GAZED: Online Shot Selection and Editing of Virtual Cameras From Wide-Angle Monocular Video Recordings: Sudheer Achary,

Rohit Girmaji,

Adhiraj Anil Deshmukh,

Vineet Gandhi; [pdf] [arXiv]
[bibtex]
@InProceedings{Achary_2024_WACV, author = {Achary, Sudheer and Girmaji, Rohit and Deshmukh, Adhiraj Anil and Gandhi, Vineet}, title = {Real Time GAZED: Online Shot Selection and Editing of Virtual Cameras From Wide-Angle Monocular Video Recordings}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4108-4116} }
ConfTrack: Kalman Filter-Based Multi-Person Tracking by Utilizing Confidence Score of Detection Box: Hyeonchul Jung,

Seokjun Kang,

Takgen Kim,

HyeongKi Kim; [pdf]
[bibtex]
@InProceedings{Jung_2024_WACV, author = {Jung, Hyeonchul and Kang, Seokjun and Kim, Takgen and Kim, HyeongKi}, title = {ConfTrack: Kalman Filter-Based Multi-Person Tracking by Utilizing Confidence Score of Detection Box}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6583-6592} }
Hybrid Sample Synthesis-Based Debiasing of Classifier in Limited Data Setting: Piyush Arora,

Pratik Mazumder; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Arora_2024_WACV, author = {Arora, Piyush and Mazumder, Pratik}, title = {Hybrid Sample Synthesis-Based Debiasing of Classifier in Limited Data Setting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4791-4799} }
Visually Guided Audio Source Separation With Meta Consistency Learning: Md Amirul Islam,

Seyed Shahabeddin Nabavi,

Irina Kezele,

Yang Wang,

Yuanhao Yu,

Jin Tang; [pdf] [supp]
[bibtex]
@InProceedings{Islam_2024_WACV, author = {Islam, Md Amirul and Nabavi, Seyed Shahabeddin and Kezele, Irina and Wang, Yang and Yu, Yuanhao and Tang, Jin}, title = {Visually Guided Audio Source Separation With Meta Consistency Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3014-3023} }
RGBT-Dog: A Parametric Model and Pose Prior for Canine Body Analysis Data Creation: Jake Deane,

Sinéad Kearney,

Kwang In Kim,

Darren Cosker; [pdf] [supp]
[bibtex]
@InProceedings{Deane_2024_WACV, author = {Deane, Jake and Kearney, Sin\'ead and Kim, Kwang In and Cosker, Darren}, title = {RGBT-Dog: A Parametric Model and Pose Prior for Canine Body Analysis Data Creation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6056-6066} }
Diffusion-Based Generation of Histopathological Whole Slide Images at a Gigapixel Scale: Robert Harb,

Thomas Pock,

Heimo Müller; [pdf] [supp]
[bibtex]
@InProceedings{Harb_2024_WACV, author = {Harb, Robert and Pock, Thomas and M\"uller, Heimo}, title = {Diffusion-Based Generation of Histopathological Whole Slide Images at a Gigapixel Scale}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5131-5140} }
Bridging the Gap Between Multi-Focus and Multi-Modal: A Focused Integration Framework for Multi-Modal Image Fusion: Xilai Li,

Xiaosong Li,

Tao Ye,

Xiaoqi Cheng,

Wuyang Liu,

Haishu Tan; [pdf]
[bibtex]
@InProceedings{Li_2024_WACV, author = {Li, Xilai and Li, Xiaosong and Ye, Tao and Cheng, Xiaoqi and Liu, Wuyang and Tan, Haishu}, title = {Bridging the Gap Between Multi-Focus and Multi-Modal: A Focused Integration Framework for Multi-Modal Image Fusion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1628-1637} }
Image Labels Are All You Need for Coarse Seagrass Segmentation: Scarlett Raine,

Ross Marchant,

Brano Kusy,

Frederic Maire,

Tobias Fischer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Raine_2024_WACV, author = {Raine, Scarlett and Marchant, Ross and Kusy, Brano and Maire, Frederic and Fischer, Tobias}, title = {Image Labels Are All You Need for Coarse Seagrass Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5943-5952} }
Registered and Segmented Deformable Object Reconstruction From a Single View Point Cloud: Pit Henrich,

Balázs Gyenes,

Paul Maria Scheikl,

Gerhard Neumann,

Franziska Mathis-Ullrich; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Henrich_2024_WACV, author = {Henrich, Pit and Gyenes, Bal\'azs and Scheikl, Paul Maria and Neumann, Gerhard and Mathis-Ullrich, Franziska}, title = {Registered and Segmented Deformable Object Reconstruction From a Single View Point Cloud}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3129-3138} }
Adaptive Manifold for Imbalanced Transductive Few-Shot Learning: Michalis Lazarou,

Yannis Avrithis,

Tania Stathaki; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lazarou_2024_WACV, author = {Lazarou, Michalis and Avrithis, Yannis and Stathaki, Tania}, title = {Adaptive Manifold for Imbalanced Transductive Few-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2297-2306} }
Restoring Degraded Old Films With Recursive Recurrent Transformer Networks: Shan Lin,

Edgar Simo-Serra; [pdf] [supp]
[bibtex]
@InProceedings{Lin_2024_WACV, author = {Lin, Shan and Simo-Serra, Edgar}, title = {Restoring Degraded Old Films With Recursive Recurrent Transformer Networks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6718-6728} }
Re-Evaluating LiDAR Scene Flow: Nathaniel Chodosh,

Deva Ramanan,

Simon Lucey; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chodosh_2024_WACV, author = {Chodosh, Nathaniel and Ramanan, Deva and Lucey, Simon}, title = {Re-Evaluating LiDAR Scene Flow}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6005-6015} }
Unsupervised 3D Pose Estimation With Non-Rigid Structure-From-Motion Modeling: Haorui Ji,

Hui Deng,

Yuchao Dai,

Hongdong Li; [pdf] [arXiv]
[bibtex]
@InProceedings{Ji_2024_WACV, author = {Ji, Haorui and Deng, Hui and Dai, Yuchao and Li, Hongdong}, title = {Unsupervised 3D Pose Estimation With Non-Rigid Structure-From-Motion Modeling}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3314-3323} }
FAKD: Feature Augmented Knowledge Distillation for Semantic Segmentation: Jianlong Yuan,

Minh Hieu Phan,

Liyang Liu,

Yifan Liu; [pdf] [supp]
[bibtex]
@InProceedings{Yuan_2024_WACV, author = {Yuan, Jianlong and Phan, Minh Hieu and Liu, Liyang and Liu, Yifan}, title = {FAKD: Feature Augmented Knowledge Distillation for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {595-605} }
TriCoLo: Trimodal Contrastive Loss for Text To Shape Retrieval: Yue Ruan,

Han-Hung Lee,

Yiming Zhang,

Ke Zhang,

Angel X. Chang; [pdf] [supp]
[bibtex]
@InProceedings{Ruan_2024_WACV, author = {Ruan, Yue and Lee, Han-Hung and Zhang, Yiming and Zhang, Ke and Chang, Angel X.}, title = {TriCoLo: Trimodal Contrastive Loss for Text To Shape Retrieval}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5815-5825} }
Expanding Expressiveness of Diffusion Models With Limited Data via Self-Distillation Based Fine-Tuning: Jiwan Hur,

Jaehyun Choi,

Gyojin Han,

Dong-Jae Lee,

Junmo Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hur_2024_WACV, author = {Hur, Jiwan and Choi, Jaehyun and Han, Gyojin and Lee, Dong-Jae and Kim, Junmo}, title = {Expanding Expressiveness of Diffusion Models With Limited Data via Self-Distillation Based Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5028-5037} }
Diff2Lip: Audio Conditioned Diffusion Models for Lip-Synchronization: Soumik Mukhopadhyay,

Saksham Suri,

Ravi Teja Gadde,

Abhinav Shrivastava; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mukhopadhyay_2024_WACV, author = {Mukhopadhyay, Soumik and Suri, Saksham and Gadde, Ravi Teja and Shrivastava, Abhinav}, title = {Diff2Lip: Audio Conditioned Diffusion Models for Lip-Synchronization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5292-5302} }
A*: Atrous Spatial Temporal Action Recognition for Real Time Applications: Myeongjun Kim,

Federica Spinola,

Philipp Benz,

Tae-hoon Kim; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2024_WACV, author = {Kim, Myeongjun and Spinola, Federica and Benz, Philipp and Kim, Tae-hoon}, title = {A*: Atrous Spatial Temporal Action Recognition for Real Time Applications}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7014-7024} }
Augment the Pairs: Semantics-Preserving Image-Caption Pair Augmentation for Grounding-Based Vision and Language Models: Jingru Yi,

Burak Uzkent,

Oana Ignat,

Zili Li,

Amanmeet Garg,

Xiang Yu,

Linda Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Yi_2024_WACV, author = {Yi, Jingru and Uzkent, Burak and Ignat, Oana and Li, Zili and Garg, Amanmeet and Yu, Xiang and Liu, Linda}, title = {Augment the Pairs: Semantics-Preserving Image-Caption Pair Augmentation for Grounding-Based Vision and Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5520-5530} }
Controllable Image Synthesis of Industrial Data Using Stable Diffusion: Gabriele Valvano,

Antonino Agostino,

Giovanni De Magistris,

Antonino Graziano,

Giacomo Veneri; [pdf]
[bibtex]
@InProceedings{Valvano_2024_WACV, author = {Valvano, Gabriele and Agostino, Antonino and De Magistris, Giovanni and Graziano, Antonino and Veneri, Giacomo}, title = {Controllable Image Synthesis of Industrial Data Using Stable Diffusion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5354-5363} }
Understanding Dark Scenes by Contrasting Multi-Modal Observations: Xiaoyu Dong,

Naoto Yokoya; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dong_2024_WACV, author = {Dong, Xiaoyu and Yokoya, Naoto}, title = {Understanding Dark Scenes by Contrasting Multi-Modal Observations}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {840-850} }
Expanding Hyperspherical Space for Few-Shot Class-Incremental Learning: Yao Deng,

Xiang Xiang; [pdf]
[bibtex]
@InProceedings{Deng_2024_WACV, author = {Deng, Yao and Xiang, Xiang}, title = {Expanding Hyperspherical Space for Few-Shot Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1967-1976} }
Differentially Private Video Activity Recognition: Zelun Luo,

Yuliang Zou,

Yijin Yang,

Zane Durante,

De-An Huang,

Zhiding Yu,

Chaowei Xiao,

Li Fei-Fei,

Animashree Anandkumar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Luo_2024_WACV, author = {Luo, Zelun and Zou, Yuliang and Yang, Yijin and Durante, Zane and Huang, De-An and Yu, Zhiding and Xiao, Chaowei and Fei-Fei, Li and Anandkumar, Animashree}, title = {Differentially Private Video Activity Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6657-6667} }
Towards a Dynamic Vision Sensor-Based Insect Camera Trap: Eike Gebauer,

Sebastian Thiele,

Pierre Ouvrard,

Adrien Sicard,

Benjamin Risse; [pdf]
[bibtex]
@InProceedings{Gebauer_2024_WACV, author = {Gebauer, Eike and Thiele, Sebastian and Ouvrard, Pierre and Sicard, Adrien and Risse, Benjamin}, title = {Towards a Dynamic Vision Sensor-Based Insect Camera Trap}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7157-7166} }
FLORA: Fine-Grained Low-Rank Architecture Search for Vision Transformer: Chi-Chih Chang,

Yuan-Yao Sung,

Shixing Yu,

Ning-Chi Huang,

Diana Marculescu,

Kai-Chiang Wu; [pdf] [arXiv]
[bibtex]
@InProceedings{Chang_2024_WACV, author = {Chang, Chi-Chih and Sung, Yuan-Yao and Yu, Shixing and Huang, Ning-Chi and Marculescu, Diana and Wu, Kai-Chiang}, title = {FLORA: Fine-Grained Low-Rank Architecture Search for Vision Transformer}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2482-2491} }
Latent-Guided Exemplar-Based Image Re-Colorization: Wenjie Yang,

Ning Xu,

Yifei Fan; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2024_WACV, author = {Yang, Wenjie and Xu, Ning and Fan, Yifei}, title = {Latent-Guided Exemplar-Based Image Re-Colorization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4250-4259} }
Data Augmentation for Object Detection via Controllable Diffusion Models: Haoyang Fang,

Boran Han,

Shuai Zhang,

Su Zhou,

Cuixiong Hu,

Wen-Ming Ye; [pdf] [supp]
[bibtex]
@InProceedings{Fang_2024_WACV, author = {Fang, Haoyang and Han, Boran and Zhang, Shuai and Zhou, Su and Hu, Cuixiong and Ye, Wen-Ming}, title = {Data Augmentation for Object Detection via Controllable Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1257-1266} }
Self-Supervised Learning With Masked Autoencoders for Teeth Segmentation From Intra-Oral 3D Scans: Amani Almalki,

Longin Jan Latecki; [pdf] [supp]
[bibtex]
@InProceedings{Almalki_2024_WACV, author = {Almalki, Amani and Latecki, Longin Jan}, title = {Self-Supervised Learning With Masked Autoencoders for Teeth Segmentation From Intra-Oral 3D Scans}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7820-7830} }
Small Objects Matters in Weakly-Supervised Semantic Segmentation: Cheolhyun Mun,

Sanghuk Lee,

Youngjung Uh,

Junsuk Choe,

Hyeran Byun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mun_2024_WACV, author = {Mun, Cheolhyun and Lee, Sanghuk and Uh, Youngjung and Choe, Junsuk and Byun, Hyeran}, title = {Small Objects Matters in Weakly-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {414-423} }
MaskConver: Revisiting Pure Convolution Model for Panoptic Segmentation: Abdullah Rashwan,

Jiageng Zhang,

Ali Taalimi,

Fan Yang,

Xingyi Zhou,

Chaochao Yan,

Liang-Chieh Chen,

Yeqing Li; [pdf] [arXiv]
[bibtex]
@InProceedings{Rashwan_2024_WACV, author = {Rashwan, Abdullah and Zhang, Jiageng and Taalimi, Ali and Yang, Fan and Zhou, Xingyi and Yan, Chaochao and Chen, Liang-Chieh and Li, Yeqing}, title = {MaskConver: Revisiting Pure Convolution Model for Panoptic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {851-861} }
From Chaos to Calibration: A Geometric Mutual Information Approach To Target-Free Camera LiDAR Extrinsic Calibration: Jack Borer,

Jeremy Tschirner,

Florian Ölsner,

Stefan Milz; [pdf]
[bibtex]
@InProceedings{Borer_2024_WACV, author = {Borer, Jack and Tschirner, Jeremy and \"Olsner, Florian and Milz, Stefan}, title = {From Chaos to Calibration: A Geometric Mutual Information Approach To Target-Free Camera LiDAR Extrinsic Calibration}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8409-8418} }
PHG-Net: Persistent Homology Guided Medical Image Classification: Yaopeng Peng,

Hongxiao Wang,

Milan Sonka,

Danny Z. Chen; [pdf]
[bibtex]
@InProceedings{Peng_2024_WACV, author = {Peng, Yaopeng and Wang, Hongxiao and Sonka, Milan and Chen, Danny Z.}, title = {PHG-Net: Persistent Homology Guided Medical Image Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7583-7592} }
Masking Improves Contrastive Self-Supervised Learning for ConvNets, and Saliency Tells You Where: Zhi-Yi Chin,

Chieh-Ming Jiang,

Ching-Chun Huang,

Pin-Yu Chen,

Wei-Chen Chiu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chin_2024_WACV, author = {Chin, Zhi-Yi and Jiang, Chieh-Ming and Huang, Ching-Chun and Chen, Pin-Yu and Chiu, Wei-Chen}, title = {Masking Improves Contrastive Self-Supervised Learning for ConvNets, and Saliency Tells You Where}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2761-2770} }
Cheating Depth: Enhancing 3D Surface Anomaly Detection via Depth Simulation: Vitjan Zavrtanik,

Matej Kristan,

Danijel Skočaj; [pdf] [supp]
[bibtex]
@InProceedings{Zavrtanik_2024_WACV, author = {Zavrtanik, Vitjan and Kristan, Matej and Sko\v{c}aj, Danijel}, title = {Cheating Depth: Enhancing 3D Surface Anomaly Detection via Depth Simulation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2164-2172} }
CLID: Controlled-Length Image Descriptions With Limited Data: Elad Hirsch,

Ayellet Tal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hirsch_2024_WACV, author = {Hirsch, Elad and Tal, Ayellet}, title = {CLID: Controlled-Length Image Descriptions With Limited Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5531-5541} }
Steering Prototypes With Prompt-Tuning for Rehearsal-Free Continual Learning: Zhuowei Li,

Long Zhao,

Zizhao Zhang,

Han Zhang,

Di Liu,

Ting Liu,

Dimitris N. Metaxas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_WACV, author = {Li, Zhuowei and Zhao, Long and Zhang, Zizhao and Zhang, Han and Liu, Di and Liu, Ting and Metaxas, Dimitris N.}, title = {Steering Prototypes With Prompt-Tuning for Rehearsal-Free Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2523-2533} }
Modality-Aware Representation Learning for Zero-Shot Sketch-Based Image Retrieval: Eunyi Lyou,

Doyeon Lee,

Jooeun Kim,

Joonseok Lee; [pdf] [supp]
[bibtex]
@InProceedings{Lyou_2024_WACV, author = {Lyou, Eunyi and Lee, Doyeon and Kim, Jooeun and Lee, Joonseok}, title = {Modality-Aware Representation Learning for Zero-Shot Sketch-Based Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5646-5655} }
Concurrent Band Selection and Traversability Estimation From Long-Wave Hyperspectral Imagery in Off-Road Settings: Florence Yellin,

Scott McCloskey,

Cole Hill,

Eric Smith,

Brian Clipp; [pdf]
[bibtex]
@InProceedings{Yellin_2024_WACV, author = {Yellin, Florence and McCloskey, Scott and Hill, Cole and Smith, Eric and Clipp, Brian}, title = {Concurrent Band Selection and Traversability Estimation From Long-Wave Hyperspectral Imagery in Off-Road Settings}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7483-7492} }
Token Fusion: Bridging the Gap Between Token Pruning and Token Merging: Minchul Kim,

Shangqian Gao,

Yen-Chang Hsu,

Yilin Shen,

Hongxia Jin; [pdf] [arXiv]
[bibtex]
@InProceedings{Kim_2024_WACV, author = {Kim, Minchul and Gao, Shangqian and Hsu, Yen-Chang and Shen, Yilin and Jin, Hongxia}, title = {Token Fusion: Bridging the Gap Between Token Pruning and Token Merging}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1383-1392} }
Global Occlusion-Aware Transformer for Robust Stereo Matching: Zihua Liu,

Yizhou Li,

Masatoshi Okutomi; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2024_WACV, author = {Liu, Zihua and Li, Yizhou and Okutomi, Masatoshi}, title = {Global Occlusion-Aware Transformer for Robust Stereo Matching}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3535-3544} }
SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstruction: Sebastian Koch,

Pedro Hermosilla,

Narunas Vaskevicius,

Mirco Colosi,

Timo Ropinski; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Koch_2024_WACV, author = {Koch, Sebastian and Hermosilla, Pedro and Vaskevicius, Narunas and Colosi, Mirco and Ropinski, Timo}, title = {SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3404-3414} }
Estimating Fog Parameters From an Image Sequence Using Non-Linear Optimisation: Yining Ding,

Andrew M. Wallace,

Sen Wang; [pdf] [supp]
[bibtex]
@InProceedings{Ding_2024_WACV, author = {Ding, Yining and Wallace, Andrew M. and Wang, Sen}, title = {Estimating Fog Parameters From an Image Sequence Using Non-Linear Optimisation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1578-1586} }
Fast and Interpretable Face Identification for Out-of-Distribution Data Using Vision Transformers: Hai Phan,

Cindy X. Le,

Vu Le,

Yihui He,

Anh “Totti” Nguyen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Phan_2024_WACV, author = {Phan, Hai and Le, Cindy X. and Le, Vu and He, Yihui and Nguyen, Anh {\textquotedblleft}Totti{\textquotedblright}}, title = {Fast and Interpretable Face Identification for Out-of-Distribution Data Using Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6301-6311} }
Investigating the Role of Attribute Context in Vision-Language Models for Object Recognition and Detection: Kyle Buettner,

Adriana Kovashka; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Buettner_2024_WACV, author = {Buettner, Kyle and Kovashka, Adriana}, title = {Investigating the Role of Attribute Context in Vision-Language Models for Object Recognition and Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5474-5484} }
Membership Inference Attack Using Self Influence Functions: Gilad Cohen,

Raja Giryes; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cohen_2024_WACV, author = {Cohen, Gilad and Giryes, Raja}, title = {Membership Inference Attack Using Self Influence Functions}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4892-4901} }
Mixing Gradients in Neural Networks as a Strategy To Enhance Privacy in Federated Learning: Shaltiel Eloul,

Fran Silavong,

Sanket Kamthe,

Antonios Georgiadis,

Sean J. Moran; [pdf] [supp]
[bibtex]
@InProceedings{Eloul_2024_WACV, author = {Eloul, Shaltiel and Silavong, Fran and Kamthe, Sanket and Georgiadis, Antonios and Moran, Sean J.}, title = {Mixing Gradients in Neural Networks as a Strategy To Enhance Privacy in Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3956-3965} }
Learning to Read Analog Gauges from Synthetic Data: Juan Leon-Alcazar,

Yazeed Alnumay,

Cheng Zheng,

Hassane Trigui,

Sahejad Patel,

Bernard Ghanem; [pdf] [arXiv]
[bibtex]
@InProceedings{Leon-Alcazar_2024_WACV, author = {Leon-Alcazar, Juan and Alnumay, Yazeed and Zheng, Cheng and Trigui, Hassane and Patel, Sahejad and Ghanem, Bernard}, title = {Learning to Read Analog Gauges from Synthetic Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8616-8625} }
Learning Saliency From Fixations: Yasser Abdelaziz Dahou Djilali,

Kevin McGuinness,

Noel O’Connor; [pdf] [supp]
[bibtex]
@InProceedings{Djilali_2024_WACV, author = {Djilali, Yasser Abdelaziz Dahou and McGuinness, Kevin and O{\textquoteright}Connor, Noel}, title = {Learning Saliency From Fixations}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {383-393} }
PECoP: Parameter Efficient Continual Pretraining for Action Quality Assessment: Amirhossein Dadashzadeh,

Shuchao Duan,

Alan Whone,

Majid Mirmehdi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dadashzadeh_2024_WACV, author = {Dadashzadeh, Amirhossein and Duan, Shuchao and Whone, Alan and Mirmehdi, Majid}, title = {PECoP: Parameter Efficient Continual Pretraining for Action Quality Assessment}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {42-52} }
Face Identity-Aware Disentanglement in StyleGAN: Adrian Suwała,

Bartosz Wójcik,

Magdalena Proszewska,

Jacek Tabor,

Przemysław Spurek,

Marek Śmieja; [pdf]
[bibtex]
@InProceedings{Suwala_2024_WACV, author = {Suwa{\l}a, Adrian and W\'ojcik, Bartosz and Proszewska, Magdalena and Tabor, Jacek and Spurek, Przemys{\l}aw and \'Smieja, Marek}, title = {Face Identity-Aware Disentanglement in StyleGAN}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5222-5231} }
A Robust Diffusion Modeling Framework for Radar Camera 3D Object Detection: Zizhang Wu,

Yunzhe Wu,

Xiaoquan Wang,

Yuanzhu Gan,

Jian Pu; [pdf]
[bibtex]
@InProceedings{Wu_2024_WACV, author = {Wu, Zizhang and Wu, Yunzhe and Wang, Xiaoquan and Gan, Yuanzhu and Pu, Jian}, title = {A Robust Diffusion Modeling Framework for Radar Camera 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3282-3292} }
InfraParis: A Multi-Modal and Multi-Task Autonomous Driving Dataset: Gianni Franchi,

Marwane Hariat,

Xuanlong Yu,

Nacim Belkhir,

Antoine Manzanera,

David Filliat; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Franchi_2024_WACV, author = {Franchi, Gianni and Hariat, Marwane and Yu, Xuanlong and Belkhir, Nacim and Manzanera, Antoine and Filliat, David}, title = {InfraParis: A Multi-Modal and Multi-Task Autonomous Driving Dataset}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2973-2983} }
LAVSS: Location-Guided Audio-Visual Spatial Audio Separation: Yuxin Ye,

Wenming Yang,

Yapeng Tian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ye_2024_WACV, author = {Ye, Yuxin and Yang, Wenming and Tian, Yapeng}, title = {LAVSS: Location-Guided Audio-Visual Spatial Audio Separation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5508-5519} }
PIDiffu: Pixel-Aligned Diffusion Model for High-Fidelity Clothed Human Reconstruction: Jungeun Lee,

Sanghun Kim,

Hansol Lee,

Tserendorj Adiya,

Hwasup Lim; [pdf]
[bibtex]
@InProceedings{Lee_2024_WACV, author = {Lee, Jungeun and Kim, Sanghun and Lee, Hansol and Adiya, Tserendorj and Lim, Hwasup}, title = {PIDiffu: Pixel-Aligned Diffusion Model for High-Fidelity Clothed Human Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5172-5181} }
Kaizen: Practical Self-Supervised Continual Learning With Continual Fine-Tuning: Chi Ian Tang,

Lorena Qendro,

Dimitris Spathis,

Fahim Kawsar,

Cecilia Mascolo,

Akhil Mathur; [pdf] [supp]
[bibtex]
@InProceedings{Tang_2024_WACV, author = {Tang, Chi Ian and Qendro, Lorena and Spathis, Dimitris and Kawsar, Fahim and Mascolo, Cecilia and Mathur, Akhil}, title = {Kaizen: Practical Self-Supervised Continual Learning With Continual Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2841-2850} }
SBCFormer: Lightweight Network Capable of Full-Size ImageNet Classification at 1 FPS on Single Board Computers: Xiangyong Lu,

Masanori Suganuma,

Takayuki Okatani; [pdf] [arXiv]
[bibtex]
@InProceedings{Lu_2024_WACV, author = {Lu, Xiangyong and Suganuma, Masanori and Okatani, Takayuki}, title = {SBCFormer: Lightweight Network Capable of Full-Size ImageNet Classification at 1 FPS on Single Board Computers}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1123-1133} }
Fixing Overconfidence in Dynamic Neural Networks: Lassi Meronen,

Martin Trapp,

Andrea Pilzer,

Le Yang,

Arno Solin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Meronen_2024_WACV, author = {Meronen, Lassi and Trapp, Martin and Pilzer, Andrea and Yang, Le and Solin, Arno}, title = {Fixing Overconfidence in Dynamic Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2680-2690} }
Multispectral Imaging for Differential Face Morphing Attack Detection: A Preliminary Study: Raghavendra Ramachandra,

Sushma Venkatesh,

Naser Damer,

Narayan Vetrekar,

R. S. Gad; [pdf] [arXiv]
[bibtex]
@InProceedings{Ramachandra_2024_WACV, author = {Ramachandra, Raghavendra and Venkatesh, Sushma and Damer, Naser and Vetrekar, Narayan and Gad, R. S.}, title = {Multispectral Imaging for Differential Face Morphing Attack Detection: A Preliminary Study}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6185-6193} }
Learning Robust Deep Visual Representations From EEG Brain Recordings: Prajwal Singh,

Dwip Dalal,

Gautam Vashishtha,

Krishna Miyapuram,

Shanmuganathan Raman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Singh_2024_WACV, author = {Singh, Prajwal and Dalal, Dwip and Vashishtha, Gautam and Miyapuram, Krishna and Raman, Shanmuganathan}, title = {Learning Robust Deep Visual Representations From EEG Brain Recordings}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7553-7562} }
Spiking Denoising Diffusion Probabilistic Models: Jiahang Cao,

Ziqing Wang,

Hanzhong Guo,

Hao Cheng,

Qiang Zhang,

Renjing Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2024_WACV, author = {Cao, Jiahang and Wang, Ziqing and Guo, Hanzhong and Cheng, Hao and Zhang, Qiang and Xu, Renjing}, title = {Spiking Denoising Diffusion Probabilistic Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4912-4921} }
An Analysis of Initial Training Strategies for Exemplar-Free Class-Incremental Learning: Grégoire Petit,

Michaël Soumm,

Eva Feillet,

Adrian Popescu,

Bertrand Delezoide,

David Picard,

Céline Hudelot; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Petit_2024_WACV, author = {Petit, Gr\'egoire and Soumm, Micha\"el and Feillet, Eva and Popescu, Adrian and Delezoide, Bertrand and Picard, David and Hudelot, C\'eline}, title = {An Analysis of Initial Training Strategies for Exemplar-Free Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1837-1847} }
Taming Normalizing Flows: Shimon Malnick,

Shai Avidan,

Ohad Fried; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Malnick_2024_WACV, author = {Malnick, Shimon and Avidan, Shai and Fried, Ohad}, title = {Taming Normalizing Flows}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4644-4654} }
Booster-SHOT: Boosting Stacked Homography Transformations for Multiview Pedestrian Detection With Attention: Jinwoo Hwang,

Philipp Benz,

Pete Kim; [pdf] [supp]
[bibtex]
@InProceedings{Hwang_2024_WACV, author = {Hwang, Jinwoo and Benz, Philipp and Kim, Pete}, title = {Booster-SHOT: Boosting Stacked Homography Transformations for Multiview Pedestrian Detection With Attention}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {363-372} }
ZRG: A Dataset for Multimodal 3D Residential Rooftop Understanding: Isaac Corley,

Jonathan Lwowski,

Peyman Najafirad; [pdf] [arXiv]
[bibtex]
@InProceedings{Corley_2024_WACV, author = {Corley, Isaac and Lwowski, Jonathan and Najafirad, Peyman}, title = {ZRG: A Dataset for Multimodal 3D Residential Rooftop Understanding}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4635-4643} }
Beyond Self-Attention: Deformable Large Kernel Attention for Medical Image Segmentation: Reza Azad,

Leon Niggemeier,

Michael Hüttemann,

Amirhossein Kazerouni,

Ehsan Khodapanah Aghdam,

Yury Velichko,

Ulas Bagci,

Dorit Merhof; [pdf] [supp]
[bibtex]
@InProceedings{Azad_2024_WACV, author = {Azad, Reza and Niggemeier, Leon and H\"uttemann, Michael and Kazerouni, Amirhossein and Aghdam, Ehsan Khodapanah and Velichko, Yury and Bagci, Ulas and Merhof, Dorit}, title = {Beyond Self-Attention: Deformable Large Kernel Attention for Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1287-1297} }
OOD Aware Supervised Contrastive Learning: Soroush Seifi,

Daniel Olmeda Reino,

Nikolay Chumerin,

Rahaf Aljundi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Seifi_2024_WACV, author = {Seifi, Soroush and Reino, Daniel Olmeda and Chumerin, Nikolay and Aljundi, Rahaf}, title = {OOD Aware Supervised Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1956-1966} }
Meta-Learned Kernel for Blind Super-Resolution Kernel Estimation: Royson Lee,

Rui Li,

Stylianos Venieris,

Timothy Hospedales,

Ferenc Huszár,

Nicholas D. Lane; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2024_WACV, author = {Lee, Royson and Li, Rui and Venieris, Stylianos and Hospedales, Timothy and Husz\'ar, Ferenc and Lane, Nicholas D.}, title = {Meta-Learned Kernel for Blind Super-Resolution Kernel Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1496-1505} }
DDAM-PS: Diligent Domain Adaptive Mixer for Person Search: Mohammed Khaleed Almansoori,

Mustansar Fiaz,

Hisham Cholakkal; [pdf]
[bibtex]
@InProceedings{Almansoori_2024_WACV, author = {Almansoori, Mohammed Khaleed and Fiaz, Mustansar and Cholakkal, Hisham}, title = {DDAM-PS: Diligent Domain Adaptive Mixer for Person Search}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6688-6697} }
ArtQuest: Countering Hidden Language Biases in ArtVQA: Tibor Bleidt,

Sedigheh Eslami,

Gerard de Melo; [pdf]
[bibtex]
@InProceedings{Bleidt_2024_WACV, author = {Bleidt, Tibor and Eslami, Sedigheh and de Melo, Gerard}, title = {ArtQuest: Countering Hidden Language Biases in ArtVQA}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7326-7335} }
ISAR: A Benchmark for Single- and Few-Shot Object Instance Segmentation and Re-Identification: Nicolas Gorlo,

Kenneth Blomqvist,

Francesco Milano,

Roland Siegwart; [pdf]
[bibtex]
@InProceedings{Gorlo_2024_WACV, author = {Gorlo, Nicolas and Blomqvist, Kenneth and Milano, Francesco and Siegwart, Roland}, title = {ISAR: A Benchmark for Single- and Few-Shot Object Instance Segmentation and Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4384-4396} }
Textron: Weakly Supervised Multilingual Text Detection Through Data Programming: Dhruv Kudale,

Badri Vishal Kasuba,

Venkatapathy Subramanian,

Parag Chaudhuri,

Ganesh Ramakrishnan; [pdf] [supp]
[bibtex]
@InProceedings{Kudale_2024_WACV, author = {Kudale, Dhruv and Kasuba, Badri Vishal and Subramanian, Venkatapathy and Chaudhuri, Parag and Ramakrishnan, Ganesh}, title = {Textron: Weakly Supervised Multilingual Text Detection Through Data Programming}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2871-2880} }
Sharp-NeRF: Grid-Based Fast Deblurring Neural Radiance Fields Using Sharpness Prior: Byeonghyeon Lee,

Howoong Lee,

Usman Ali,

Eunbyung Park; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2024_WACV, author = {Lee, Byeonghyeon and Lee, Howoong and Ali, Usman and Park, Eunbyung}, title = {Sharp-NeRF: Grid-Based Fast Deblurring Neural Radiance Fields Using Sharpness Prior}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3709-3718} }
4K-Resolution Photo Exposure Correction at 125 FPS With ~8K Parameters: Yijie Zhou,

Chao Li,

Jin Liang,

Tianyi Xu,

Xin Liu,

Jun Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2024_WACV, author = {Zhou, Yijie and Li, Chao and Liang, Jin and Xu, Tianyi and Liu, Xin and Xu, Jun}, title = {4K-Resolution Photo Exposure Correction at 125 FPS With {\textasciitilde}8K Parameters}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1587-1597} }
Context-Based Interpretable Spatio-Temporal Graph Convolutional Network for Human Motion Forecasting: Edgar Medina,

Leyong Loh,

Namrata Gurung,

Kyung Hun Oh,

Niels Heller; [pdf] [supp]
[bibtex]
@InProceedings{Medina_2024_WACV, author = {Medina, Edgar and Loh, Leyong and Gurung, Namrata and Oh, Kyung Hun and Heller, Niels}, title = {Context-Based Interpretable Spatio-Temporal Graph Convolutional Network for Human Motion Forecasting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3232-3241} }
TPSeNCE: Towards Artifact-Free Realistic Rain Generation for Deraining and Object Detection in Rain: Shen Zheng,

Changjie Lu,

Srinivasa G. Narasimhan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2024_WACV, author = {Zheng, Shen and Lu, Changjie and Narasimhan, Srinivasa G.}, title = {TPSeNCE: Towards Artifact-Free Realistic Rain Generation for Deraining and Object Detection in Rain}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5394-5403} }
Robust Category-Level 3D Pose Estimation From Diffusion-Enhanced Synthetic Data: Jiahao Yang,

Wufei Ma,

Angtian Wang,

Xiaoding Yuan,

Alan Yuille,

Adam Kortylewski; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2024_WACV, author = {Yang, Jiahao and Ma, Wufei and Wang, Angtian and Yuan, Xiaoding and Yuille, Alan and Kortylewski, Adam}, title = {Robust Category-Level 3D Pose Estimation From Diffusion-Enhanced Synthetic Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3446-3455} }
Vision Transformer for Multispectral Satellite Imagery: Advancing Landcover Classification: Ryan Rad; [pdf]
[bibtex]
@InProceedings{Rad_2024_WACV, author = {Rad, Ryan}, title = {Vision Transformer for Multispectral Satellite Imagery: Advancing Landcover Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8176-8183} }
ENTED: Enhanced Neural Texture Extraction and Distribution for Reference-Based Blind Face Restoration: Yuen-Fui Lau,

Tianjia Zhang,

Zhefan Rao,

Qifeng Chen; [pdf] [supp]
[bibtex]
@InProceedings{Lau_2024_WACV, author = {Lau, Yuen-Fui and Zhang, Tianjia and Rao, Zhefan and Chen, Qifeng}, title = {ENTED: Enhanced Neural Texture Extraction and Distribution for Reference-Based Blind Face Restoration}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5162-5171} }
A Sequential Learning-Based Approach for Monocular Human Performance Capture: Jianchun Chen,

Jayakorn Vongkulbhisal,

Fernando De la Torre Frade; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2024_WACV, author = {Chen, Jianchun and Vongkulbhisal, Jayakorn and De la Torre Frade, Fernando}, title = {A Sequential Learning-Based Approach for Monocular Human Performance Capture}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3514-3523} }
VCISR: Blind Single Image Super-Resolution With Video Compression Synthetic Data: Boyang Wang,

Bowen Liu,

Shiyu Liu,

Fengyu Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_WACV, author = {Wang, Boyang and Liu, Bowen and Liu, Shiyu and Yang, Fengyu}, title = {VCISR: Blind Single Image Super-Resolution With Video Compression Synthetic Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4302-4312} }
Synthesizing Coherent Story With Auto-Regressive Latent Diffusion Models: Xichen Pan,

Pengda Qin,

Yuhong Li,

Hui Xue,

Wenhu Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pan_2024_WACV, author = {Pan, Xichen and Qin, Pengda and Li, Yuhong and Xue, Hui and Chen, Wenhu}, title = {Synthesizing Coherent Story With Auto-Regressive Latent Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2920-2930} }
Text-to-Image Editing by Image Information Removal: Zhongping Zhang,

Jian Zheng,

Zhiyuan Fang,

Bryan A. Plummer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Zhongping and Zheng, Jian and Fang, Zhiyuan and Plummer, Bryan A.}, title = {Text-to-Image Editing by Image Information Removal}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5232-5241} }
Self-Annotated 3D Geometric Learning for Smeared Points Removal: Miaowei Wang,

Daniel Morris; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2024_WACV, author = {Wang, Miaowei and Morris, Daniel}, title = {Self-Annotated 3D Geometric Learning for Smeared Points Removal}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3494-3503} }
Deep Metric Learning With Chance Constraints: Yeti Z. Gürbüz,

Oğul Can,

Aydin Alatan; [pdf] [supp]
[bibtex]
@InProceedings{Gurbuz_2024_WACV, author = {G\"urb\"uz, Yeti Z. and Can, O\u{g}ul and Alatan, Aydin}, title = {Deep Metric Learning With Chance Constraints}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {543-553} }
CrashCar101: Procedural Generation for Damage Assessment: Jens Parslov,

Erik Riise,

Dim P. Papadopoulos; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Parslov_2024_WACV, author = {Parslov, Jens and Riise, Erik and Papadopoulos, Dim P.}, title = {CrashCar101: Procedural Generation for Damage Assessment}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4624-4634} }
Towards Domain-Aware Knowledge Distillation for Continual Model Generalization: Nikhil Reddy,

Mahsa Baktashmotlagh,

Chetan Arora; [pdf] [supp]
[bibtex]
@InProceedings{Reddy_2024_WACV, author = {Reddy, Nikhil and Baktashmotlagh, Mahsa and Arora, Chetan}, title = {Towards Domain-Aware Knowledge Distillation for Continual Model Generalization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {696-707} }
SCoRD: Subject-Conditional Relation Detection With Text-Augmented Data: Ziyan Yang,

Kushal Kafle,

Zhe Lin,

Scott Cohen,

Zhihong Ding,

Vicente Ordonez; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2024_WACV, author = {Yang, Ziyan and Kafle, Kushal and Lin, Zhe and Cohen, Scott and Ding, Zhihong and Ordonez, Vicente}, title = {SCoRD: Subject-Conditional Relation Detection With Text-Augmented Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5731-5741} }
THInImg: Cross-Modal Steganography for Presenting Talking Heads in Images: Lin Zhao,

Hongxuan Li,

Xuefei Ning,

Xinru Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2024_WACV, author = {Zhao, Lin and Li, Hongxuan and Ning, Xuefei and Jiang, Xinru}, title = {THInImg: Cross-Modal Steganography for Presenting Talking Heads in Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5553-5562} }
Causal Analysis for Robust Interpretability of Neural Networks: Ola Ahmad,

Nicolas Béreux,

Loïc Baret,

Vahid Hashemi,

Freddy Lecue; [pdf] [supp]
[bibtex]
@InProceedings{Ahmad_2024_WACV, author = {Ahmad, Ola and B\'ereux, Nicolas and Baret, Lo{\"\i}c and Hashemi, Vahid and Lecue, Freddy}, title = {Causal Analysis for Robust Interpretability of Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4685-4694} }
TransFed: A Way To Epitomize Focal Modulation Using Transformer-Based Federated Learning: Tajamul Ashraf,

Fuzayil Bin Afzal Mir,

Iqra Altaf Gillani; [pdf]
[bibtex]
@InProceedings{Ashraf_2024_WACV, author = {Ashraf, Tajamul and Bin Afzal Mir, Fuzayil and Gillani, Iqra Altaf}, title = {TransFed: A Way To Epitomize Focal Modulation Using Transformer-Based Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {554-563} }
Natural Light Can Also Be Dangerous: Traffic Sign Misinterpretation Under Adversarial Natural Light Attacks: Teng-Fang Hsiao,

Bo-Lun Huang,

Zi-Xiang Ni,

Yan-Ting Lin,

Hong-Han Shuai,

Yung-Hui Li,

Wen-Huang Cheng; [pdf] [supp]
[bibtex]
@InProceedings{Hsiao_2024_WACV, author = {Hsiao, Teng-Fang and Huang, Bo-Lun and Ni, Zi-Xiang and Lin, Yan-Ting and Shuai, Hong-Han and Li, Yung-Hui and Cheng, Wen-Huang}, title = {Natural Light Can Also Be Dangerous: Traffic Sign Misinterpretation Under Adversarial Natural Light Attacks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3915-3924} }
PAIR: Perception Aided Image Restoration for Natural Driving Conditions: Pranjay Shyam,

HyunJin Yoo; [pdf]
[bibtex]
@InProceedings{Shyam_2024_WACV, author = {Shyam, Pranjay and Yoo, HyunJin}, title = {PAIR: Perception Aided Image Restoration for Natural Driving Conditions}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7459-7470} }
RecycleNet: Latent Feature Recycling Leads to Iterative Decision Refinement: Gregor Köhler,

Tassilo Wald,

Constantin Ulrich,

David Zimmerer,

Paul F. Jäger,

Jörg K.H. Franke,

Simon Kohl,

Fabian Isensee,

Klaus H. Maier-Hein; [pdf]
[bibtex]
@InProceedings{Kohler_2024_WACV, author = {K\"ohler, Gregor and Wald, Tassilo and Ulrich, Constantin and Zimmerer, David and J\"ager, Paul F. and Franke, J\"org K.H. and Kohl, Simon and Isensee, Fabian and Maier-Hein, Klaus H.}, title = {RecycleNet: Latent Feature Recycling Leads to Iterative Decision Refinement}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {810-818} }
CamoFocus: Enhancing Camouflage Object Detection With Split-Feature Focal Modulation and Context Refinement: Abbas Khan,

Mustaqeem Khan,

Wail Gueaieb,

Abdulmotaleb El Saddik,

Giulia De Masi,

Fakhri Karray; [pdf]
[bibtex]
@InProceedings{Khan_2024_WACV, author = {Khan, Abbas and Khan, Mustaqeem and Gueaieb, Wail and El Saddik, Abdulmotaleb and De Masi, Giulia and Karray, Fakhri}, title = {CamoFocus: Enhancing Camouflage Object Detection With Split-Feature Focal Modulation and Context Refinement}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1434-1443} }
Scene Text Image Super-Resolution Based on Text-Conditional Diffusion Models: Chihiro Noguchi,

Shun Fukuda,

Masao Yamanaka; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Noguchi_2024_WACV, author = {Noguchi, Chihiro and Fukuda, Shun and Yamanaka, Masao}, title = {Scene Text Image Super-Resolution Based on Text-Conditional Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1485-1495} }
Domain Adaptive 3D Shape Retrieval From Monocular Images: Harsh Pal,

Ritwik Khandelwal,

Shivam Pande,

Biplab Banerjee,

Srikrishna Karanam; [pdf]
[bibtex]
@InProceedings{Pal_2024_WACV, author = {Pal, Harsh and Khandelwal, Ritwik and Pande, Shivam and Banerjee, Biplab and Karanam, Srikrishna}, title = {Domain Adaptive 3D Shape Retrieval From Monocular Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3192-3201} }
Learning Quality Labels for Robust Image Classification: Xiaosong Wang,

Ziyue Xu,

Dong Yang,

Leo Tam,

Holger Roth,

Daguang Xu; [pdf]
[bibtex]
@InProceedings{Wang_2024_WACV, author = {Wang, Xiaosong and Xu, Ziyue and Yang, Dong and Tam, Leo and Roth, Holger and Xu, Daguang}, title = {Learning Quality Labels for Robust Image Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1103-1112} }
LibreFace: An Open-Source Toolkit for Deep Facial Expression Analysis: Di Chang,

Yufeng Yin,

Zongjian Li,

Minh Tran,

Mohammad Soleymani; [pdf] [arXiv]
[bibtex]
@InProceedings{Chang_2024_WACV, author = {Chang, Di and Yin, Yufeng and Li, Zongjian and Tran, Minh and Soleymani, Mohammad}, title = {LibreFace: An Open-Source Toolkit for Deep Facial Expression Analysis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8205-8215} }
SCUNet++: Swin-UNet and CNN Bottleneck Hybrid Architecture With Multi-Fusion Dense Skip Connection for Pulmonary Embolism CT Image Segmentation: Yifei Chen,

Binfeng Zou,

Zhaoxin Guo,

Yiyu Huang,

Yifan Huang,

Feiwei Qin,

Qinhai Li,

Changmiao Wang; [pdf]
[bibtex]
@InProceedings{Chen_2024_WACV, author = {Chen, Yifei and Zou, Binfeng and Guo, Zhaoxin and Huang, Yiyu and Huang, Yifan and Qin, Feiwei and Li, Qinhai and Wang, Changmiao}, title = {SCUNet++: Swin-UNet and CNN Bottleneck Hybrid Architecture With Multi-Fusion Dense Skip Connection for Pulmonary Embolism CT Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7759-7767} }
Attention Modules Improve Image-Level Anomaly Detection for Industrial Inspection: A DifferNet Case Study: André Luiz Vieira e Silva,

Francisco Simões,

Danny Kowerko,

Tobias Schlosser,

Felipe Battisti,

Veronica Teichrieb; [pdf]
[bibtex]
@InProceedings{e_Silva_2024_WACV, author = {e Silva, Andr\'e Luiz Vieira and Sim\~oes, Francisco and Kowerko, Danny and Schlosser, Tobias and Battisti, Felipe and Teichrieb, Veronica}, title = {Attention Modules Improve Image-Level Anomaly Detection for Industrial Inspection: A DifferNet Case Study}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8246-8255} }
Indoor Visual Localization Using Point and Line Correspondences in Dense Colored Point Cloud: Yuya Matsumoto,

Gaku Nakano,

Kazumine Ogura; [pdf]
[bibtex]
@InProceedings{Matsumoto_2024_WACV, author = {Matsumoto, Yuya and Nakano, Gaku and Ogura, Kazumine}, title = {Indoor Visual Localization Using Point and Line Correspondences in Dense Colored Point Cloud}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3616-3625} }
RGB-D Mapping and Tracking in a Plenoxel Radiance Field: Andreas L. Teigen,

Yeonsoo Park,

Annette Stahl,

Rudolf Mester; [pdf] [supp]
[bibtex]
@InProceedings{Teigen_2024_WACV, author = {Teigen, Andreas L. and Park, Yeonsoo and Stahl, Annette and Mester, Rudolf}, title = {RGB-D Mapping and Tracking in a Plenoxel Radiance Field}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3342-3351} }
An Empirical Investigation Into Benchmarking Model Multiplicity for Trustworthy Machine Learning: A Case Study on Image Classification: Prakhar Ganesh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ganesh_2024_WACV, author = {Ganesh, Prakhar}, title = {An Empirical Investigation Into Benchmarking Model Multiplicity for Trustworthy Machine Learning: A Case Study on Image Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4488-4497} }
Pixel-Grounded Prototypical Part Networks: Zachariah Carmichael,

Suhas Lohit,

Anoop Cherian,

Michael J. Jones,

Walter J. Scheirer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Carmichael_2024_WACV, author = {Carmichael, Zachariah and Lohit, Suhas and Cherian, Anoop and Jones, Michael J. and Scheirer, Walter J.}, title = {Pixel-Grounded Prototypical Part Networks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4768-4779} }
LatentDR: Improving Model Generalization Through Sample-Aware Latent Degradation and Restoration: Ran Liu,

Sahil Khose,

Jingyun Xiao,

Lakshmi Sathidevi,

Keerthan Ramnath,

Zsolt Kira,

Eva L. Dyer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_WACV, author = {Liu, Ran and Khose, Sahil and Xiao, Jingyun and Sathidevi, Lakshmi and Ramnath, Keerthan and Kira, Zsolt and Dyer, Eva L.}, title = {LatentDR: Improving Model Generalization Through Sample-Aware Latent Degradation and Restoration}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2669-2679} }
G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation: Md Mostafijur Rahman,

Radu Marculescu; [pdf] [supp]
[bibtex]
@InProceedings{Rahman_2024_WACV, author = {Rahman, Md Mostafijur and Marculescu, Radu}, title = {G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7728-7737} }
TAMPAR: Visual Tampering Detection for Parcel Logistics in Postal Supply Chains: Alexander Naumann,

Felix Hertlein,

Laura Dörr,

Kai Furmans; [pdf]
[bibtex]
@InProceedings{Naumann_2024_WACV, author = {Naumann, Alexander and Hertlein, Felix and D\"orr, Laura and Furmans, Kai}, title = {TAMPAR: Visual Tampering Detection for Parcel Logistics in Postal Supply Chains}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8076-8086} }
PGVT: Pose-Guided Video Transformer for Fine-Grained Action Recognition: Haosong Zhang,

Mei Chee Leong,

Liyuan Li,

Weisi Lin; [pdf]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Haosong and Leong, Mei Chee and Li, Liyuan and Lin, Weisi}, title = {PGVT: Pose-Guided Video Transformer for Fine-Grained Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6645-6656} }
Multi-View Classification Using Hybrid Fusion and Mutual Distillation: Samuel Black,

Richard Souvenir; [pdf] [supp]
[bibtex]
@InProceedings{Black_2024_WACV, author = {Black, Samuel and Souvenir, Richard}, title = {Multi-View Classification Using Hybrid Fusion and Mutual Distillation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {270-280} }
Real-Time User-Guided Adaptive Colorization With Vision Transformer: Gwanghan Lee,

Saebyeol Shin,

Taeyoung Na,

Simon S. Woo; [pdf]
[bibtex]
@InProceedings{Lee_2024_WACV, author = {Lee, Gwanghan and Shin, Saebyeol and Na, Taeyoung and Woo, Simon S.}, title = {Real-Time User-Guided Adaptive Colorization With Vision Transformer}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {484-493} }
CAMOT: Camera Angle-Aware Multi-Object Tracking: Felix Limanta,

Kuniaki Uto,

Koichi Shinoda; [pdf] [supp]
[bibtex]
@InProceedings{Limanta_2024_WACV, author = {Limanta, Felix and Uto, Kuniaki and Shinoda, Koichi}, title = {CAMOT: Camera Angle-Aware Multi-Object Tracking}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6479-6488} }
Egocentric Action Recognition by Capturing Hand-Object Contact and Object State: Tsukasa Shiota,

Motohiro Takagi,

Kaori Kumagai,

Hitoshi Seshimo,

Yushi Aono; [pdf] [supp]
[bibtex]
@InProceedings{Shiota_2024_WACV, author = {Shiota, Tsukasa and Takagi, Motohiro and Kumagai, Kaori and Seshimo, Hitoshi and Aono, Yushi}, title = {Egocentric Action Recognition by Capturing Hand-Object Contact and Object State}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6541-6551} }
IndustReal: A Dataset for Procedure Step Recognition Handling Execution Errors in Egocentric Videos in an Industrial-Like Setting: Tim J. Schoonbeek,

Tim Houben,

Hans Onvlee,

Peter H.N. de With,

Fons van der Sommen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Schoonbeek_2024_WACV, author = {Schoonbeek, Tim J. and Houben, Tim and Onvlee, Hans and de With, Peter H.N. and van der Sommen, Fons}, title = {IndustReal: A Dataset for Procedure Step Recognition Handling Execution Errors in Egocentric Videos in an Industrial-Like Setting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4365-4374} }
FastCLIPstyler: Optimisation-Free Text-Based Image Style Transfer Using Style Representations: Ananda Padhmanabhan Suresh,

Sanjana Jain,

Pavit Noinongyao,

Ankush Ganguly,

Ukrit Watchareeruetai,

Aubin Samacoits; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Suresh_2024_WACV, author = {Suresh, Ananda Padhmanabhan and Jain, Sanjana and Noinongyao, Pavit and Ganguly, Ankush and Watchareeruetai, Ukrit and Samacoits, Aubin}, title = {FastCLIPstyler: Optimisation-Free Text-Based Image Style Transfer Using Style Representations}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7316-7325} }
Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation: Inkyu Shin,

Dahun Kim,

Qihang Yu,

Jun Xie,

Hong-Seok Kim,

Bradley Green,

In So Kweon,

Kuk-Jin Yoon,

Liang-Chieh Chen; [pdf] [supp]
[bibtex]
@InProceedings{Shin_2024_WACV, author = {Shin, Inkyu and Kim, Dahun and Yu, Qihang and Xie, Jun and Kim, Hong-Seok and Green, Bradley and Kweon, In So and Yoon, Kuk-Jin and Chen, Liang-Chieh}, title = {Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {229-239} }
Cross-Feature Contrastive Loss for Decentralized Deep Learning on Heterogeneous Data: Sai Aparna Aketi,

Kaushik Roy; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Aketi_2024_WACV, author = {Aketi, Sai Aparna and Roy, Kaushik}, title = {Cross-Feature Contrastive Loss for Decentralized Deep Learning on Heterogeneous Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {12-21} }
MOPA: Modular Object Navigation With PointGoal Agents: Sonia Raychaudhuri,

Tommaso Campari,

Unnat Jain,

Manolis Savva,

Angel X. Chang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Raychaudhuri_2024_WACV, author = {Raychaudhuri, Sonia and Campari, Tommaso and Jain, Unnat and Savva, Manolis and Chang, Angel X.}, title = {MOPA: Modular Object Navigation With PointGoal Agents}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5763-5773} }
The Paleographer's Eye ex machina: Using Computer Vision To Assist Humanists in Scribal Hand Identification: Samuel Grieggs,

C. E. M. Henderson,

Sebastian Sobecki,

Alexandra Gillespie,

Walter Scheirer; [pdf]
[bibtex]
@InProceedings{Grieggs_2024_WACV, author = {Grieggs, Samuel and Henderson, C. E. M. and Sobecki, Sebastian and Gillespie, Alexandra and Scheirer, Walter}, title = {The Paleographer's Eye ex machina: Using Computer Vision To Assist Humanists in Scribal Hand Identification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7177-7186} }
Learning To Recognize Occluded and Small Objects With Partial Inputs: Hasib Zunair,

A. Ben Hamza; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zunair_2024_WACV, author = {Zunair, Hasib and Ben Hamza, A.}, title = {Learning To Recognize Occluded and Small Objects With Partial Inputs}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {675-684} }
BALF: Simple and Efficient Blur Aware Local Feature Detector: Zhenjun Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2024_WACV, author = {Zhao, Zhenjun}, title = {BALF: Simple and Efficient Blur Aware Local Feature Detector}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3362-3372} }
RS2G: Data-Driven Scene-Graph Extraction and Embedding for Robust Autonomous Perception and Scenario Understanding: Junyao Wang,

Arnav Vaibhav Malawade,

Junhong Zhou,

Shih-Yuan Yu,

Mohammad Abdullah Al Faruque; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_WACV, author = {Wang, Junyao and Malawade, Arnav Vaibhav and Zhou, Junhong and Yu, Shih-Yuan and Al Faruque, Mohammad Abdullah}, title = {RS2G: Data-Driven Scene-Graph Extraction and Embedding for Robust Autonomous Perception and Scenario Understanding}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7493-7502} }
Leveraging the Power of Data Augmentation for Transformer-Based Tracking: Jie Zhao,

Johan Edstedt,

Michael Felsberg,

Dong Wang,

Huchuan Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2024_WACV, author = {Zhao, Jie and Edstedt, Johan and Felsberg, Michael and Wang, Dong and Lu, Huchuan}, title = {Leveraging the Power of Data Augmentation for Transformer-Based Tracking}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6469-6478} }
Med-DANet V2: A Flexible Dynamic Architecture for Efficient Medical Volumetric Segmentation: Haoran Shen,

Yifu Zhang,

Wenxuan Wang,

Chen Chen,

Jing Liu,

Shanshan Song,

Jiangyun Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shen_2024_WACV, author = {Shen, Haoran and Zhang, Yifu and Wang, Wenxuan and Chen, Chen and Liu, Jing and Song, Shanshan and Li, Jiangyun}, title = {Med-DANet V2: A Flexible Dynamic Architecture for Efficient Medical Volumetric Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7871-7881} }
Partial Binarization of Neural Networks for Budget-Aware Efficient Learning: Udbhav Bamba,

Neeraj Anand,

Saksham Aggarwal,

Dilip K. Prasad,

Deepak K. Gupta; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bamba_2024_WACV, author = {Bamba, Udbhav and Anand, Neeraj and Aggarwal, Saksham and Prasad, Dilip K. and Gupta, Deepak K.}, title = {Partial Binarization of Neural Networks for Budget-Aware Efficient Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2336-2345} }
Improving the Fairness of the Min-Max Game in GANs Training: Zhaoyu Zhang,

Yang Hua,

Hui Wang,

Seán McLoone; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Zhaoyu and Hua, Yang and Wang, Hui and McLoone, Se\'an}, title = {Improving the Fairness of the Min-Max Game in GANs Training}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2910-2919} }
When 3D Bounding-Box Meets SAM: Point Cloud Instance Segmentation With Weak-and-Noisy Supervision: Qingtao Yu,

Heming Du,

Chen Liu,

Xin Yu; [pdf] [arXiv]
[bibtex]
@InProceedings{Yu_2024_WACV, author = {Yu, Qingtao and Du, Heming and Liu, Chen and Yu, Xin}, title = {When 3D Bounding-Box Meets SAM: Point Cloud Instance Segmentation With Weak-and-Noisy Supervision}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3719-3728} }
Domain Aligned CLIP for Few-Shot Classification: Muhammad Waleed Gondal,

Jochen Gast,

Inigo Alonso Ruiz,

Richard Droste,

Tommaso Macri,

Suren Kumar,

Luitpold Staudigl; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gondal_2024_WACV, author = {Gondal, Muhammad Waleed and Gast, Jochen and Ruiz, Inigo Alonso and Droste, Richard and Macri, Tommaso and Kumar, Suren and Staudigl, Luitpold}, title = {Domain Aligned CLIP for Few-Shot Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5721-5730} }
Beyond Document Page Classification: Design, Datasets, and Challenges: Jordy Van Landeghem,

Sanket Biswas,

Matthew Blaschko,

Marie-Francine Moens; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Van_Landeghem_2024_WACV, author = {Van Landeghem, Jordy and Biswas, Sanket and Blaschko, Matthew and Moens, Marie-Francine}, title = {Beyond Document Page Classification: Design, Datasets, and Challenges}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2962-2972} }
Towards More Realistic Membership Inference Attacks on Large Diffusion Models: Jan Dubiński,

Antoni Kowalczuk,

Stanisław Pawlak,

Przemyslaw Rokita,

Tomasz Trzciński,

Paweł Morawiecki; [pdf] [supp]
[bibtex]
@InProceedings{Dubinski_2024_WACV, author = {Dubi\'nski, Jan and Kowalczuk, Antoni and Pawlak, Stanis{\l}aw and Rokita, Przemyslaw and Trzci\'nski, Tomasz and Morawiecki, Pawe{\l}}, title = {Towards More Realistic Membership Inference Attacks on Large Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4860-4869} }
Slice and Conquer: A Planar-to-3D Framework for Efficient Interactive Segmentation of Volumetric Images: Wonwoo Cho,

Dongmin Choi,

Hyesu Lim,

Jinho Choi,

Saemee Choi,

Hyun-seok Min,

Sungbin Lim,

Jaegul Choo; [pdf]
[bibtex]
@InProceedings{Cho_2024_WACV, author = {Cho, Wonwoo and Choi, Dongmin and Lim, Hyesu and Choi, Jinho and Choi, Saemee and Min, Hyun-seok and Lim, Sungbin and Choo, Jaegul}, title = {Slice and Conquer: A Planar-to-3D Framework for Efficient Interactive Segmentation of Volumetric Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7614-7623} }
Mitigate Domain Shift by Primary-Auxiliary Objectives Association for Generalizing Person ReID: Qilei Li,

Shaogang Gong; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2024_WACV, author = {Li, Qilei and Gong, Shaogang}, title = {Mitigate Domain Shift by Primary-Auxiliary Objectives Association for Generalizing Person ReID}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {394-403} }
MonoProb: Self-Supervised Monocular Depth Estimation With Interpretable Uncertainty: Rémi Marsal,

Florian Chabot,

Angélique Loesch,

William Grolleau,

Hichem Sahbi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Marsal_2024_WACV, author = {Marsal, R\'emi and Chabot, Florian and Loesch, Ang\'elique and Grolleau, William and Sahbi, Hichem}, title = {MonoProb: Self-Supervised Monocular Depth Estimation With Interpretable Uncertainty}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3637-3646} }
LP-OVOD: Open-Vocabulary Object Detection by Linear Probing: Chau Pham,

Truong Vu,

Khoi Nguyen; [pdf]
[bibtex]
@InProceedings{Pham_2024_WACV, author = {Pham, Chau and Vu, Truong and Nguyen, Khoi}, title = {LP-OVOD: Open-Vocabulary Object Detection by Linear Probing}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {779-788} }
Beyond Active Learning: Leveraging the Full Potential of Human Interaction via Auto-Labeling, Human Correction, and Human Verification: Nathan Beck,

Krishnateja Killamsetty,

Suraj Kothawade,

Rishabh Iyer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Beck_2024_WACV, author = {Beck, Nathan and Killamsetty, Krishnateja and Kothawade, Suraj and Iyer, Rishabh}, title = {Beyond Active Learning: Leveraging the Full Potential of Human Interaction via Auto-Labeling, Human Correction, and Human Verification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2881-2889} }
ARNIQA: Learning Distortion Manifold for Image Quality Assessment: Lorenzo Agnolucci,

Leonardo Galteri,

Marco Bertini,

Alberto Del Bimbo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Agnolucci_2024_WACV, author = {Agnolucci, Lorenzo and Galteri, Leonardo and Bertini, Marco and Del Bimbo, Alberto}, title = {ARNIQA: Learning Distortion Manifold for Image Quality Assessment}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {189-198} }
CVTHead: One-Shot Controllable Head Avatar With Vertex-Feature Transformer: Haoyu Ma,

Tong Zhang,

Shanlin Sun,

Xiangyi Yan,

Kun Han,

Xiaohui Xie; [pdf] [arXiv]
[bibtex]
@InProceedings{Ma_2024_WACV, author = {Ma, Haoyu and Zhang, Tong and Sun, Shanlin and Yan, Xiangyi and Han, Kun and Xie, Xiaohui}, title = {CVTHead: One-Shot Controllable Head Avatar With Vertex-Feature Transformer}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6131-6141} }
FIRe: Fast Inverse Rendering Using Directional and Signed Distance Functions: Tarun Yenamandra,

Ayush Tewari,

Nan Yang,

Florian Bernard,

Christian Theobalt,

Daniel Cremers; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yenamandra_2024_WACV, author = {Yenamandra, Tarun and Tewari, Ayush and Yang, Nan and Bernard, Florian and Theobalt, Christian and Cremers, Daniel}, title = {FIRe: Fast Inverse Rendering Using Directional and Signed Distance Functions}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3077-3087} }
Ego2HandsPose: A Dataset for Egocentric Two-Hand 3D Global Pose Estimation: Fanqing Lin,

Tony Martinez; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2024_WACV, author = {Lin, Fanqing and Martinez, Tony}, title = {Ego2HandsPose: A Dataset for Egocentric Two-Hand 3D Global Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4375-4383} }
Improving Vision-and-Language Reasoning via Spatial Relations Modeling: Cheng Yang,

Rui Xu,

Ye Guo,

Peixiang Huang,

Yiru Chen,

Wenkui Ding,

Zhongyuan Wang,

Hong Zhou; [pdf] [arXiv]
[bibtex]
@InProceedings{Yang_2024_WACV, author = {Yang, Cheng and Xu, Rui and Guo, Ye and Huang, Peixiang and Chen, Yiru and Ding, Wenkui and Wang, Zhongyuan and Zhou, Hong}, title = {Improving Vision-and-Language Reasoning via Spatial Relations Modeling}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {769-778} }
WATCH: Wide-Area Terrestrial Change Hypercube: Connor Greenwell,

Jon Crall,

Matthew Purri,

Kristin Dana,

Nathan Jacobs,

Armin Hadzic,

Scott Workman,

Matt Leotta; [pdf]
[bibtex]
@InProceedings{Greenwell_2024_WACV, author = {Greenwell, Connor and Crall, Jon and Purri, Matthew and Dana, Kristin and Jacobs, Nathan and Hadzic, Armin and Workman, Scott and Leotta, Matt}, title = {WATCH: Wide-Area Terrestrial Change Hypercube}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8277-8286} }
Detecting Content Segments From Online Sports Streaming Events: Challenges and Solutions: Zongyi Liu,

Yarong Feng,

Shunyan Luo,

Yuan Ling,

Shujing Dong,

Shuyi Wang; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2024_WACV, author = {Liu, Zongyi and Feng, Yarong and Luo, Shunyan and Ling, Yuan and Dong, Shujing and Wang, Shuyi}, title = {Detecting Content Segments From Online Sports Streaming Events: Challenges and Solutions}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6414-6425} }
Vikriti-ID: A Novel Approach for Real Looking Fingerprint Data-Set Generation: Rishabh Shukla,

Aditya Sinha,

Vansh Singh,

Harkeerat Kaur; [pdf]
[bibtex]
@InProceedings{Shukla_2024_WACV, author = {Shukla, Rishabh and Sinha, Aditya and Singh, Vansh and Kaur, Harkeerat}, title = {Vikriti-ID: A Novel Approach for Real Looking Fingerprint Data-Set Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6395-6403} }
PETIT-GAN: Physically Enhanced Thermal Image-Translating Generative Adversarial Network: Omri Berman,

Navot Oz,

David Mendlovic,

Nir Sochen,

Yafit Cohen,

Iftach Klapp; [pdf] [supp]
[bibtex]
@InProceedings{Berman_2024_WACV, author = {Berman, Omri and Oz, Navot and Mendlovic, David and Sochen, Nir and Cohen, Yafit and Klapp, Iftach}, title = {PETIT-GAN: Physically Enhanced Thermal Image-Translating Generative Adversarial Network}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1618-1627} }
Design Choices for Enhancing Noisy Student Self-Training: Aswathnarayan Radhakrishnan,

Jim Davis,

Zachary Rabin,

Benjamin Lewis,

Matthew Scherreik,

Roman Ilin; [pdf]
[bibtex]
@InProceedings{Radhakrishnan_2024_WACV, author = {Radhakrishnan, Aswathnarayan and Davis, Jim and Rabin, Zachary and Lewis, Benjamin and Scherreik, Matthew and Ilin, Roman}, title = {Design Choices for Enhancing Noisy Student Self-Training}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1926-1935} }
ArcGeo: Localizing Limited Field-of-View Images Using Cross-View Matching: Maxim Shugaev,

Ilya Semenov,

Kyle Ashley,

Michael Klaczynski,

Naresh Cuntoor,

Mun Wai Lee,

Nathan Jacobs; [pdf] [supp]
[bibtex]
@InProceedings{Shugaev_2024_WACV, author = {Shugaev, Maxim and Semenov, Ilya and Ashley, Kyle and Klaczynski, Michael and Cuntoor, Naresh and Lee, Mun Wai and Jacobs, Nathan}, title = {ArcGeo: Localizing Limited Field-of-View Images Using Cross-View Matching}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {209-218} }
Understanding Hyperbolic Metric Learning Through Hard Negative Sampling: Yun Yue,

Fangzhou Lin,

Guanyi Mou,

Ziming Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Yue_2024_WACV, author = {Yue, Yun and Lin, Fangzhou and Mou, Guanyi and Zhang, Ziming}, title = {Understanding Hyperbolic Metric Learning Through Hard Negative Sampling}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1891-1903} }
FIRE: Food Image to REcipe Generation: Prateek Chhikara,

Dhiraj Chaurasia,

Yifan Jiang,

Omkar Masur,

Filip Ilievski; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chhikara_2024_WACV, author = {Chhikara, Prateek and Chaurasia, Dhiraj and Jiang, Yifan and Masur, Omkar and Ilievski, Filip}, title = {FIRE: Food Image to REcipe Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8184-8194} }
DiffCLIP: Leveraging Stable Diffusion for Language Grounded 3D Classification: Sitian Shen,

Zilin Zhu,

Linqian Fan,

Harry Zhang,

Xinxiao Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shen_2024_WACV, author = {Shen, Sitian and Zhu, Zilin and Fan, Linqian and Zhang, Harry and Wu, Xinxiao}, title = {DiffCLIP: Leveraging Stable Diffusion for Language Grounded 3D Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3596-3605} }
A One-Shot Learning Approach To Document Layout Segmentation of Ancient Arabic Manuscripts: Axel De Nardin,

Silvia Zottin,

Claudio Piciarelli,

Emanuela Colombi,

Gian Luca Foresti; [pdf]
[bibtex]
@InProceedings{De_Nardin_2024_WACV, author = {De Nardin, Axel and Zottin, Silvia and Piciarelli, Claudio and Colombi, Emanuela and Foresti, Gian Luca}, title = {A One-Shot Learning Approach To Document Layout Segmentation of Ancient Arabic Manuscripts}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8127-8136} }
Do We Still Need Non-Maximum Suppression? Accurate Confidence Estimates and Implicit Duplication Modeling With IoU-Aware Calibration: Johannes Gilg,

Torben Teepe,

Fabian Herzog,

Philipp Wolters,

Gerhard Rigoll; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gilg_2024_WACV, author = {Gilg, Johannes and Teepe, Torben and Herzog, Fabian and Wolters, Philipp and Rigoll, Gerhard}, title = {Do We Still Need Non-Maximum Suppression? Accurate Confidence Estimates and Implicit Duplication Modeling With IoU-Aware Calibration}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4850-4859} }
On the Importance of Large Objects in CNN Based Object Detection Algorithms: Ahmed Ben Saad,

Gabriele Facciolo,

Axel Davy; [pdf] [arXiv]
[bibtex]
@InProceedings{Ben_Saad_2024_WACV, author = {Ben Saad, Ahmed and Facciolo, Gabriele and Davy, Axel}, title = {On the Importance of Large Objects in CNN Based Object Detection Algorithms}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {533-542} }
Learning Intra-Class Multimodal Distributions With Orthonormal Matrices: Jumpei Goto,

Yohei Nakata,

Kiyofumi Abe,

Yasunori Ishii,

Takayoshi Yamashita; [pdf] [supp]
[bibtex]
@InProceedings{Goto_2024_WACV, author = {Goto, Jumpei and Nakata, Yohei and Abe, Kiyofumi and Ishii, Yasunori and Yamashita, Takayoshi}, title = {Learning Intra-Class Multimodal Distributions With Orthonormal Matrices}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1870-1879} }
Assessing Neural Network Robustness via Adversarial Pivotal Tuning: Peter Ebert Christensen,

Vésteinn Snæbjarnarson,

Andrea Dittadi,

Serge Belongie,

Sagie Benaim; [pdf]
[bibtex]
@InProceedings{Christensen_2024_WACV, author = {Christensen, Peter Ebert and Sn{\ae}bjarnarson, V\'esteinn and Dittadi, Andrea and Belongie, Serge and Benaim, Sagie}, title = {Assessing Neural Network Robustness via Adversarial Pivotal Tuning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2952-2961} }
Opinion Unaware Image Quality Assessment via Adversarial Convolutional Variational Autoencoder: Ankit Shukla,

Avinash Upadhyay,

Swati Bhugra,

Manoj Sharma; [pdf]
[bibtex]
@InProceedings{Shukla_2024_WACV, author = {Shukla, Ankit and Upadhyay, Avinash and Bhugra, Swati and Sharma, Manoj}, title = {Opinion Unaware Image Quality Assessment via Adversarial Convolutional Variational Autoencoder}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2153-2163} }
A Geometry Loss Combination for 3D Human Pose Estimation: Ai Matsune,

Shichen Hu,

Guangquan Li,

Sihan Wen,

Xiantan Zhu,

Zhiming Tan; [pdf]
[bibtex]
@InProceedings{Matsune_2024_WACV, author = {Matsune, Ai and Hu, Shichen and Li, Guangquan and Wen, Sihan and Zhu, Xiantan and Tan, Zhiming}, title = {A Geometry Loss Combination for 3D Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3272-3281} }
Few-Shot Generative Model for Skeleton-Based Human Action Synthesis Using Cross-Domain Adversarial Learning: Kenichiro Fukushi,

Yoshitaka Nozaki,

Kosuke Nishihara,

Kentaro Nakahara; [pdf]
[bibtex]
@InProceedings{Fukushi_2024_WACV, author = {Fukushi, Kenichiro and Nozaki, Yoshitaka and Nishihara, Kosuke and Nakahara, Kentaro}, title = {Few-Shot Generative Model for Skeleton-Based Human Action Synthesis Using Cross-Domain Adversarial Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3946-3955} }
Linking Convolutional Kernel Size to Generalization Bias in Face Analysis CNNs: Hao Liang,

Josue Ortega Caro,

Vikram Maheshri,

Ankit B. Patel,

Guha Balakrishnan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liang_2024_WACV, author = {Liang, Hao and Caro, Josue Ortega and Maheshri, Vikram and Patel, Ankit B. and Balakrishnan, Guha}, title = {Linking Convolutional Kernel Size to Generalization Bias in Face Analysis CNNs}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4705-4715} }
Cross-Attention Between Satellite and Ground Views for Enhanced Fine-Grained Robot Geo-Localization: Dong Yuan,

Frederic Maire,

Feras Dayoub; [pdf] [supp]
[bibtex]
@InProceedings{Yuan_2024_WACV, author = {Yuan, Dong and Maire, Frederic and Dayoub, Feras}, title = {Cross-Attention Between Satellite and Ground Views for Enhanced Fine-Grained Robot Geo-Localization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1249-1256} }
StyleGAN-Fusion: Diffusion Guided Domain Adaptation of Image Generators: Kunpeng Song,

Ligong Han,

Bingchen Liu,

Dimitris Metaxas,

Ahmed Elgammal; [pdf] [supp]
[bibtex]
@InProceedings{Song_2024_WACV, author = {Song, Kunpeng and Han, Ligong and Liu, Bingchen and Metaxas, Dimitris and Elgammal, Ahmed}, title = {StyleGAN-Fusion: Diffusion Guided Domain Adaptation of Image Generators}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5453-5463} }
TSP-Transformer: Task-Specific Prompts Boosted Transformer for Holistic Scene Understanding: Shuo Wang,

Jing Li,

Zibo Zhao,

Dongze Lian,

Binbin Huang,

Xiaomei Wang,

Zhengxin Li,

Shenghua Gao; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2024_WACV, author = {Wang, Shuo and Li, Jing and Zhao, Zibo and Lian, Dongze and Huang, Binbin and Wang, Xiaomei and Li, Zhengxin and Gao, Shenghua}, title = {TSP-Transformer: Task-Specific Prompts Boosted Transformer for Holistic Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {925-934} }
Late to the Party? On-Demand Unlabeled Personalized Federated Learning: Ohad Amosy,

Gal Eyal,

Gal Chechik; [pdf] [supp]
[bibtex]
@InProceedings{Amosy_2024_WACV, author = {Amosy, Ohad and Eyal, Gal and Chechik, Gal}, title = {Late to the Party? On-Demand Unlabeled Personalized Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2184-2193} }
EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies: Kilian Batzner,

Lars Heckler,

Rebecca König; [pdf] [supp]
[bibtex]
@InProceedings{Batzner_2024_WACV, author = {Batzner, Kilian and Heckler, Lars and K\"onig, Rebecca}, title = {EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {128-138} }
Implicit Neural Representation for Change Detection: Peter Naylor,

Diego Di Carlo,

Arianna Traviglia,

Makoto Yamada,

Marco Fiorucci; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Naylor_2024_WACV, author = {Naylor, Peter and Di Carlo, Diego and Traviglia, Arianna and Yamada, Makoto and Fiorucci, Marco}, title = {Implicit Neural Representation for Change Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {935-945} }
Maximum Knowledge Orthogonality Reconstruction With Gradients in Federated Learning: Feng Wang,

Senem Velipasalar,

M. Cenk Gursoy; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_WACV, author = {Wang, Feng and Velipasalar, Senem and Gursoy, M. Cenk}, title = {Maximum Knowledge Orthogonality Reconstruction With Gradients in Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3884-3893} }
ENIGMA-51: Towards a Fine-Grained Understanding of Human Behavior in Industrial Scenarios: Francesco Ragusa,

Rosario Leonardi,

Michele Mazzamuto,

Claudia Bonanno,

Rosario Scavo,

Antonino Furnari,

Giovanni Maria Farinella; [pdf] [supp]
[bibtex]
@InProceedings{Ragusa_2024_WACV, author = {Ragusa, Francesco and Leonardi, Rosario and Mazzamuto, Michele and Bonanno, Claudia and Scavo, Rosario and Furnari, Antonino and Farinella, Giovanni Maria}, title = {ENIGMA-51: Towards a Fine-Grained Understanding of Human Behavior in Industrial Scenarios}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4549-4559} }
HELA-VFA: A Hellinger Distance-Attention-Based Feature Aggregation Network for Few-Shot Classification: Gao Yu Lee,

Tanmoy Dam,

Daniel Puiu Poenar,

Vu N. Duong,

Md Meftahul Ferdaus; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2024_WACV, author = {Lee, Gao Yu and Dam, Tanmoy and Poenar, Daniel Puiu and Duong, Vu N. and Ferdaus, Md Meftahul}, title = {HELA-VFA: A Hellinger Distance-Attention-Based Feature Aggregation Network for Few-Shot Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2173-2183} }
ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenes: Ahmed Abdelreheem,

Kyle Olszewski,

Hsin-Ying Lee,

Peter Wonka,

Panos Achlioptas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Abdelreheem_2024_WACV, author = {Abdelreheem, Ahmed and Olszewski, Kyle and Lee, Hsin-Ying and Wonka, Peter and Achlioptas, Panos}, title = {ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenes}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3524-3534} }
A Closer Look at Robustness of Vision Transformers to Backdoor Attacks: Akshayvarun Subramanya,

Soroush Abbasi Koohpayegani,

Aniruddha Saha,

Ajinkya Tejankar,

Hamed Pirsiavash; [pdf] [supp]
[bibtex]
@InProceedings{Subramanya_2024_WACV, author = {Subramanya, Akshayvarun and Koohpayegani, Soroush Abbasi and Saha, Aniruddha and Tejankar, Ajinkya and Pirsiavash, Hamed}, title = {A Closer Look at Robustness of Vision Transformers to Backdoor Attacks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3874-3883} }
Differentiable JPEG: The Devil Is in the Details: Christoph Reich,

Biplob Debnath,

Deep Patel,

Srimat Chakradhar; [pdf] [arXiv]
[bibtex]
@InProceedings{Reich_2024_WACV, author = {Reich, Christoph and Debnath, Biplob and Patel, Deep and Chakradhar, Srimat}, title = {Differentiable JPEG: The Devil Is in the Details}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4126-4135} }
CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Free: Monika Wysoczańska,

Michaël Ramamonjisoa,

Tomasz Trzciński,

Oriane Siméoni; [pdf] [supp]
[bibtex]
@InProceedings{Wysoczanska_2024_WACV, author = {Wysocza\'nska, Monika and Ramamonjisoa, Micha\"el and Trzci\'nski, Tomasz and Sim\'eoni, Oriane}, title = {CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Free}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1403-1413} }
Dual Domain Diffusion Guidance for 3D CBCT Metal Artifact Reduction: Yongjin Choi,

Doeyoung Kwon,

Seung Jun Baek; [pdf]
[bibtex]
@InProceedings{Choi_2024_WACV, author = {Choi, Yongjin and Kwon, Doeyoung and Baek, Seung Jun}, title = {Dual Domain Diffusion Guidance for 3D CBCT Metal Artifact Reduction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7965-7974} }
Joint 3D Shape and Motion Estimation From Rolling Shutter Light-Field Images: Hermès McGriff,

Renato Martins,

Nicolas Andreff,

Cédric Demonceaux; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{McGriff_2024_WACV, author = {McGriff, Herm\`es and Martins, Renato and Andreff, Nicolas and Demonceaux, C\'edric}, title = {Joint 3D Shape and Motion Estimation From Rolling Shutter Light-Field Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3699-3708} }
ConeQuest: A Benchmark for Cone Segmentation on Mars: Mirali Purohit,

Jacob Adler,

Hannah Kerner; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Purohit_2024_WACV, author = {Purohit, Mirali and Adler, Jacob and Kerner, Hannah}, title = {ConeQuest: A Benchmark for Cone Segmentation on Mars}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6026-6035} }
A Multimodal Benchmark and Improved Architecture for Zero Shot Learning: Keval Doshi,

Amanmeet Garg,

Burak Uzkent,

Xiaolong Wang,

Mohamed Omar; [pdf] [supp]
[bibtex]
@InProceedings{Doshi_2024_WACV, author = {Doshi, Keval and Garg, Amanmeet and Uzkent, Burak and Wang, Xiaolong and Omar, Mohamed}, title = {A Multimodal Benchmark and Improved Architecture for Zero Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2021-2030} }
PlantPlotGAN: A Physics-Informed Generative Adversarial Network for Plant Disease Prediction: Felipe A. Lopes,

Vasit Sagan,

Flavio Esposito; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lopes_2024_WACV, author = {Lopes, Felipe A. and Sagan, Vasit and Esposito, Flavio}, title = {PlantPlotGAN: A Physics-Informed Generative Adversarial Network for Plant Disease Prediction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7066-7075} }
Common Diffusion Noise Schedules and Sample Steps Are Flawed: Shanchuan Lin,

Bingchen Liu,

Jiashi Li,

Xiao Yang; [pdf] [arXiv]
[bibtex]
@InProceedings{Lin_2024_WACV, author = {Lin, Shanchuan and Liu, Bingchen and Li, Jiashi and Yang, Xiao}, title = {Common Diffusion Noise Schedules and Sample Steps Are Flawed}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5404-5411} }
Efficient Expansion and Gradient Based Task Inference for Replay Free Incremental Learning: Soumya Roy,

Vinay Verma,

Deepak Gupta; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Roy_2024_WACV, author = {Roy, Soumya and Verma, Vinay and Gupta, Deepak}, title = {Efficient Expansion and Gradient Based Task Inference for Replay Free Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1165-1175} }
PolyMaX: General Dense Prediction With Mask Transformer: Xuan Yang,

Liangzhe Yuan,

Kimberly Wilber,

Astuti Sharma,

Xiuye Gu,

Siyuan Qiao,

Stephanie Debats,

Huisheng Wang,

Hartwig Adam,

Mikhail Sirotenko,

Liang-Chieh Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2024_WACV, author = {Yang, Xuan and Yuan, Liangzhe and Wilber, Kimberly and Sharma, Astuti and Gu, Xiuye and Qiao, Siyuan and Debats, Stephanie and Wang, Huisheng and Adam, Hartwig and Sirotenko, Mikhail and Chen, Liang-Chieh}, title = {PolyMaX: General Dense Prediction With Mask Transformer}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1050-1061} }
Approximating Intersections and Differences Between Linear Statistical Shape Models Using Markov Chain Monte Carlo: Maximilian Weiherer,

Finn Klein,

Bernhard Egger; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Weiherer_2024_WACV, author = {Weiherer, Maximilian and Klein, Finn and Egger, Bernhard}, title = {Approximating Intersections and Differences Between Linear Statistical Shape Models Using Markov Chain Monte Carlo}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6364-6373} }
Few-Shot Shape Recognition by Learning Deep Shape-Aware Features: Wenlong Shi,

Changsheng Lu,

Ming Shao,

Yinjie Zhang,

Siyu Xia,

Piotr Koniusz; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shi_2024_WACV, author = {Shi, Wenlong and Lu, Changsheng and Shao, Ming and Zhang, Yinjie and Xia, Siyu and Koniusz, Piotr}, title = {Few-Shot Shape Recognition by Learning Deep Shape-Aware Features}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1848-1859} }
Multi-Class Segmentation From Aerial Views Using Recursive Noise Diffusion: Benedikt Kolbeinsson,

Krystian Mikolajczyk; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kolbeinsson_2024_WACV, author = {Kolbeinsson, Benedikt and Mikolajczyk, Krystian}, title = {Multi-Class Segmentation From Aerial Views Using Recursive Noise Diffusion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8439-8449} }
Enhancing Multi-View Pedestrian Detection Through Generalized 3D Feature Pulling: Sithu Aung,

Haesol Park,

Hyungjoo Jung,

Junghyun Cho; [pdf] [supp]
[bibtex]
@InProceedings{Aung_2024_WACV, author = {Aung, Sithu and Park, Haesol and Jung, Hyungjoo and Cho, Junghyun}, title = {Enhancing Multi-View Pedestrian Detection Through Generalized 3D Feature Pulling}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1196-1205} }
Automated Sperm Assessment Framework and Neural Network Specialized for Sperm Video Recognition: Takuro Fujii,

Hayato Nakagawa,

Teppei Takeshima,

Yasushi Yumura,

Tomoki Hamagami; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fujii_2024_WACV, author = {Fujii, Takuro and Nakagawa, Hayato and Takeshima, Teppei and Yumura, Yasushi and Hamagami, Tomoki}, title = {Automated Sperm Assessment Framework and Neural Network Specialized for Sperm Video Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7675-7684} }
Have We Ever Encountered This Before? Retrieving Out-of-Distribution Road Obstacles From Driving Scenes: Youssef Shoeb,

Robin Chan,

Gesina Schwalbe,

Azarm Nowzad,

Fatma Güney,

Hanno Gottschalk; [pdf] [arXiv]
[bibtex]
@InProceedings{Shoeb_2024_WACV, author = {Shoeb, Youssef and Chan, Robin and Schwalbe, Gesina and Nowzad, Azarm and G\"uney, Fatma and Gottschalk, Hanno}, title = {Have We Ever Encountered This Before? Retrieving Out-of-Distribution Road Obstacles From Driving Scenes}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7396-7406} }
Polarimetric PatchMatch Multi-View Stereo: Jinyu Zhao,

Jumpei Oishi,

Yusuke Monno,

Masatoshi Okutomi; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhao_2024_WACV, author = {Zhao, Jinyu and Oishi, Jumpei and Monno, Yusuke and Okutomi, Masatoshi}, title = {Polarimetric PatchMatch Multi-View Stereo}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3476-3484} }
High-Fidelity Pseudo-Labels for Boosting Weakly-Supervised Segmentation: Arvi Jonnarth,

Yushan Zhang,

Michael Felsberg; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jonnarth_2024_WACV, author = {Jonnarth, Arvi and Zhang, Yushan and Felsberg, Michael}, title = {High-Fidelity Pseudo-Labels for Boosting Weakly-Supervised Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1010-1019} }
Optical Flow Domain Adaptation via Target Style Transfer: Jeongbeen Yoon,

Sanghyun Kim,

Suha Kwak,

Minsu Cho; [pdf] [supp]
[bibtex]
@InProceedings{Yoon_2024_WACV, author = {Yoon, Jeongbeen and Kim, Sanghyun and Kwak, Suha and Cho, Minsu}, title = {Optical Flow Domain Adaptation via Target Style Transfer}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2111-2121} }
Controlling Character Motions Without Observable Driving Source: Weiyuan Li,

Bin Dai,

Ziyi Zhou,

Qi Yao,

Baoyuan Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_WACV, author = {Li, Weiyuan and Dai, Bin and Zhou, Ziyi and Yao, Qi and Wang, Baoyuan}, title = {Controlling Character Motions Without Observable Driving Source}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6194-6203} }
Evaluation of Video Masked Autoencoders' Performance and Uncertainty Estimations for Driver Action and Intention Recognition: Koen Vellenga,

H. Joe Steinhauer,

Göran Falkman,

Tomas Björklund; [pdf]
[bibtex]
@InProceedings{Vellenga_2024_WACV, author = {Vellenga, Koen and Steinhauer, H. Joe and Falkman, G\"oran and Bj\"orklund, Tomas}, title = {Evaluation of Video Masked Autoencoders' Performance and Uncertainty Estimations for Driver Action and Intention Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7429-7437} }
Nested Diffusion Processes for Anytime Image Generation: Noam Elata,

Bahjat Kawar,

Tomer Michaeli,

Michael Elad; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Elata_2024_WACV, author = {Elata, Noam and Kawar, Bahjat and Michaeli, Tomer and Elad, Michael}, title = {Nested Diffusion Processes for Anytime Image Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5018-5027} }
Can You Even Tell Left From Right? Presenting a New Challenge for VQA: Sai Raam Venkataraman,

Rishi Sridhar Rao,

S. Balasubramanian,

R. Raghunatha Sarma,

Chandra Sekhar Vorugunti; [pdf] [supp]
[bibtex]
@InProceedings{Venkataraman_2024_WACV, author = {Venkataraman, Sai Raam and Rao, Rishi Sridhar and Balasubramanian, S. and Sarma, R. Raghunatha and Vorugunti, Chandra Sekhar}, title = {Can You Even Tell Left From Right? Presenting a New Challenge for VQA}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4498-4507} }
2D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentation: Ozan Unal,

Dengxin Dai,

Lukas Hoyer,

Yigit Baran Can,

Luc Van Gool; [pdf] [supp]
[bibtex]
@InProceedings{Unal_2024_WACV, author = {Unal, Ozan and Dai, Dengxin and Hoyer, Lukas and Can, Yigit Baran and Van Gool, Luc}, title = {2D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7336-7345} }
MAELi: Masked Autoencoder for Large-Scale LiDAR Point Clouds: Georg Krispel,

David Schinagl,

Christian Fruhwirth-Reisinger,

Horst Possegger,

Horst Bischof; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Krispel_2024_WACV, author = {Krispel, Georg and Schinagl, David and Fruhwirth-Reisinger, Christian and Possegger, Horst and Bischof, Horst}, title = {MAELi: Masked Autoencoder for Large-Scale LiDAR Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3383-3392} }
Empowering Unsupervised Domain Adaptation With Large-Scale Pre-Trained Vision-Language Models: Zhengfeng Lai,

Haoping Bai,

Haotian Zhang,

Xianzhi Du,

Jiulong Shan,

Yinfei Yang,

Chen-Nee Chuah,

Meng Cao; [pdf]
[bibtex]
@InProceedings{Lai_2024_WACV, author = {Lai, Zhengfeng and Bai, Haoping and Zhang, Haotian and Du, Xianzhi and Shan, Jiulong and Yang, Yinfei and Chuah, Chen-Nee and Cao, Meng}, title = {Empowering Unsupervised Domain Adaptation With Large-Scale Pre-Trained Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2691-2701} }
FreMIM: Fourier Transform Meets Masked Image Modeling for Medical Image Segmentation: Wenxuan Wang,

Jing Wang,

Chen Chen,

Jianbo Jiao,

Yuanxiu Cai,

Shanshan Song,

Jiangyun Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_WACV, author = {Wang, Wenxuan and Wang, Jing and Chen, Chen and Jiao, Jianbo and Cai, Yuanxiu and Song, Shanshan and Li, Jiangyun}, title = {FreMIM: Fourier Transform Meets Masked Image Modeling for Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7860-7870} }
Rotation-Constrained Cross-View Feature Fusion for Multi-View Appearance-Based Gaze Estimation: Yoichiro Hisadome,

Tianyi Wu,

Jiawei Qin,

Yusuke Sugano; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hisadome_2024_WACV, author = {Hisadome, Yoichiro and Wu, Tianyi and Qin, Jiawei and Sugano, Yusuke}, title = {Rotation-Constrained Cross-View Feature Fusion for Multi-View Appearance-Based Gaze Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5985-5994} }
Continual Atlas-Based Segmentation of Prostate MRI: Amin Ranem,

Camila González,

Daniel Pinto dos Santos,

Andreas M. Bucher,

Ahmed E. Othman,

Anirban Mukhopadhyay; [pdf] [supp]
[bibtex]
@InProceedings{Ranem_2024_WACV, author = {Ranem, Amin and Gonz\'alez, Camila and dos Santos, Daniel Pinto and Bucher, Andreas M. and Othman, Ahmed E. and Mukhopadhyay, Anirban}, title = {Continual Atlas-Based Segmentation of Prostate MRI}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7563-7572} }
CGAPoseNet+GCAN: A Geometric Clifford Algebra Network for Geometry-Aware Camera Pose Regression: Alberto Pepe,

Joan Lasenby,

Sven Buchholz; [pdf]
[bibtex]
@InProceedings{Pepe_2024_WACV, author = {Pepe, Alberto and Lasenby, Joan and Buchholz, Sven}, title = {CGAPoseNet+GCAN: A Geometric Clifford Algebra Network for Geometry-Aware Camera Pose Regression}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6593-6603} }
Contextual Affinity Distillation for Image Anomaly Detection: Jie Zhang,

Masanori Suganuma,

Takayuki Okatani; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Jie and Suganuma, Masanori and Okatani, Takayuki}, title = {Contextual Affinity Distillation for Image Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {149-158} }
Semantic-Aware Video Representation for Few-Shot Action Recognition: Yutao Tang,

Benjamín Béjar,

René Vidal; [pdf]
[bibtex]
@InProceedings{Tang_2024_WACV, author = {Tang, Yutao and B\'ejar, Benjam{\'\i}n and Vidal, Ren\'e}, title = {Semantic-Aware Video Representation for Few-Shot Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6458-6468} }
Adaptive Deep Neural Network Inference Optimization With EENet: Fatih Ilhan,

Ka-Ho Chow,

Sihao Hu,

Tiansheng Huang,

Selim Tekin,

Wenqi Wei,

Yanzhao Wu,

Myungjin Lee,

Ramana Kompella,

Hugo Latapie,

Gaowen Liu,

Ling Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ilhan_2024_WACV, author = {Ilhan, Fatih and Chow, Ka-Ho and Hu, Sihao and Huang, Tiansheng and Tekin, Selim and Wei, Wenqi and Wu, Yanzhao and Lee, Myungjin and Kompella, Ramana and Latapie, Hugo and Liu, Gaowen and Liu, Ling}, title = {Adaptive Deep Neural Network Inference Optimization With EENet}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1373-1382} }
MIVC: Multiple Instance Visual Component for Visual-Language Models: Wenyi Wu,

Qi Li,

Wenliang Zhong,

Junzhou Huang; [pdf]
[bibtex]
@InProceedings{Wu_2024_WACV, author = {Wu, Wenyi and Li, Qi and Zhong, Wenliang and Huang, Junzhou}, title = {MIVC: Multiple Instance Visual Component for Visual-Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8117-8126} }
Attentive Prototypes for Source-Free Unsupervised Domain Adaptive 3D Object Detection: Deepti Hegde,

Vishal M. Patel; [pdf] [arXiv]
[bibtex]
@InProceedings{Hegde_2024_WACV, author = {Hegde, Deepti and Patel, Vishal M.}, title = {Attentive Prototypes for Source-Free Unsupervised Domain Adaptive 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3066-3076} }
Exploring the Impact of Rendering Method and Motion Quality on Model Performance When Using Multi-View Synthetic Data for Action Recognition: Stanislav Panev,

Emily Kim,

Sai Abhishek Si Namburu,

Desislava Nikolova,

Celso de Melo,

Fernando De la Torre,

Jessica Hodgins; [pdf] [supp]
[bibtex]
@InProceedings{Panev_2024_WACV, author = {Panev, Stanislav and Kim, Emily and Namburu, Sai Abhishek Si and Nikolova, Desislava and de Melo, Celso and De la Torre, Fernando and Hodgins, Jessica}, title = {Exploring the Impact of Rendering Method and Motion Quality on Model Performance When Using Multi-View Synthetic Data for Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4592-4602} }
ATS: Adaptive Temperature Scaling for Enhancing Out-of-Distribution Detection Methods: Gerhard Krumpl,

Henning Avenhaus,

Horst Possegger,

Horst Bischof; [pdf] [supp]
[bibtex]
@InProceedings{Krumpl_2024_WACV, author = {Krumpl, Gerhard and Avenhaus, Henning and Possegger, Horst and Bischof, Horst}, title = {ATS: Adaptive Temperature Scaling for Enhancing Out-of-Distribution Detection Methods}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3864-3873} }
Exploring Adversarial Robustness of Vision Transformers in the Spectral Perspective: Gihyun Kim,

Juyeop Kim,

Jong-Seok Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2024_WACV, author = {Kim, Gihyun and Kim, Juyeop and Lee, Jong-Seok}, title = {Exploring Adversarial Robustness of Vision Transformers in the Spectral Perspective}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3976-3985} }
MotionAGFormer: Enhancing 3D Human Pose Estimation With a Transformer-GCNFormer Network: Soroush Mehraban,

Vida Adeli,

Babak Taati; [pdf] [arXiv]
[bibtex]
@InProceedings{Mehraban_2024_WACV, author = {Mehraban, Soroush and Adeli, Vida and Taati, Babak}, title = {MotionAGFormer: Enhancing 3D Human Pose Estimation With a Transformer-GCNFormer Network}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6920-6930} }
Density-Based Flow Mask Integration via Deformable Convolution for Video People Flux Estimation: Chang-Lin Wan,

Feng-Kai Huang,

Hong-Han Shuai; [pdf]
[bibtex]
@InProceedings{Wan_2024_WACV, author = {Wan, Chang-Lin and Huang, Feng-Kai and Shuai, Hong-Han}, title = {Density-Based Flow Mask Integration via Deformable Convolution for Video People Flux Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6573-6582} }
Learning Class and Domain Augmentations for Single-Source Open-Domain Generalization: Prathmesh Bele,

Valay Bundele,

Avigyan Bhattacharya,

Ankit Jha,

Gemma Roig,

Biplab Banerjee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bele_2024_WACV, author = {Bele, Prathmesh and Bundele, Valay and Bhattacharya, Avigyan and Jha, Ankit and Roig, Gemma and Banerjee, Biplab}, title = {Learning Class and Domain Augmentations for Single-Source Open-Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1816-1826} }
RankDVQA: Deep VQA Based on Ranking-Inspired Hybrid Training: Chen Feng,

Duolikun Danier,

Fan Zhang,

David Bull; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Feng_2024_WACV, author = {Feng, Chen and Danier, Duolikun and Zhang, Fan and Bull, David}, title = {RankDVQA: Deep VQA Based on Ranking-Inspired Hybrid Training}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1648-1658} }
Salient Object Detection for Images Taken by People With Vision Impairments: Jarek Reynolds,

Chandra Kanth Nagesh,

Danna Gurari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Reynolds_2024_WACV, author = {Reynolds, Jarek and Nagesh, Chandra Kanth and Gurari, Danna}, title = {Salient Object Detection for Images Taken by People With Vision Impairments}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8522-8531} }
HD-Fusion: Detailed Text-to-3D Generation Leveraging Multiple Noise Estimation: Jinbo Wu,

Xiaobo Gao,

Xing Liu,

Zhengyang Shen,

Chen Zhao,

Haocheng Feng,

Jingtuo Liu,

Errui Ding; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2024_WACV, author = {Wu, Jinbo and Gao, Xiaobo and Liu, Xing and Shen, Zhengyang and Zhao, Chen and Feng, Haocheng and Liu, Jingtuo and Ding, Errui}, title = {HD-Fusion: Detailed Text-to-3D Generation Leveraging Multiple Noise Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3202-3211} }
pSTarC: Pseudo Source Guided Target Clustering for Fully Test-Time Adaptation: Manogna Sreenivas,

Goirik Chakrabarty,

Soma Biswas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sreenivas_2024_WACV, author = {Sreenivas, Manogna and Chakrabarty, Goirik and Biswas, Soma}, title = {pSTarC: Pseudo Source Guided Target Clustering for Fully Test-Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2702-2710} }
FocusTune: Tuning Visual Localization Through Focus-Guided Sampling: Son Tung Nguyen,

Alejandro Fontan,

Michael Milford,

Tobias Fischer; [pdf] [arXiv]
[bibtex]
@InProceedings{Nguyen_2024_WACV, author = {Nguyen, Son Tung and Fontan, Alejandro and Milford, Michael and Fischer, Tobias}, title = {FocusTune: Tuning Visual Localization Through Focus-Guided Sampling}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3606-3615} }
Improving Normalization With the James-Stein Estimator: Seyedalireza Khoshsirat,

Chandra Kambhamettu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Khoshsirat_2024_WACV, author = {Khoshsirat, Seyedalireza and Kambhamettu, Chandra}, title = {Improving Normalization With the James-Stein Estimator}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2041-2051} }
Depth From Asymmetric Frame-Event Stereo: A Divide-and-Conquer Approach: Xihao Chen,

Wenming Weng,

Yueyi Zhang,

Zhiwei Xiong; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2024_WACV, author = {Chen, Xihao and Weng, Wenming and Zhang, Yueyi and Xiong, Zhiwei}, title = {Depth From Asymmetric Frame-Event Stereo: A Divide-and-Conquer Approach}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3045-3054} }
Framework-Agnostic Semantically-Aware Global Reasoning for Segmentation: Mir Rayat Imtiaz Hossain,

Leonid Sigal,

James J. Little; [pdf] [supp]
[bibtex]
@InProceedings{Hossain_2024_WACV, author = {Hossain, Mir Rayat Imtiaz and Sigal, Leonid and Little, James J.}, title = {Framework-Agnostic Semantically-Aware Global Reasoning for Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {999-1009} }
Self-Supervised Relation Alignment for Scene Graph Generation: Bicheng Xu,

Renjie Liao,

Leonid Sigal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2024_WACV, author = {Xu, Bicheng and Liao, Renjie and Sigal, Leonid}, title = {Self-Supervised Relation Alignment for Scene Graph Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1339-1349} }
Tackling Data Bias in MUSIC-AVQA: Crafting a Balanced Dataset for Unbiased Question-Answering: Xiulong Liu,

Zhikang Dong,

Peng Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2024_WACV, author = {Liu, Xiulong and Dong, Zhikang and Zhang, Peng}, title = {Tackling Data Bias in MUSIC-AVQA: Crafting a Balanced Dataset for Unbiased Question-Answering}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4478-4487} }
RPCANet: Deep Unfolding RPCA Based Infrared Small Target Detection: Fengyi Wu,

Tianfang Zhang,

Lei Li,

Yian Huang,

Zhenming Peng; [pdf] [arXiv]
[bibtex]
@InProceedings{Wu_2024_WACV, author = {Wu, Fengyi and Zhang, Tianfang and Li, Lei and Huang, Yian and Peng, Zhenming}, title = {RPCANet: Deep Unfolding RPCA Based Infrared Small Target Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4809-4818} }
GLAD: Global-Local View Alignment and Background Debiasing for Unsupervised Video Domain Adaptation With Large Domain Gap: Hyogun Lee,

Kyungho Bae,

Seong Jong Ha,

Yumin Ko,

Gyeong-Moon Park,

Jinwoo Choi; [pdf] [arXiv]
[bibtex]
@InProceedings{Lee_2024_WACV, author = {Lee, Hyogun and Bae, Kyungho and Ha, Seong Jong and Ko, Yumin and Park, Gyeong-Moon and Choi, Jinwoo}, title = {GLAD: Global-Local View Alignment and Background Debiasing for Unsupervised Video Domain Adaptation With Large Domain Gap}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6816-6825} }
Learning To Compose SuperWeights for Neural Parameter Allocation Search: Piotr Teterwak,

Soren Nelson,

Nikoli Dryden,

Dina Bashkirova,

Kate Saenko,

Bryan A. Plummer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Teterwak_2024_WACV, author = {Teterwak, Piotr and Nelson, Soren and Dryden, Nikoli and Bashkirova, Dina and Saenko, Kate and Plummer, Bryan A.}, title = {Learning To Compose SuperWeights for Neural Parameter Allocation Search}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2751-2760} }
Second-Order Graph ODEs for Multi-Agent Trajectory Forecasting: Song Wen,

Hao Wang,

Di Liu,

Qilong Zhangli,

Dimitris Metaxas; [pdf] [supp]
[bibtex]
@InProceedings{Wen_2024_WACV, author = {Wen, Song and Wang, Hao and Liu, Di and Zhangli, Qilong and Metaxas, Dimitris}, title = {Second-Order Graph ODEs for Multi-Agent Trajectory Forecasting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5101-5110} }
FOUND: Foot Optimization With Uncertain Normals for Surface Deformation Using Synthetic Data: Oliver Boyne,

Gwangbin Bae,

James Charles,

Roberto Cipolla; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Boyne_2024_WACV, author = {Boyne, Oliver and Bae, Gwangbin and Charles, James and Cipolla, Roberto}, title = {FOUND: Foot Optimization With Uncertain Normals for Surface Deformation Using Synthetic Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8097-8106} }
Unsupervised Event-Based Video Reconstruction: Gereon Fox,

Xingang Pan,

Ayush Tewari,

Mohamed Elgharib,

Christian Theobalt; [pdf] [supp]
[bibtex]
@InProceedings{Fox_2024_WACV, author = {Fox, Gereon and Pan, Xingang and Tewari, Ayush and Elgharib, Mohamed and Theobalt, Christian}, title = {Unsupervised Event-Based Video Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4179-4188} }
Can CLIP Help Sound Source Localization?: Sooyoung Park,

Arda Senocak,

Joon Son Chung; [pdf] [arXiv]
[bibtex]
@InProceedings{Park_2024_WACV, author = {Park, Sooyoung and Senocak, Arda and Chung, Joon Son}, title = {Can CLIP Help Sound Source Localization?}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5711-5720} }
FastSR-NeRF: Improving NeRF Efficiency on Consumer Devices With a Simple Super-Resolution Pipeline: Chien-Yu Lin,

Qichen Fu,

Thomas Merth,

Karren Yang,

Anurag Ranjan; [pdf] [supp]
[bibtex]
@InProceedings{Lin_2024_WACV, author = {Lin, Chien-Yu and Fu, Qichen and Merth, Thomas and Yang, Karren and Ranjan, Anurag}, title = {FastSR-NeRF: Improving NeRF Efficiency on Consumer Devices With a Simple Super-Resolution Pipeline}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6036-6045} }
Online Class-Incremental Learning for Real-World Food Image Classification: Siddeshwar Raghavan,

Jiangpeng He,

Fengqing Zhu; [pdf]
[bibtex]
@InProceedings{Raghavan_2024_WACV, author = {Raghavan, Siddeshwar and He, Jiangpeng and Zhu, Fengqing}, title = {Online Class-Incremental Learning for Real-World Food Image Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8195-8204} }
United We Stand, Divided We Fall: UnityGraph for Unsupervised Procedure Learning From Videos: Siddhant Bansal,

Chetan Arora,

C. V. Jawahar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bansal_2024_WACV, author = {Bansal, Siddhant and Arora, Chetan and Jawahar, C. V.}, title = {United We Stand, Divided We Fall: UnityGraph for Unsupervised Procedure Learning From Videos}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6509-6519} }
3D Face Style Transfer With a Hybrid Solution of NeRF and Mesh Rasterization: Jianwei Feng,

Prateek Singhal; [pdf] [arXiv]
[bibtex]
@InProceedings{Feng_2024_WACV, author = {Feng, Jianwei and Singhal, Prateek}, title = {3D Face Style Transfer With a Hybrid Solution of NeRF and Mesh Rasterization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3504-3513} }
USDN: A Unified Sample-Wise Dynamic Network With Mixed-Precision and Early-Exit: Ji-Ye Jeon,

Xuan Truong Nguyen,

Soojung Ryu,

Hyuk-Jae Lee; [pdf] [supp]
[bibtex]
@InProceedings{Jeon_2024_WACV, author = {Jeon, Ji-Ye and Nguyen, Xuan Truong and Ryu, Soojung and Lee, Hyuk-Jae}, title = {USDN: A Unified Sample-Wise Dynamic Network With Mixed-Precision and Early-Exit}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {646-654} }
Learn To Unlearn for Deep Neural Networks: Minimizing Unlearning Interference With Gradient Projection: Tuan Hoang,

Santu Rana,

Sunil Gupta,

Svetha Venkatesh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hoang_2024_WACV, author = {Hoang, Tuan and Rana, Santu and Gupta, Sunil and Venkatesh, Svetha}, title = {Learn To Unlearn for Deep Neural Networks: Minimizing Unlearning Interference With Gradient Projection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4819-4828} }
Human Motion Aware Text-to-Video Generation With Explicit Camera Control: Taehoon Kim,

ChanHee Kang,

JaeHyuk Park,

Daun Jeong,

ChangHee Yang,

Suk-Ju Kang,

Kyeongbo Kong; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2024_WACV, author = {Kim, Taehoon and Kang, ChanHee and Park, JaeHyuk and Jeong, Daun and Yang, ChangHee and Kang, Suk-Ju and Kong, Kyeongbo}, title = {Human Motion Aware Text-to-Video Generation With Explicit Camera Control}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5081-5090} }
Beyond SOT: Tracking Multiple Generic Objects at Once: Christoph Mayer,

Martin Danelljan,

Ming-Hsuan Yang,

Vittorio Ferrari,

Luc Van Gool,

Alina Kuznetsova; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mayer_2024_WACV, author = {Mayer, Christoph and Danelljan, Martin and Yang, Ming-Hsuan and Ferrari, Vittorio and Van Gool, Luc and Kuznetsova, Alina}, title = {Beyond SOT: Tracking Multiple Generic Objects at Once}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6826-6836} }
Revisiting Latent Space of GAN Inversion for Robust Real Image Editing: Kai Katsumata,

Duc Minh Vo,

Bei Liu,

Hideki Nakayama; [pdf] [supp]
[bibtex]
@InProceedings{Katsumata_2024_WACV, author = {Katsumata, Kai and Vo, Duc Minh and Liu, Bei and Nakayama, Hideki}, title = {Revisiting Latent Space of GAN Inversion for Robust Real Image Editing}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5313-5322} }
Robust TRISO-Fueled Pebble Identification by Digit Recognition: Roshan Kenia,

Jihane Mendil,

Ahmed Jasim,

Muthanna Al-Dahhan,

Zhaozheng Yin; [pdf] [supp]
[bibtex]
@InProceedings{Kenia_2024_WACV, author = {Kenia, Roshan and Mendil, Jihane and Jasim, Ahmed and Al-Dahhan, Muthanna and Yin, Zhaozheng}, title = {Robust TRISO-Fueled Pebble Identification by Digit Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8157-8165} }
Evidential Uncertainty Quantification: A Variance-Based Perspective: Ruxiao Duan,

Brian Caffo,

Harrison X. Bai,

Haris I. Sair,

Craig Jones; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Duan_2024_WACV, author = {Duan, Ruxiao and Caffo, Brian and Bai, Harrison X. and Sair, Haris I. and Jones, Craig}, title = {Evidential Uncertainty Quantification: A Variance-Based Perspective}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2132-2141} }
ICF-SRSR: Invertible Scale-Conditional Function for Self-Supervised Real-World Single Image Super-Resolution: Reyhaneh Neshatavar,

Mohsen Yavartanoo,

Sanghyun Son,

Kyoung Mu Lee; [pdf] [supp]
[bibtex]
@InProceedings{Neshatavar_2024_WACV, author = {Neshatavar, Reyhaneh and Yavartanoo, Mohsen and Son, Sanghyun and Lee, Kyoung Mu}, title = {ICF-SRSR: Invertible Scale-Conditional Function for Self-Supervised Real-World Single Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1557-1567} }
PATROL: Privacy-Oriented Pruning for Collaborative Inference Against Model Inversion Attacks: Shiwei Ding,

Lan Zhang,

Miao Pan,

Xiaoyong Yuan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ding_2024_WACV, author = {Ding, Shiwei and Zhang, Lan and Pan, Miao and Yuan, Xiaoyong}, title = {PATROL: Privacy-Oriented Pruning for Collaborative Inference Against Model Inversion Attacks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4716-4725} }
Collage Diffusion: Vishnu Sarukkai,

Linden Li,

Arden Ma,

Christopher Ré,

Kayvon Fatahalian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sarukkai_2024_WACV, author = {Sarukkai, Vishnu and Li, Linden and Ma, Arden and R\'e, Christopher and Fatahalian, Kayvon}, title = {Collage Diffusion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4208-4217} }
Camera-Independent Single Image Depth Estimation From Defocus Blur: Lahiru Wijayasingha,

Homa Alemzadeh,

John A. Stankovic; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wijayasingha_2024_WACV, author = {Wijayasingha, Lahiru and Alemzadeh, Homa and Stankovic, John A.}, title = {Camera-Independent Single Image Depth Estimation From Defocus Blur}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3749-3758} }
Wakening Past Concepts Without Past Data: Class-Incremental Learning From Online Placebos: Yaoyao Liu,

Yingying Li,

Bernt Schiele,

Qianru Sun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_WACV, author = {Liu, Yaoyao and Li, Yingying and Schiele, Bernt and Sun, Qianru}, title = {Wakening Past Concepts Without Past Data: Class-Incremental Learning From Online Placebos}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2226-2235} }
Fine-Grained Alignment for Cross-Modal Recipe Retrieval: Muntasir Wahed,

Xiaona Zhou,

Tianjiao Yu,

Ismini Lourentzou; [pdf] [supp]
[bibtex]
@InProceedings{Wahed_2024_WACV, author = {Wahed, Muntasir and Zhou, Xiaona and Yu, Tianjiao and Lourentzou, Ismini}, title = {Fine-Grained Alignment for Cross-Modal Recipe Retrieval}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5584-5593} }
NOMAD: A Natural, Occluded, Multi-Scale Aerial Dataset, for Emergency Response Scenarios: Arturo Miguel Russell Bernal,

Walter Scheirer,

Jane Cleland-Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Russell_Bernal_2024_WACV, author = {Russell Bernal, Arturo Miguel and Scheirer, Walter and Cleland-Huang, Jane}, title = {NOMAD: A Natural, Occluded, Multi-Scale Aerial Dataset, for Emergency Response Scenarios}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8584-8595} }
UNSPAT: Uncertainty-Guided SpatioTemporal Transformer for 3D Human Pose and Shape Estimation on Videos: Minsoo Lee,

Hyunmin Lee,

Bumsoo Kim,

Seunghwan Kim; [pdf]
[bibtex]
@InProceedings{Lee_2024_WACV, author = {Lee, Minsoo and Lee, Hyunmin and Kim, Bumsoo and Kim, Seunghwan}, title = {UNSPAT: Uncertainty-Guided SpatioTemporal Transformer for 3D Human Pose and Shape Estimation on Videos}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3004-3013} }
Consistent Multimodal Generation via a Unified GAN Framework: Zhen Zhu,

Yijun Li,

Weijie Lyu,

Krishna Kumar Singh,

Zhixin Shu,

Sören Pirk,

Derek Hoiem; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2024_WACV, author = {Zhu, Zhen and Li, Yijun and Lyu, Weijie and Singh, Krishna Kumar and Shu, Zhixin and Pirk, S\"oren and Hoiem, Derek}, title = {Consistent Multimodal Generation via a Unified GAN Framework}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5048-5057} }
Self-Supervised Learning of Semantic Correspondence Using Web Videos: Donghyeon Kwon,

Minsu Cho,

Suha Kwak; [pdf]
[bibtex]
@InProceedings{Kwon_2024_WACV, author = {Kwon, Donghyeon and Cho, Minsu and Kwak, Suha}, title = {Self-Supervised Learning of Semantic Correspondence Using Web Videos}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2142-2152} }
TIAM - A Metric for Evaluating Alignment in Text-to-Image Generation: Paul Grimal,

Hervé Le Borgne,

Olivier Ferret,

Julien Tourille; [pdf] [supp]
[bibtex]
@InProceedings{Grimal_2024_WACV, author = {Grimal, Paul and Le Borgne, Herv\'e and Ferret, Olivier and Tourille, Julien}, title = {TIAM - A Metric for Evaluating Alignment in Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2890-2899} }
HDMNet: A Hierarchical Matching Network With Double Attention for Large-Scale Outdoor LiDAR Point Cloud Registration: Weiyi Xue,

Fan Lu,

Guang Chen; [pdf] [arXiv]
[bibtex]
@InProceedings{Xue_2024_WACV, author = {Xue, Weiyi and Lu, Fan and Chen, Guang}, title = {HDMNet: A Hierarchical Matching Network With Double Attention for Large-Scale Outdoor LiDAR Point Cloud Registration}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3393-3403} }
UGPNet: Universal Generative Prior for Image Restoration: Hwayoon Lee,

Kyoungkook Kang,

Hyeongmin Lee,

Seung-Hwan Baek,

Sunghyun Cho; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2024_WACV, author = {Lee, Hwayoon and Kang, Kyoungkook and Lee, Hyeongmin and Baek, Seung-Hwan and Cho, Sunghyun}, title = {UGPNet: Universal Generative Prior for Image Restoration}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1598-1608} }
Defense Against Adversarial Cloud Attack on Remote Sensing Salient Object Detection: Huiming Sun,

Lan Fu,

Jinlong Li,

Qing Guo,

Zibo Meng,

Tianyun Zhang,

Yuewei Lin,

Hongkai Yu; [pdf] [arXiv]
[bibtex]
@InProceedings{Sun_2024_WACV, author = {Sun, Huiming and Fu, Lan and Li, Jinlong and Guo, Qing and Meng, Zibo and Zhang, Tianyun and Lin, Yuewei and Yu, Hongkai}, title = {Defense Against Adversarial Cloud Attack on Remote Sensing Salient Object Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8345-8354} }
Diffusion in the Dark: A Diffusion Model for Low-Light Text Recognition: Cindy M. Nguyen,

Eric R. Chan,

Alexander W. Bergman,

Gordon Wetzstein; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nguyen_2024_WACV, author = {Nguyen, Cindy M. and Chan, Eric R. and Bergman, Alexander W. and Wetzstein, Gordon}, title = {Diffusion in the Dark: A Diffusion Model for Low-Light Text Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4146-4157} }
RobustCLEVR: A Benchmark and Framework for Evaluating Robustness in Object-Centric Learning: Nathan Drenkow,

Mathias Unberath; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Drenkow_2024_WACV, author = {Drenkow, Nathan and Unberath, Mathias}, title = {RobustCLEVR: A Benchmark and Framework for Evaluating Robustness in Object-Centric Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4518-4527} }
AFTer-SAM: Adapting SAM With Axial Fusion Transformer for Medical Imaging Segmentation: Xiangyi Yan,

Shanlin Sun,

Kun Han,

Thanh-Tung Le,

Haoyu Ma,

Chenyu You,

Xiaohui Xie; [pdf]
[bibtex]
@InProceedings{Yan_2024_WACV, author = {Yan, Xiangyi and Sun, Shanlin and Han, Kun and Le, Thanh-Tung and Ma, Haoyu and You, Chenyu and Xie, Xiaohui}, title = {AFTer-SAM: Adapting SAM With Axial Fusion Transformer for Medical Imaging Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7975-7984} }
Plasticity-Optimized Complementary Networks for Unsupervised Continual Learning: Alex Gomez-Villa,

Bartlomiej Twardowski,

Kai Wang,

Joost van de Weijer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gomez-Villa_2024_WACV, author = {Gomez-Villa, Alex and Twardowski, Bartlomiej and Wang, Kai and van de Weijer, Joost}, title = {Plasticity-Optimized Complementary Networks for Unsupervised Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1690-1700} }
FATE: Feature-Agnostic Transformer-Based Encoder for Learning Generalized Embedding Spaces in Flow Cytometry Data: Lisa Weijler,

Florian Kowarsch,

Michael Reiter,

Pedro Hermosilla,

Margarita Maurer-Granofszky,

Michael Dworzak; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Weijler_2024_WACV, author = {Weijler, Lisa and Kowarsch, Florian and Reiter, Michael and Hermosilla, Pedro and Maurer-Granofszky, Margarita and Dworzak, Michael}, title = {FATE: Feature-Agnostic Transformer-Based Encoder for Learning Generalized Embedding Spaces in Flow Cytometry Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7956-7964} }
Label Augmentation As Inter-Class Data Augmentation for Conditional Image Synthesis With Imbalanced Data: Kai Katsumata,

Duc Minh Vo,

Hideki Nakayama; [pdf] [supp]
[bibtex]
@InProceedings{Katsumata_2024_WACV, author = {Katsumata, Kai and Vo, Duc Minh and Nakayama, Hideki}, title = {Label Augmentation As Inter-Class Data Augmentation for Conditional Image Synthesis With Imbalanced Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4944-4953} }
Sign Language Production With Latent Motion Transformer: Pan Xie,

Taiying Peng,

Yao Du,

Qipeng Zhang; [pdf]
[bibtex]
@InProceedings{Xie_2024_WACV, author = {Xie, Pan and Peng, Taiying and Du, Yao and Zhang, Qipeng}, title = {Sign Language Production With Latent Motion Transformer}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3024-3034} }
Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generation: Michał Stypułkowski,

Konstantinos Vougioukas,

Sen He,

Maciej Zięba,

Stavros Petridis,

Maja Pantic; [pdf]
[bibtex]
@InProceedings{Stypulkowski_2024_WACV, author = {Stypu{\l}kowski, Micha{\l} and Vougioukas, Konstantinos and He, Sen and Zi\k{e}ba, Maciej and Petridis, Stavros and Pantic, Maja}, title = {Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5091-5100} }
U3DS3: Unsupervised 3D Semantic Scene Segmentation: Jiaxu Liu,

Zhengdi Yu,

Toby P. Breckon,

Hubert P. H. Shum; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2024_WACV, author = {Liu, Jiaxu and Yu, Zhengdi and Breckon, Toby P. and Shum, Hubert P. H.}, title = {U3DS3: Unsupervised 3D Semantic Scene Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3759-3768} }
GIPCOL: Graph-Injected Soft Prompting for Compositional Zero-Shot Learning: Guangyue Xu,

Joyce Chai,

Parisa Kordjamshidi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2024_WACV, author = {Xu, Guangyue and Chai, Joyce and Kordjamshidi, Parisa}, title = {GIPCOL: Graph-Injected Soft Prompting for Compositional Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5774-5783} }
STEP - Towards Structured Scene-Text Spotting: Sergi Garcia-Bordils,

Dimosthenis Karatzas,

Marçal Rusiñol; [pdf] [supp]
[bibtex]
@InProceedings{Garcia-Bordils_2024_WACV, author = {Garcia-Bordils, Sergi and Karatzas, Dimosthenis and Rusi\~nol, Mar\c{c}al}, title = {STEP - Towards Structured Scene-Text Spotting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {883-892} }
ClipSitu: Effectively Leveraging CLIP for Conditional Predictions in Situation Recognition: Debaditya Roy,

Dhruv Verma,

Basura Fernando; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Roy_2024_WACV, author = {Roy, Debaditya and Verma, Dhruv and Fernando, Basura}, title = {ClipSitu: Effectively Leveraging CLIP for Conditional Predictions in Situation Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {444-453} }
Multimodality-Guided Image Style Transfer Using Cross-Modal GAN Inversion: Hanyu Wang,

Pengxiang Wu,

Kevin Dela Rosa,

Chen Wang,

Abhinav Shrivastava; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_WACV, author = {Wang, Hanyu and Wu, Pengxiang and Rosa, Kevin Dela and Wang, Chen and Shrivastava, Abhinav}, title = {Multimodality-Guided Image Style Transfer Using Cross-Modal GAN Inversion}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4976-4985} }
Meta-Learned Attribute Self-Interaction Network for Continual and Generalized Zero-Shot Learning: Vinay Verma,

Nikhil Mehta,

Kevin J. Liang,

Aakansha Mishra,

Lawrence Carin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Verma_2024_WACV, author = {Verma, Vinay and Mehta, Nikhil and Liang, Kevin J. and Mishra, Aakansha and Carin, Lawrence}, title = {Meta-Learned Attribute Self-Interaction Network for Continual and Generalized Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2721-2731} }
MoP-CLIP: A Mixture of Prompt-Tuned CLIP Models for Domain Incremental Learning: Julien Nicolas,

Florent Chiaroni,

Imtiaz Ziko,

Ola Ahmad,

Christian Desrosiers,

Jose Dolz; [pdf] [supp]
[bibtex]
@InProceedings{Nicolas_2024_WACV, author = {Nicolas, Julien and Chiaroni, Florent and Ziko, Imtiaz and Ahmad, Ola and Desrosiers, Christian and Dolz, Jose}, title = {MoP-CLIP: A Mixture of Prompt-Tuned CLIP Models for Domain Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1762-1772} }
So You Think You Can Track?: Derek Gloudemans,

Gergely Zachár,

Yanbing Wang,

Junyi Ji,

Matt Nice,

Matt Bunting,

William W. Barbour,

Jonathan Sprinkle,

Benedetto Piccoli,

Maria Laura Delle Monache,

Alexandre Bayen,

Benjamin Seibold,

Daniel B. Work; [pdf] [supp]
[bibtex]
@InProceedings{Gloudemans_2024_WACV, author = {Gloudemans, Derek and Zach\'ar, Gergely and Wang, Yanbing and Ji, Junyi and Nice, Matt and Bunting, Matt and Barbour, William W. and Sprinkle, Jonathan and Piccoli, Benedetto and Monache, Maria Laura Delle and Bayen, Alexandre and Seibold, Benjamin and Work, Daniel B.}, title = {So You Think You Can Track?}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4528-4538} }
OmniVec: Learning Robust Representations With Cross Modal Sharing: Siddharth Srivastava,

Gaurav Sharma; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Srivastava_2024_WACV, author = {Srivastava, Siddharth and Sharma, Gaurav}, title = {OmniVec: Learning Robust Representations With Cross Modal Sharing}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1236-1248} }
MSCC: Multi-Scale Transformers for Camera Calibration: Xu Song,

Hao Kang,

Atsunori Moteki,

Genta Suzuki,

Yoshie Kobayashi,

Zhiming Tan; [pdf]
[bibtex]
@InProceedings{Song_2024_WACV, author = {Song, Xu and Kang, Hao and Moteki, Atsunori and Suzuki, Genta and Kobayashi, Yoshie and Tan, Zhiming}, title = {MSCC: Multi-Scale Transformers for Camera Calibration}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3262-3271} }
Multi-Modal Gaze Following in Conversational Scenarios: Yuqi Hou,

Zhongqun Zhang,

Nora Horanyi,

Jaewon Moon,

Yihua Cheng,

Hyung Jin Chang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hou_2024_WACV, author = {Hou, Yuqi and Zhang, Zhongqun and Horanyi, Nora and Moon, Jaewon and Cheng, Yihua and Chang, Hyung Jin}, title = {Multi-Modal Gaze Following in Conversational Scenarios}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1186-1195} }
Contrastive Viewpoint-Aware Shape Learning for Long-Term Person Re-Identification: Vuong D. Nguyen,

Khadija Khaldi,

Dung Nguyen,

Pranav Mantini,

Shishir Shah; [pdf]
[bibtex]
@InProceedings{Nguyen_2024_WACV, author = {Nguyen, Vuong D. and Khaldi, Khadija and Nguyen, Dung and Mantini, Pranav and Shah, Shishir}, title = {Contrastive Viewpoint-Aware Shape Learning for Long-Term Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1041-1049} }
Scale-Adaptive Feature Aggregation for Efficient Space-Time Video Super-Resolution: Zhewei Huang,

Ailin Huang,

Xiaotao Hu,

Chen Hu,

Jun Xu,

Shuchang Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2024_WACV, author = {Huang, Zhewei and Huang, Ailin and Hu, Xiaotao and Hu, Chen and Xu, Jun and Zhou, Shuchang}, title = {Scale-Adaptive Feature Aggregation for Efficient Space-Time Video Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4228-4239} }
SSP: Semi-Signed Prioritized Neural Fitting for Surface Reconstruction From Unoriented Point Clouds: Runsong Zhu,

Di Kang,

Ka-Hei Hui,

Yue Qian,

Shi Qiu,

Zhen Dong,

Linchao Bao,

Pheng-Ann Heng,

Chi-Wing Fu; [pdf] [supp]
[bibtex]
@InProceedings{Zhu_2024_WACV, author = {Zhu, Runsong and Kang, Di and Hui, Ka-Hei and Qian, Yue and Qiu, Shi and Dong, Zhen and Bao, Linchao and Heng, Pheng-Ann and Fu, Chi-Wing}, title = {SSP: Semi-Signed Prioritized Neural Fitting for Surface Reconstruction From Unoriented Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3769-3778} }
DeVos: Flow-Guided Deformable Transformer for Video Object Segmentation: Volodymyr Fedynyak,

Yaroslav Romanus,

Bohdan Hlovatskyi,

Bohdan Sydor,

Oles Dobosevych,

Igor Babin,

Roman Riazantsev; [pdf] [supp]
[bibtex]
@InProceedings{Fedynyak_2024_WACV, author = {Fedynyak, Volodymyr and Romanus, Yaroslav and Hlovatskyi, Bohdan and Sydor, Bohdan and Dobosevych, Oles and Babin, Igor and Riazantsev, Roman}, title = {DeVos: Flow-Guided Deformable Transformer for Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {240-249} }
GraphFill: Deep Image Inpainting Using Graphs: Shashikant Verma,

Aman Sharma,

Roopa Sheshadri,

Shanmuganathan Raman; [pdf] [supp]
[bibtex]
@InProceedings{Verma_2024_WACV, author = {Verma, Shashikant and Sharma, Aman and Sheshadri, Roopa and Raman, Shanmuganathan}, title = {GraphFill: Deep Image Inpainting Using Graphs}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4996-5006} }
AU-Aware Dynamic 3D Face Reconstruction From Videos With Transformer: Chenyi Kuang,

Jeffrey O. Kephart,

Qiang Ji; [pdf] [supp]
[bibtex]
@InProceedings{Kuang_2024_WACV, author = {Kuang, Chenyi and Kephart, Jeffrey O. and Ji, Qiang}, title = {AU-Aware Dynamic 3D Face Reconstruction From Videos With Transformer}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6237-6247} }
Unified Concept Editing in Diffusion Models: Rohit Gandikota,

Hadas Orgad,

Yonatan Belinkov,

Joanna Materzyńska,

David Bau; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gandikota_2024_WACV, author = {Gandikota, Rohit and Orgad, Hadas and Belinkov, Yonatan and Materzy\'nska, Joanna and Bau, David}, title = {Unified Concept Editing in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5111-5120} }
MEGANet: Multi-Scale Edge-Guided Attention Network for Weak Boundary Polyp Segmentation: Nhat-Tan Bui,

Dinh-Hieu Hoang,

Quang-Thuc Nguyen,

Minh-Triet Tran,

Ngan Le; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bui_2024_WACV, author = {Bui, Nhat-Tan and Hoang, Dinh-Hieu and Nguyen, Quang-Thuc and Tran, Minh-Triet and Le, Ngan}, title = {MEGANet: Multi-Scale Edge-Guided Attention Network for Weak Boundary Polyp Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7985-7994} }
GazeGNN: A Gaze-Guided Graph Neural Network for Chest X-Ray Classification: Bin Wang,

Hongyi Pan,

Armstrong Aboah,

Zheyuan Zhang,

Elif Keles,

Drew Torigian,

Baris Turkbey,

Elizabeth Krupinski,

Jayaram Udupa,

Ulas Bagci; [pdf]
[bibtex]
@InProceedings{Wang_2024_WACV, author = {Wang, Bin and Pan, Hongyi and Aboah, Armstrong and Zhang, Zheyuan and Keles, Elif and Torigian, Drew and Turkbey, Baris and Krupinski, Elizabeth and Udupa, Jayaram and Bagci, Ulas}, title = {GazeGNN: A Gaze-Guided Graph Neural Network for Chest X-Ray Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2194-2203} }
LipAT: Beyond Style Transfer for Controllable Neural Simulation of Lipstick Using Cosmetic Attributes: Amila Silva,

Olga Moskvyak,

Alexander Long,

Ravi Garg,

Stephen Gould,

Gil Avraham,

Anton van den Hengel; [pdf] [supp]
[bibtex]
@InProceedings{Silva_2024_WACV, author = {Silva, Amila and Moskvyak, Olga and Long, Alexander and Garg, Ravi and Gould, Stephen and Avraham, Gil and van den Hengel, Anton}, title = {LipAT: Beyond Style Transfer for Controllable Neural Simulation of Lipstick Using Cosmetic Attributes}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8046-8055} }
WildlifeDatasets: An Open-Source Toolkit for Animal Re-Identification: Vojtěch Čermák,

Lukas Picek,

Lukáš Adam,

Kostas Papafitsoros; [pdf] [supp]
[bibtex]
@InProceedings{Cermak_2024_WACV, author = {\v{C}erm\'ak, Vojt\v{e}ch and Picek, Lukas and Adam, Luk\'a\v{s} and Papafitsoros, Kostas}, title = {WildlifeDatasets: An Open-Source Toolkit for Animal Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5953-5963} }
OTAS: Unsupervised Boundary Detection for Object-Centric Temporal Action Segmentation: Yuerong Li,

Zhengrong Xue,

Huazhe Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_WACV, author = {Li, Yuerong and Xue, Zhengrong and Xu, Huazhe}, title = {OTAS: Unsupervised Boundary Detection for Object-Centric Temporal Action Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6437-6446} }
Deblur-NSFF: Neural Scene Flow Fields for Blurry Dynamic Scenes: Achleshwar Luthra,

Shiva Souhith Gantha,

Xiyun Song,

Heather Yu,

Zongfang Lin,

Liang Peng; [pdf]
[bibtex]
@InProceedings{Luthra_2024_WACV, author = {Luthra, Achleshwar and Gantha, Shiva Souhith and Song, Xiyun and Yu, Heather and Lin, Zongfang and Peng, Liang}, title = {Deblur-NSFF: Neural Scene Flow Fields for Blurry Dynamic Scenes}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3658-3667} }
Multi-Source Domain Adaptation for Object Detection With Prototype-Based Mean Teacher: Atif Belal,

Akhil Meethal,

Francisco Perdigon Romero,

Marco Pedersoli,

Eric Granger; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Belal_2024_WACV, author = {Belal, Atif and Meethal, Akhil and Romero, Francisco Perdigon and Pedersoli, Marco and Granger, Eric}, title = {Multi-Source Domain Adaptation for Object Detection With Prototype-Based Mean Teacher}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1277-1286} }
PathLDM: Text Conditioned Latent Diffusion Model for Histopathology: Srikar Yellapragada,

Alexandros Graikos,

Prateek Prasanna,

Tahsin Kurc,

Joel Saltz,

Dimitris Samaras; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yellapragada_2024_WACV, author = {Yellapragada, Srikar and Graikos, Alexandros and Prasanna, Prateek and Kurc, Tahsin and Saltz, Joel and Samaras, Dimitris}, title = {PathLDM: Text Conditioned Latent Diffusion Model for Histopathology}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5182-5191} }
EASUM: Enhancing Affective State Understanding Through Joint Sentiment and Emotion Modeling for Multimodal Tasks: Yewon Hwang,

Jong-Hwan Kim; [pdf]
[bibtex]
@InProceedings{Hwang_2024_WACV, author = {Hwang, Yewon and Kim, Jong-Hwan}, title = {EASUM: Enhancing Affective State Understanding Through Joint Sentiment and Emotion Modeling for Multimodal Tasks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5668-5678} }
Efficient Explainable Face Verification Based on Similarity Score Argument Backpropagation: Marco Huber,

Anh Thi Luu,

Philipp Terhörst,

Naser Damer; [pdf] [supp]
[bibtex]
@InProceedings{Huber_2024_WACV, author = {Huber, Marco and Luu, Anh Thi and Terh\"orst, Philipp and Damer, Naser}, title = {Efficient Explainable Face Verification Based on Similarity Score Argument Backpropagation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4736-4745} }
Rank2Tell: A Multimodal Driving Dataset for Joint Importance Ranking and Reasoning: Enna Sachdeva,

Nakul Agarwal,

Suhas Chundi,

Sean Roelofs,

Jiachen Li,

Mykel Kochenderfer,

Chiho Choi,

Behzad Dariush; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sachdeva_2024_WACV, author = {Sachdeva, Enna and Agarwal, Nakul and Chundi, Suhas and Roelofs, Sean and Li, Jiachen and Kochenderfer, Mykel and Choi, Chiho and Dariush, Behzad}, title = {Rank2Tell: A Multimodal Driving Dataset for Joint Importance Ranking and Reasoning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7513-7522} }
ArcAid: Analysis of Archaeological Artifacts Using Drawings: Offry Hayon,

Stefan Münger,

Ilan Shimshoni,

Ayellet Tal; [pdf] [supp]
[bibtex]
@InProceedings{Hayon_2024_WACV, author = {Hayon, Offry and M\"unger, Stefan and Shimshoni, Ilan and Tal, Ayellet}, title = {ArcAid: Analysis of Archaeological Artifacts Using Drawings}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7264-7274} }
FishTrack23: An Ensemble Underwater Dataset for Multi-Object Tracking: Matthew Dawkins,

Jack Prior,

Bryon Lewis,

Robin Faillettaz,

Thompson Banez,

Mary Salvi,

Audrey Rollo,

Julien Simon,

Matthew Campbell,

Matthew Lucero,

Aashish Chaudhary,

Benjamin Richards,

Anthony Hoogs; [pdf] [supp]
[bibtex]
@InProceedings{Dawkins_2024_WACV, author = {Dawkins, Matthew and Prior, Jack and Lewis, Bryon and Faillettaz, Robin and Banez, Thompson and Salvi, Mary and Rollo, Audrey and Simon, Julien and Campbell, Matthew and Lucero, Matthew and Chaudhary, Aashish and Richards, Benjamin and Hoogs, Anthony}, title = {FishTrack23: An Ensemble Underwater Dataset for Multi-Object Tracking}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7167-7176} }
Reducing the Side-Effects of Oscillations in Training of Quantized YOLO Networks: Kartik Gupta,

Akshay Asthana; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gupta_2024_WACV, author = {Gupta, Kartik and Asthana, Akshay}, title = {Reducing the Side-Effects of Oscillations in Training of Quantized YOLO Networks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2452-2461} }
PressureVision++: Estimating Fingertip Pressure From Diverse RGB Images: Patrick Grady,

Jeremy A. Collins,

Chengcheng Tang,

Christopher D. Twigg,

Kunal Aneja,

James Hays,

Charles C. Kemp; [pdf] [supp]
[bibtex]
@InProceedings{Grady_2024_WACV, author = {Grady, Patrick and Collins, Jeremy A. and Tang, Chengcheng and Twigg, Christopher D. and Aneja, Kunal and Hays, James and Kemp, Charles C.}, title = {PressureVision++: Estimating Fingertip Pressure From Diverse RGB Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8698-8708} }
Diffusion Models Meet Image Counter-Forensics: Matías Tailanián,

Marina Gardella,

Alvaro Pardo,

Pablo Musé; [pdf] [supp]
[bibtex]
@InProceedings{Tailanian_2024_WACV, author = {Tailani\'an, Mat{\'\i}as and Gardella, Marina and Pardo, Alvaro and Mus\'e, Pablo}, title = {Diffusion Models Meet Image Counter-Forensics}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3925-3935} }
STYLIP: Multi-Scale Style-Conditioned Prompt Learning for CLIP-Based Domain Generalization: Shirsha Bose,

Ankit Jha,

Enrico Fini,

Mainak Singha,

Elisa Ricci,

Biplab Banerjee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bose_2024_WACV, author = {Bose, Shirsha and Jha, Ankit and Fini, Enrico and Singha, Mainak and Ricci, Elisa and Banerjee, Biplab}, title = {STYLIP: Multi-Scale Style-Conditioned Prompt Learning for CLIP-Based Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5542-5552} }
Increasing Biases Can Be More Efficient Than Increasing Weights: Carlo Metta,

Marco Fantozzi,

Andrea Papini,

Gianluca Amato,

Matteo Bergamaschi,

Silvia Giulia Galfrè,

Alessandro Marchetti,

Michelangelo Vegliò,

Maurizio Parton,

Francesco Morandin; [pdf]
[bibtex]
@InProceedings{Metta_2024_WACV, author = {Metta, Carlo and Fantozzi, Marco and Papini, Andrea and Amato, Gianluca and Bergamaschi, Matteo and Galfr\`e, Silvia Giulia and Marchetti, Alessandro and Vegli\`o, Michelangelo and Parton, Maurizio and Morandin, Francesco}, title = {Increasing Biases Can Be More Efficient Than Increasing Weights}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2810-2819} }
TransRadar: Adaptive-Directional Transformer for Real-Time Multi-View Radar Semantic Segmentation: Yahia Dalbah,

Jean Lahoud,

Hisham Cholakkal; [pdf] [arXiv]
[bibtex]
@InProceedings{Dalbah_2024_WACV, author = {Dalbah, Yahia and Lahoud, Jean and Cholakkal, Hisham}, title = {TransRadar: Adaptive-Directional Transformer for Real-Time Multi-View Radar Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {353-362} }
Sequential Transformer for End-to-End Video Text Detection: Jun-Bo Zhang,

Meng-Biao Zhao,

Fei Yin,

Cheng-Lin Liu; [pdf]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Jun-Bo and Zhao, Meng-Biao and Yin, Fei and Liu, Cheng-Lin}, title = {Sequential Transformer for End-to-End Video Text Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6520-6530} }
The Background Also Matters: Background-Aware Motion-Guided Objects Discovery: Sandra Kara,

Hejer Ammar,

Florian Chabot,

Quoc-Cuong Pham; [pdf] [arXiv]
[bibtex]
@InProceedings{Kara_2024_WACV, author = {Kara, Sandra and Ammar, Hejer and Chabot, Florian and Pham, Quoc-Cuong}, title = {The Background Also Matters: Background-Aware Motion-Guided Objects Discovery}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1216-1225} }
Neural Style Protection: Counteracting Unauthorized Neural Style Transfer: Yaxin Li,

Jie Ren,

Han Xu,

Hui Liu; [pdf]
[bibtex]
@InProceedings{Li_2024_WACV, author = {Li, Yaxin and Ren, Jie and Xu, Han and Liu, Hui}, title = {Neural Style Protection: Counteracting Unauthorized Neural Style Transfer}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3966-3975} }
FRoG-MOT: Fast and Robust Generic Multiple-Object Tracking by IoU and Motion-State Associations: Takuya Ogawa,

Takashi Shibata,

Toshinori Hosoi; [pdf] [supp]
[bibtex]
@InProceedings{Ogawa_2024_WACV, author = {Ogawa, Takuya and Shibata, Takashi and Hosoi, Toshinori}, title = {FRoG-MOT: Fast and Robust Generic Multiple-Object Tracking by IoU and Motion-State Associations}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6563-6572} }
OVeNet: Offset Vector Network for Semantic Segmentation: Stamatis Alexandropoulos,

Christos Sakaridis,

Petros Maragos; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Alexandropoulos_2024_WACV, author = {Alexandropoulos, Stamatis and Sakaridis, Christos and Maragos, Petros}, title = {OVeNet: Offset Vector Network for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7407-7418} }
A Neural Height-Map Approach for the Binocular Photometric Stereo Problem: Fotios Logothetis,

Ignas Budvytis,

Roberto Cipolla; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Logothetis_2024_WACV, author = {Logothetis, Fotios and Budvytis, Ignas and Cipolla, Roberto}, title = {A Neural Height-Map Approach for the Binocular Photometric Stereo Problem}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1568-1577} }
Towards Addressing the Misalignment of Object Proposal Evaluation for Vision-Language Tasks via Semantic Grounding: Joshua Feinglass,

Yezhou Yang; [pdf] [arXiv]
[bibtex]
@InProceedings{Feinglass_2024_WACV, author = {Feinglass, Joshua and Yang, Yezhou}, title = {Towards Addressing the Misalignment of Object Proposal Evaluation for Vision-Language Tasks via Semantic Grounding}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4397-4407} }
Spiking Neural Networks for Active Time-Resolved SPAD Imaging: Yang Lin,

Edoardo Charbon; [pdf]
[bibtex]
@InProceedings{Lin_2024_WACV, author = {Lin, Yang and Charbon, Edoardo}, title = {Spiking Neural Networks for Active Time-Resolved SPAD Imaging}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8147-8156} }
Domain Generalization With Correlated Style Uncertainty: Zheyuan Zhang,

Bin Wang,

Debesh Jha,

Ugur Demir,

Ulas Bagci; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Zheyuan and Wang, Bin and Jha, Debesh and Demir, Ugur and Bagci, Ulas}, title = {Domain Generalization With Correlated Style Uncertainty}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2000-2009} }
Leveraging Next-Active Objects for Context-Aware Anticipation in Egocentric Videos: Sanket Thakur,

Cigdem Beyan,

Pietro Morerio,

Vittorio Murino,

Alessio Del Bue; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Thakur_2024_WACV, author = {Thakur, Sanket and Beyan, Cigdem and Morerio, Pietro and Murino, Vittorio and Del Bue, Alessio}, title = {Leveraging Next-Active Objects for Context-Aware Anticipation in Egocentric Videos}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8657-8666} }
CryoRL: Reinforcement Learning Enables Efficient Cryo-EM Data Collection: Quanfu Fan,

Yilai Li,

Yuguang Yao,

John Cohn,

Sijia Liu,

Ziping Xu,

Seychelle Vos,

Michael Cianfrocco; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fan_2024_WACV, author = {Fan, Quanfu and Li, Yilai and Yao, Yuguang and Cohn, John and Liu, Sijia and Xu, Ziping and Vos, Seychelle and Cianfrocco, Michael}, title = {CryoRL: Reinforcement Learning Enables Efficient Cryo-EM Data Collection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7892-7902} }
On the Fly Neural Style Smoothing for Risk-Averse Domain Generalization: Akshay Mehra,

Yunbei Zhang,

Bhavya Kailkhura,

Jihun Hamm; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mehra_2024_WACV, author = {Mehra, Akshay and Zhang, Yunbei and Kailkhura, Bhavya and Hamm, Jihun}, title = {On the Fly Neural Style Smoothing for Risk-Averse Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3800-3811} }
StyleGenes: Discrete and Efficient Latent Distributions for GANs: Evangelos Ntavelis,

Mohamad Shahbazi,

Iason Kastanis,

Martin Danelljan,

Luc Van Gool; [pdf] [arXiv]
[bibtex]
@InProceedings{Ntavelis_2024_WACV, author = {Ntavelis, Evangelos and Shahbazi, Mohamad and Kastanis, Iason and Danelljan, Martin and Van Gool, Luc}, title = {StyleGenes: Discrete and Efficient Latent Distributions for GANs}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4077-4086} }
Aligning Non-Causal Factors for Transformer-Based Source-Free Domain Adaptation: Sunandini Sanyal,

Ashish Ramayee Asokan,

Suvaansh Bhambri,

Pradyumna YM,

Akshay Kulkarni,

Jogendra Nath Kundu,

R. Venkatesh Babu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sanyal_2024_WACV, author = {Sanyal, Sunandini and Asokan, Ashish Ramayee and Bhambri, Suvaansh and YM, Pradyumna and Kulkarni, Akshay and Kundu, Jogendra Nath and Babu, R. Venkatesh}, title = {Aligning Non-Causal Factors for Transformer-Based Source-Free Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1904-1913} }
Benchmarking Out-of-Distribution Detection in Visual Question Answering: Xiangxi Shi,

Stefan Lee; [pdf] [supp]
[bibtex]
@InProceedings{Shi_2024_WACV, author = {Shi, Xiangxi and Lee, Stefan}, title = {Benchmarking Out-of-Distribution Detection in Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5485-5495} }
Joint Depth Prediction and Semantic Segmentation With Multi-View SAM: Mykhailo Shvets,

Dongxu Zhao,

Marc Niethammer,

Roni Sengupta,

Alexander C. Berg; [pdf] [arXiv]
[bibtex]
@InProceedings{Shvets_2024_WACV, author = {Shvets, Mykhailo and Zhao, Dongxu and Niethammer, Marc and Sengupta, Roni and Berg, Alexander C.}, title = {Joint Depth Prediction and Semantic Segmentation With Multi-View SAM}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1328-1338} }
GC-VTON: Predicting Globally Consistent and Occlusion Aware Local Flows With Neighborhood Integrity Preservation for Virtual Try-On: Hamza Rawal,

Muhammad Junaid Ahmad,

Farooq Zaman; [pdf] [supp]
[bibtex]
@InProceedings{Rawal_2024_WACV, author = {Rawal, Hamza and Ahmad, Muhammad Junaid and Zaman, Farooq}, title = {GC-VTON: Predicting Globally Consistent and Occlusion Aware Local Flows With Neighborhood Integrity Preservation for Virtual Try-On}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5251-5260} }
Enforcing Sparsity on Latent Space for Robust and Explainable Representations: Hanao Li,

Tian Han; [pdf] [supp]
[bibtex]
@InProceedings{Li_2024_WACV, author = {Li, Hanao and Han, Tian}, title = {Enforcing Sparsity on Latent Space for Robust and Explainable Representations}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5282-5291} }
Unsupervised Domain Adaptation for Semantic Segmentation With Pseudo Label Self-Refinement: Xingchen Zhao,

Niluthpol Chowdhury Mithun,

Abhinav Rajvanshi,

Han-Pang Chiu,

Supun Samarasekera; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2024_WACV, author = {Zhao, Xingchen and Mithun, Niluthpol Chowdhury and Rajvanshi, Abhinav and Chiu, Han-Pang and Samarasekera, Supun}, title = {Unsupervised Domain Adaptation for Semantic Segmentation With Pseudo Label Self-Refinement}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2399-2409} }
HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Information: Heitor Rapela Medeiros,

Fidel A. Guerrero Peña,

Masih Aminbeidokhti,

Thomas Dubail,

Eric Granger,

Marco Pedersoli; [pdf] [supp]
[bibtex]
@InProceedings{Medeiros_2024_WACV, author = {Medeiros, Heitor Rapela and Pe\~na, Fidel A. Guerrero and Aminbeidokhti, Masih and Dubail, Thomas and Granger, Eric and Pedersoli, Marco}, title = {HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Information}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1444-1453} }
Improving Fairness in Deepfake Detection: Yan Ju,

Shu Hu,

Shan Jia,

George H. Chen,

Siwei Lyu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ju_2024_WACV, author = {Ju, Yan and Hu, Shu and Jia, Shan and Chen, George H. and Lyu, Siwei}, title = {Improving Fairness in Deepfake Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4655-4665} }
Evolve: Enhancing Unsupervised Continual Learning With Multiple Experts: Xiaofan Yu,

Tajana Rosing,

Yunhui Guo; [pdf] [supp]
[bibtex]
@InProceedings{Yu_2024_WACV, author = {Yu, Xiaofan and Rosing, Tajana and Guo, Yunhui}, title = {Evolve: Enhancing Unsupervised Continual Learning With Multiple Experts}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2366-2377} }
NeRFEditor: Differentiable Style Decomposition for 3D Scene Editing: Chunyi Sun,

Yanbin Liu,

Junlin Han,

Stephen Gould; [pdf]
[bibtex]
@InProceedings{Sun_2024_WACV, author = {Sun, Chunyi and Liu, Yanbin and Han, Junlin and Gould, Stephen}, title = {NeRFEditor: Differentiable Style Decomposition for 3D Scene Editing}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7306-7315} }
Personalized Face Inpainting With Diffusion Models by Parallel Visual Attention: Jianjin Xu,

Saman Motamed,

Praneetha Vaddamanu,

Chen Henry Wu,

Christian Haene,

Jean-Charles Bazin,

Fernando De la Torre; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2024_WACV, author = {Xu, Jianjin and Motamed, Saman and Vaddamanu, Praneetha and Wu, Chen Henry and Haene, Christian and Bazin, Jean-Charles and De la Torre, Fernando}, title = {Personalized Face Inpainting With Diffusion Models by Parallel Visual Attention}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5432-5442} }
AvatarOne: Monocular 3D Human Animation: Akash Karthikeyan,

Robert Ren,

Yash Kant,

Igor Gilitschenski; [pdf] [supp]
[bibtex]
@InProceedings{Karthikeyan_2024_WACV, author = {Karthikeyan, Akash and Ren, Robert and Kant, Yash and Gilitschenski, Igor}, title = {AvatarOne: Monocular 3D Human Animation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3647-3657} }
Synthesizing Anyone, Anywhere, in Any Pose: Håkon Hukkelås,

Frank Lindseth; [pdf] [supp]
[bibtex]
@InProceedings{Hukkelas_2024_WACV, author = {Hukkel\r{a}s, H\r{a}kon and Lindseth, Frank}, title = {Synthesizing Anyone, Anywhere, in Any Pose}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4035-4046} }
Ray Deformation Networks for Novel View Synthesis of Refractive Objects: Weijian Deng,

Dylan Campbell,

Chunyi Sun,

Shubham Kanitkar,

Matthew Shaffer,

Stephen Gould; [pdf] [supp]
[bibtex]
@InProceedings{Deng_2024_WACV, author = {Deng, Weijian and Campbell, Dylan and Sun, Chunyi and Kanitkar, Shubham and Shaffer, Matthew and Gould, Stephen}, title = {Ray Deformation Networks for Novel View Synthesis of Refractive Objects}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3118-3128} }
NITEC: Versatile Hand-Annotated Eye Contact Dataset for Ego-Vision Interaction: Thorsten Hempel,

Magnus Jung,

Ahmed A. Abdelrahman,

Ayoub Al-Hamadi; [pdf] [arXiv]
[bibtex]
@InProceedings{Hempel_2024_WACV, author = {Hempel, Thorsten and Jung, Magnus and Abdelrahman, Ahmed A. and Al-Hamadi, Ayoub}, title = {NITEC: Versatile Hand-Annotated Eye Contact Dataset for Ego-Vision Interaction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4437-4446} }
Tunable Hybrid Proposal Networks for the Open World: Matthew Inkawhich,

Nathan Inkawhich,

Hai Li,

Yiran Chen; [pdf] [supp]
[bibtex]
@InProceedings{Inkawhich_2024_WACV, author = {Inkawhich, Matthew and Inkawhich, Nathan and Li, Hai and Chen, Yiran}, title = {Tunable Hybrid Proposal Networks for the Open World}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1988-1999} }
3D Reconstruction of Interacting Multi-Person in Clothing From a Single Image: Junuk Cha,

Hansol Lee,

Jaewon Kim,

Nhat Nguyen Bao Truong,

Jaeshin Yoon,

Seungryul Baek; [pdf] [supp]
[bibtex]
@InProceedings{Cha_2024_WACV, author = {Cha, Junuk and Lee, Hansol and Kim, Jaewon and Truong, Nhat Nguyen Bao and Yoon, Jaeshin and Baek, Seungryul}, title = {3D Reconstruction of Interacting Multi-Person in Clothing From a Single Image}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5303-5312} }
LensNeRF: Rethinking Volume Rendering Based on Thin-Lens Camera Model: Min-Jung Kim,

Gyojung Gu,

Jaegul Choo; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2024_WACV, author = {Kim, Min-Jung and Gu, Gyojung and Choo, Jaegul}, title = {LensNeRF: Rethinking Volume Rendering Based on Thin-Lens Camera Model}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3182-3191} }
Composite Diffusion: whole >= Sparts: Vikram Jamwal,

Ramaneswaran S.; [pdf] [supp]
[bibtex]
@InProceedings{Jamwal_2024_WACV, author = {Jamwal, Vikram and S., Ramaneswaran}, title = {Composite Diffusion: whole \ensuremath{>}= Sparts}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7231-7240} }
P2D: Plug and Play Discriminator for Accelerating GAN Frameworks: Min Jin Chong,

Krishna Kumar Singh,

Yijun Li,

Jingwan Lu,

David Forsyth; [pdf] [supp]
[bibtex]
@InProceedings{Chong_2024_WACV, author = {Chong, Min Jin and Singh, Krishna Kumar and Li, Yijun and Lu, Jingwan and Forsyth, David}, title = {P2D: Plug and Play Discriminator for Accelerating GAN Frameworks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5422-5431} }
PMI Sampler: Patch Similarity Guided Frame Selection for Aerial Action Recognition: Ruiqi Xian,

Xijun Wang,

Divya Kothandaraman,

Dinesh Manocha; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xian_2024_WACV, author = {Xian, Ruiqi and Wang, Xijun and Kothandaraman, Divya and Manocha, Dinesh}, title = {PMI Sampler: Patch Similarity Guided Frame Selection for Aerial Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6982-6991} }
REALM: Robust Entropy Adaptive Loss Minimization for Improved Single-Sample Test-Time Adaptation: Skyler Seto,

Barry-John Theobald,

Federico Danieli,

Navdeep Jaitly,

Dan Busbridge; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Seto_2024_WACV, author = {Seto, Skyler and Theobald, Barry-John and Danieli, Federico and Jaitly, Navdeep and Busbridge, Dan}, title = {REALM: Robust Entropy Adaptive Loss Minimization for Improved Single-Sample Test-Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2062-2071} }
TSA2: Temporal Segment Adaptation and Aggregation for Video Harmonization: Zeyu Xiao,

Yurui Zhu,

Xueyang Fu,

Zhiwei Xiong; [pdf] [supp]
[bibtex]
@InProceedings{Xiao_2024_WACV, author = {Xiao, Zeyu and Zhu, Yurui and Fu, Xueyang and Xiong, Zhiwei}, title = {TSA2: Temporal Segment Adaptation and Aggregation for Video Harmonization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4136-4145} }
PMVC: Promoting Multi-View Consistency for 3D Scene Reconstruction: Chushan Zhang,

Jinguang Tong,

Tao Jun Lin,

Chuong Nguyen,

Hongdong Li; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Chushan and Tong, Jinguang and Lin, Tao Jun and Nguyen, Chuong and Li, Hongdong}, title = {PMVC: Promoting Multi-View Consistency for 3D Scene Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3678-3688} }
MGM-AE: Self-Supervised Learning on 3D Shape Using Mesh Graph Masked Autoencoders: Zhangsihao Yang,

Kaize Ding,

Huan Liu,

Yalin Wang; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2024_WACV, author = {Yang, Zhangsihao and Ding, Kaize and Liu, Huan and Wang, Yalin}, title = {MGM-AE: Self-Supervised Learning on 3D Shape Using Mesh Graph Masked Autoencoders}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3303-3313} }
Interactive Network Perturbation Between Teacher and Students for Semi-Supervised Semantic Segmentation: Hyuna Cho,

Injun Choi,

Suha Kwak,

Won Hwa Kim; [pdf] [supp]
[bibtex]
@InProceedings{Cho_2024_WACV, author = {Cho, Hyuna and Choi, Injun and Kwak, Suha and Kim, Won Hwa}, title = {Interactive Network Perturbation Between Teacher and Students for Semi-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {626-635} }
Minimizing Layerwise Activation Norm Improves Generalization in Federated Learning: M. Yashwanth,

Gaurav Kumar Nayak,

Harsh Rangwani,

Arya Singh,

R. Venkatesh Babu,

Anirban Chakraborty; [pdf] [supp]
[bibtex]
@InProceedings{Yashwanth_2024_WACV, author = {Yashwanth, M. and Nayak, Gaurav Kumar and Rangwani, Harsh and Singh, Arya and Babu, R. Venkatesh and Chakraborty, Anirban}, title = {Minimizing Layerwise Activation Norm Improves Generalization in Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2287-2296} }
ReCLIP: Refine Contrastive Language Image Pre-Training With Source Free Domain Adaptation: Xuefeng Hu,

Ke Zhang,

Lu Xia,

Albert Chen,

Jiajia Luo,

Yuyin Sun,

Ken Wang,

Nan Qiao,

Xiao Zeng,

Min Sun,

Cheng-Hao Kuo,

Ram Nevatia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hu_2024_WACV, author = {Hu, Xuefeng and Zhang, Ke and Xia, Lu and Chen, Albert and Luo, Jiajia and Sun, Yuyin and Wang, Ken and Qiao, Nan and Zeng, Xiao and Sun, Min and Kuo, Cheng-Hao and Nevatia, Ram}, title = {ReCLIP: Refine Contrastive Language Image Pre-Training With Source Free Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2994-3003} }
PointCT: Point Central Transformer Network for Weakly-Supervised Point Cloud Semantic Segmentation: Anh-Thuan Tran,

Hoanh-Su Le,

Suk-Hwan Lee,

Ki-Ryong Kwon; [pdf] [supp]
[bibtex]
@InProceedings{Tran_2024_WACV, author = {Tran, Anh-Thuan and Le, Hoanh-Su and Lee, Suk-Hwan and Kwon, Ki-Ryong}, title = {PointCT: Point Central Transformer Network for Weakly-Supervised Point Cloud Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3556-3565} }
Lightweight Delivery Detection on Doorbell Cameras: Pirazh Khorramshahi,

Zhe Wu,

Tianchen Wang,

Luke DeLuccia,

Hongcheng Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Khorramshahi_2024_WACV, author = {Khorramshahi, Pirazh and Wu, Zhe and Wang, Tianchen and DeLuccia, Luke and Wang, Hongcheng}, title = {Lightweight Delivery Detection on Doorbell Cameras}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6962-6971} }
Designing a Hybrid Neural System To Learn Real-World Crack Segmentation From Fractal-Based Simulation: Achref Jaziri,

Martin Mundt,

Andres Fernandez,

Visvanathan Ramesh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jaziri_2024_WACV, author = {Jaziri, Achref and Mundt, Martin and Fernandez, Andres and Ramesh, Visvanathan}, title = {Designing a Hybrid Neural System To Learn Real-World Crack Segmentation From Fractal-Based Simulation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8636-8646} }
Deep Visual-Genetic Biometrics for Taxonomic Classification of Rare Species: Tayfun Karaderi,

Tilo Burghardt,

Raphaël Morard,

Daniela N. Schmidt; [pdf] [arXiv]
[bibtex]
@InProceedings{Karaderi_2024_WACV, author = {Karaderi, Tayfun and Burghardt, Tilo and Morard, Rapha\"el and Schmidt, Daniela N.}, title = {Deep Visual-Genetic Biometrics for Taxonomic Classification of Rare Species}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7115-7125} }
Handformer2T: A Lightweight Regression-Based Model for Interacting Hands Pose Estimation From a Single RGB Image: Pengfei Zhang,

Deying Kong; [pdf]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Pengfei and Kong, Deying}, title = {Handformer2T: A Lightweight Regression-Based Model for Interacting Hands Pose Estimation From a Single RGB Image}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6248-6257} }
Universal Semi-Supervised Model Adaptation via Collaborative Consistency Training: Zizheng Yan,

Yushuang Wu,

Yipeng Qin,

Xiaoguang Han,

Shuguang Cui,

Guanbin Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yan_2024_WACV, author = {Yan, Zizheng and Wu, Yushuang and Qin, Yipeng and Han, Xiaoguang and Cui, Shuguang and Li, Guanbin}, title = {Universal Semi-Supervised Model Adaptation via Collaborative Consistency Training}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {872-882} }
Universal Test-Time Adaptation Through Weight Ensembling, Diversity Weighting, and Prior Correction: Robert A. Marsden,

Mario Döbler,

Bin Yang; [pdf] [supp]
[bibtex]
@InProceedings{Marsden_2024_WACV, author = {Marsden, Robert A. and D\"obler, Mario and Yang, Bin}, title = {Universal Test-Time Adaptation Through Weight Ensembling, Diversity Weighting, and Prior Correction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2555-2565} }
Uncertainty Estimation in Instance Segmentation With Star-Convex Shapes: Qasim M. K. Siddiqui,

Sebastian Starke,

Peter Steinbach; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Siddiqui_2024_WACV, author = {Siddiqui, Qasim M. K. and Starke, Sebastian and Steinbach, Peter}, title = {Uncertainty Estimation in Instance Segmentation With Star-Convex Shapes}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1424-1433} }
Spatio-Temporal Filter Analysis Improves 3D-CNN for Action Classification: Takumi Kobayashi,

Jiaxing Ye; [pdf] [supp]
[bibtex]
@InProceedings{Kobayashi_2024_WACV, author = {Kobayashi, Takumi and Ye, Jiaxing}, title = {Spatio-Temporal Filter Analysis Improves 3D-CNN for Action Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6972-6981} }
Bipartite Graph Diffusion Model for Human Interaction Generation: Baptiste Chopin,

Hao Tang,

Mohamed Daoudi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chopin_2024_WACV, author = {Chopin, Baptiste and Tang, Hao and Daoudi, Mohamed}, title = {Bipartite Graph Diffusion Model for Human Interaction Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5333-5342} }
Latent Feature-Guided Diffusion Models for Shadow Removal: Kangfu Mei,

Luis Figueroa,

Zhe Lin,

Zhihong Ding,

Scott Cohen,

Vishal M. Patel; [pdf] [arXiv]
[bibtex]
@InProceedings{Mei_2024_WACV, author = {Mei, Kangfu and Figueroa, Luis and Lin, Zhe and Ding, Zhihong and Cohen, Scott and Patel, Vishal M.}, title = {Latent Feature-Guided Diffusion Models for Shadow Removal}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4313-4322} }
HAMMER: Learning Entropy Maps To Create Accurate 3D Models in Multi-View Stereo: Rafael Weilharter,

Friedrich Fraundorfer; [pdf] [supp]
[bibtex]
@InProceedings{Weilharter_2024_WACV, author = {Weilharter, Rafael and Fraundorfer, Friedrich}, title = {HAMMER: Learning Entropy Maps To Create Accurate 3D Models in Multi-View Stereo}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3466-3475} }
Localization and Manipulation of Immoral Visual Cues for Safe Text-to-Image Generation: Seongbeom Park,

Suhong Moon,

Seunghyun Park,

Jinkyu Kim; [pdf] [supp]
[bibtex]
@InProceedings{Park_2024_WACV, author = {Park, Seongbeom and Moon, Suhong and Park, Seunghyun and Kim, Jinkyu}, title = {Localization and Manipulation of Immoral Visual Cues for Safe Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4675-4684} }
Dynamic Token-Pass Transformers for Semantic Segmentation: Yuang Liu,

Qiang Zhou,

Jing Wang,

Zhibin Wang,

Fan Wang,

Jun Wang,

Wei Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Liu_2024_WACV, author = {Liu, Yuang and Zhou, Qiang and Wang, Jing and Wang, Zhibin and Wang, Fan and Wang, Jun and Zhang, Wei}, title = {Dynamic Token-Pass Transformers for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1827-1836} }
MIST: Medical Image Segmentation Transformer With Convolutional Attention Mixing (CAM) Decoder: Md Motiur Rahman,

Shiva Shokouhmand,

Smriti Bhatt,

Miad Faezipour; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rahman_2024_WACV, author = {Rahman, Md Motiur and Shokouhmand, Shiva and Bhatt, Smriti and Faezipour, Miad}, title = {MIST: Medical Image Segmentation Transformer With Convolutional Attention Mixing (CAM) Decoder}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {404-413} }
Active Learning for Single-Stage Object Detection in UAV Images: Asma Yamani,

Albandari Alyami,

Hamzah Luqman,

Bernard Ghanem,

Silvio Giancola; [pdf]
[bibtex]
@InProceedings{Yamani_2024_WACV, author = {Yamani, Asma and Alyami, Albandari and Luqman, Hamzah and Ghanem, Bernard and Giancola, Silvio}, title = {Active Learning for Single-Stage Object Detection in UAV Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1860-1869} }
WaveMixSR: Resource-Efficient Neural Network for Image Super-Resolution: Pranav Jeevan,

Akella Srinidhi,

Pasunuri Prathiba,

Amit Sethi; [pdf]
[bibtex]
@InProceedings{Jeevan_2024_WACV, author = {Jeevan, Pranav and Srinidhi, Akella and Prathiba, Pasunuri and Sethi, Amit}, title = {WaveMixSR: Resource-Efficient Neural Network for Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5884-5892} }
Disentangled Pre-Training for Image Matting: Yanda Li,

Zilong Huang,

Gang Yu,

Ling Chen,

Yunchao Wei,

Jianbo Jiao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_WACV, author = {Li, Yanda and Huang, Zilong and Yu, Gang and Chen, Ling and Wei, Yunchao and Jiao, Jianbo}, title = {Disentangled Pre-Training for Image Matting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {169-178} }
PromptAD: Zero-Shot Anomaly Detection Using Text Prompts: Yiting Li,

Adam Goodge,

Fayao Liu,

Chuan-Sheng Foo; [pdf] [supp]
[bibtex]
@InProceedings{Li_2024_WACV, author = {Li, Yiting and Goodge, Adam and Liu, Fayao and Foo, Chuan-Sheng}, title = {PromptAD: Zero-Shot Anomaly Detection Using Text Prompts}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1093-1102} }
Random Walks for Temporal Action Segmentation With Timestamp Supervision: Roy Hirsch,

Regev Cohen,

Tomer Golany,

Daniel Freedman,

Ehud Rivlin; [pdf] [supp]
[bibtex]
@InProceedings{Hirsch_2024_WACV, author = {Hirsch, Roy and Cohen, Regev and Golany, Tomer and Freedman, Daniel and Rivlin, Ehud}, title = {Random Walks for Temporal Action Segmentation With Timestamp Supervision}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6614-6624} }
Masked Collaborative Contrast for Weakly Supervised Semantic Segmentation: Fangwen Wu,

Jingxuan He,

Yufei Yin,

Yanbin Hao,

Gang Huang,

Lechao Cheng; [pdf] [arXiv]
[bibtex]
@InProceedings{Wu_2024_WACV, author = {Wu, Fangwen and He, Jingxuan and Yin, Yufei and Hao, Yanbin and Huang, Gang and Cheng, Lechao}, title = {Masked Collaborative Contrast for Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {862-871} }
Critical Gap Between Generalization Error and Empirical Error in Active Learning: Yusuke Kanebako; [pdf]
[bibtex]
@InProceedings{Kanebako_2024_WACV, author = {Kanebako, Yusuke}, title = {Critical Gap Between Generalization Error and Empirical Error in Active Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2771-2779} }
Semi-Supervised Scene Change Detection by Distillation From Feature-Metric Alignment: Seonhoon Lee,

Jong-Hwan Kim; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2024_WACV, author = {Lee, Seonhoon and Kim, Jong-Hwan}, title = {Semi-Supervised Scene Change Detection by Distillation From Feature-Metric Alignment}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1226-1235} }
Point-DynRF: Point-Based Dynamic Radiance Fields From a Monocular Video: Byeongjun Park,

Changick Kim; [pdf] [supp]
[bibtex]
@InProceedings{Park_2024_WACV, author = {Park, Byeongjun and Kim, Changick}, title = {Point-DynRF: Point-Based Dynamic Radiance Fields From a Monocular Video}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3171-3181} }
Re-VoxelDet: Rethinking Neck and Head Architectures for High-Performance Voxel-Based 3D Detection: Jae-Keun Lee,

Jin-Hee Lee,

Joohyun Lee,

Soon Kwon,

Heechul Jung; [pdf]
[bibtex]
@InProceedings{Lee_2024_WACV, author = {Lee, Jae-Keun and Lee, Jin-Hee and Lee, Joohyun and Kwon, Soon and Jung, Heechul}, title = {Re-VoxelDet: Rethinking Neck and Head Architectures for High-Performance Voxel-Based 3D Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7503-7512} }
Motion Matters: Neural Motion Transfer for Better Camera Physiological Measurement: Akshay Paruchuri,

Xin Liu,

Yulu Pan,

Shwetak Patel,

Daniel McDuff,

Soumyadip Sengupta; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Paruchuri_2024_WACV, author = {Paruchuri, Akshay and Liu, Xin and Pan, Yulu and Patel, Shwetak and McDuff, Daniel and Sengupta, Soumyadip}, title = {Motion Matters: Neural Motion Transfer for Better Camera Physiological Measurement}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5933-5942} }
Towards Diverse and Consistent Typography Generation: Wataru Shimoda,

Daichi Haraguchi,

Seiichi Uchida,

Kota Yamaguchi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shimoda_2024_WACV, author = {Shimoda, Wataru and Haraguchi, Daichi and Uchida, Seiichi and Yamaguchi, Kota}, title = {Towards Diverse and Consistent Typography Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7296-7305} }
IR-FRestormer: Iterative Refinement With Fourier-Based Restormer for Accelerated MRI Reconstruction: Mohammad Zalbagi Darestani,

Vishwesh Nath,

Wenqi Li,

Yufan He,

Holger R. Roth,

Ziyue Xu,

Daguang Xu,

Reinhard Heckel,

Can Zhao; [pdf]
[bibtex]
@InProceedings{Darestani_2024_WACV, author = {Darestani, Mohammad Zalbagi and Nath, Vishwesh and Li, Wenqi and He, Yufan and Roth, Holger R. and Xu, Ziyue and Xu, Daguang and Heckel, Reinhard and Zhao, Can}, title = {IR-FRestormer: Iterative Refinement With Fourier-Based Restormer for Accelerated MRI Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7655-7664} }
Deep Plug-and-Play Nighttime Non-Blind Deblurring With Saturated Pixel Handling Schemes: Hung-Yu Shu,

Yi-Hsien Lin,

Yi-Chang Lu; [pdf] [supp]
[bibtex]
@InProceedings{Shu_2024_WACV, author = {Shu, Hung-Yu and Lin, Yi-Hsien and Lu, Yi-Chang}, title = {Deep Plug-and-Play Nighttime Non-Blind Deblurring With Saturated Pixel Handling Schemes}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1538-1546} }
One Style Is All You Need To Generate a Video: Sandeep Manandhar,

Auguste Genovesio; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Manandhar_2024_WACV, author = {Manandhar, Sandeep and Genovesio, Auguste}, title = {One Style Is All You Need To Generate a Video}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5038-5047} }
Wino Vidi Vici: Conquering Numerical Instability of 8-Bit Winograd Convolution for Accurate Inference Acceleration on Edge: Pierpaolo Mori,

Lukas Frickenstein,

Shambhavi Balamuthu Sampath,

Moritz Thoma,

Nael Fasfous,

Manoj Rohit Vemparala,

Alexander Frickenstein,

Christian Unger,

Walter Stechele,

Daniel Mueller-Gritschneder,

Claudio Passerone; [pdf] [supp]
[bibtex]
@InProceedings{Mori_2024_WACV, author = {Mori, Pierpaolo and Frickenstein, Lukas and Sampath, Shambhavi Balamuthu and Thoma, Moritz and Fasfous, Nael and Vemparala, Manoj Rohit and Frickenstein, Alexander and Unger, Christian and Stechele, Walter and Mueller-Gritschneder, Daniel and Passerone, Claudio}, title = {Wino Vidi Vici: Conquering Numerical Instability of 8-Bit Winograd Convolution for Accurate Inference Acceleration on Edge}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {53-62} }
Leveraging Bitstream Metadata for Fast, Accurate, Generalized Compressed Video Quality Enhancement: Max Ehrlich,

Jon Barker,

Namitha Padmanabhan,

Larry Davis,

Andrew Tao,

Bryan Catanzaro,

Abhinav Shrivastava; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ehrlich_2024_WACV, author = {Ehrlich, Max and Barker, Jon and Padmanabhan, Namitha and Davis, Larry and Tao, Andrew and Catanzaro, Bryan and Shrivastava, Abhinav}, title = {Leveraging Bitstream Metadata for Fast, Accurate, Generalized Compressed Video Quality Enhancement}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1517-1527} }
ECSIC: Epipolar Cross Attention for Stereo Image Compression: Matthias Wödlinger,

Jan Kotera,

Manuel Keglevic,

Jan Xu,

Robert Sablatnig; [pdf] [supp]
[bibtex]
@InProceedings{Wodlinger_2024_WACV, author = {W\"odlinger, Matthias and Kotera, Jan and Keglevic, Manuel and Xu, Jan and Sablatnig, Robert}, title = {ECSIC: Epipolar Cross Attention for Stereo Image Compression}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3436-3445} }
FacadeNet: Conditional Facade Synthesis via Selective Editing: Yiangos Georgiou,

Marios Loizou,

Tom Kelly,

Melinos Averkiou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Georgiou_2024_WACV, author = {Georgiou, Yiangos and Loizou, Marios and Kelly, Tom and Averkiou, Melinos}, title = {FacadeNet: Conditional Facade Synthesis via Selective Editing}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5384-5393} }
VEATIC: Video-Based Emotion and Affect Tracking in Context Dataset: Zhihang Ren,

Jefferson Ortega,

Yifan Wang,

Zhimin Chen,

Yunhui Guo,

Stella X. Yu,

David Whitney; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ren_2024_WACV, author = {Ren, Zhihang and Ortega, Jefferson and Wang, Yifan and Chen, Zhimin and Guo, Yunhui and Yu, Stella X. and Whitney, David}, title = {VEATIC: Video-Based Emotion and Affect Tracking in Context Dataset}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4467-4477} }
SimpliMix: A Simplified Manifold Mixup for Few-Shot Point Cloud Classification: Minmin Yang,

Weiheng Chai,

Jiyang Wang,

Senem Velipasalar; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2024_WACV, author = {Yang, Minmin and Chai, Weiheng and Wang, Jiyang and Velipasalar, Senem}, title = {SimpliMix: A Simplified Manifold Mixup for Few-Shot Point Cloud Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3668-3677} }
ProxEdit: Improving Tuning-Free Real Image Editing With Proximal Guidance: Ligong Han,

Song Wen,

Qi Chen,

Zhixing Zhang,

Kunpeng Song,

Mengwei Ren,

Ruijiang Gao,

Anastasis Stathopoulos,

Xiaoxiao He,

Yuxiao Chen,

Di Liu,

Qilong Zhangli,

Jindong Jiang,

Zhaoyang Xia,

Akash Srivastava,

Dimitris Metaxas; [pdf] [supp]
[bibtex]
@InProceedings{Han_2024_WACV, author = {Han, Ligong and Wen, Song and Chen, Qi and Zhang, Zhixing and Song, Kunpeng and Ren, Mengwei and Gao, Ruijiang and Stathopoulos, Anastasis and He, Xiaoxiao and Chen, Yuxiao and Liu, Di and Zhangli, Qilong and Jiang, Jindong and Xia, Zhaoyang and Srivastava, Akash and Metaxas, Dimitris}, title = {ProxEdit: Improving Tuning-Free Real Image Editing With Proximal Guidance}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4291-4301} }
Diverse Imagenet Models Transfer Better: Niv Nayman,

Avram Golbert,

Asaf Noy,

Lihi Zelnik-Manor; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nayman_2024_WACV, author = {Nayman, Niv and Golbert, Avram and Noy, Asaf and Zelnik-Manor, Lihi}, title = {Diverse Imagenet Models Transfer Better}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1914-1925} }
SOAP: Cross-Sensor Domain Adaptation for 3D Object Detection Using Stationary Object Aggregation Pseudo-Labelling: Chengjie Huang,

Vahdat Abdelzad,

Sean Sedwards,

Krzysztof Czarnecki; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2024_WACV, author = {Huang, Chengjie and Abdelzad, Vahdat and Sedwards, Sean and Czarnecki, Krzysztof}, title = {SOAP: Cross-Sensor Domain Adaptation for 3D Object Detection Using Stationary Object Aggregation Pseudo-Labelling}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3352-3361} }
Layer-Wise Auto-Weighting for Non-Stationary Test-Time Adaptation: Junyoung Park,

Jin Kim,

Hyeongjun Kwon,

Ilhoon Yoon,

Kwanghoon Sohn; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2024_WACV, author = {Park, Junyoung and Kim, Jin and Kwon, Hyeongjun and Yoon, Ilhoon and Sohn, Kwanghoon}, title = {Layer-Wise Auto-Weighting for Non-Stationary Test-Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1414-1423} }
Improving Fairness Using Vision-Language Driven Image Augmentation: Moreno D'Incà,

Christos Tzelepis,

Ioannis Patras,

Nicu Sebe; [pdf]
[bibtex]
@InProceedings{D'Inca_2024_WACV, author = {D'Inc\`a, Moreno and Tzelepis, Christos and Patras, Ioannis and Sebe, Nicu}, title = {Improving Fairness Using Vision-Language Driven Image Augmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4695-4704} }
SupeRVol: Super-Resolution Shape and Reflectance Estimation in Inverse Volume Rendering: Mohammed Brahimi,

Bjoern Haefner,

Tarun Yenamandra,

Bastian Goldluecke,

Daniel Cremers; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Brahimi_2024_WACV, author = {Brahimi, Mohammed and Haefner, Bjoern and Yenamandra, Tarun and Goldluecke, Bastian and Cremers, Daniel}, title = {SupeRVol: Super-Resolution Shape and Reflectance Estimation in Inverse Volume Rendering}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3139-3149} }
Object Aware Contrastive Prior for Interactive Image Segmentation: Praful Mathur,

Shashi Kumar Parwani,

Mrinmoy Sen,

Roopa Sheshadri,

Aman Sharma; [pdf] [supp]
[bibtex]
@InProceedings{Mathur_2024_WACV, author = {Mathur, Praful and Parwani, Shashi Kumar and Sen, Mrinmoy and Sheshadri, Roopa and Sharma, Aman}, title = {Object Aware Contrastive Prior for Interactive Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {575-584} }
Torque Based Structured Pruning for Deep Neural Network: Arshita Gupta,

Tien Bau,

Joonsoo Kim,

Zhe Zhu,

Sumit Jha,

Hrishikesh Garud; [pdf] [supp]
[bibtex]
@InProceedings{Gupta_2024_WACV, author = {Gupta, Arshita and Bau, Tien and Kim, Joonsoo and Zhu, Zhe and Jha, Sumit and Garud, Hrishikesh}, title = {Torque Based Structured Pruning for Deep Neural Network}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2711-2720} }
Instruct Me More! Random Prompting for Visual In-Context Learning: Jiahao Zhang,

Bowen Wang,

Liangzhi Li,

Yuta Nakashima,

Hajime Nagahara; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Jiahao and Wang, Bowen and Li, Liangzhi and Nakashima, Yuta and Nagahara, Hajime}, title = {Instruct Me More! Random Prompting for Visual In-Context Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2597-2606} }
CL-MAE: Curriculum-Learned Masked Autoencoders: Neelu Madan,

Nicolae-Cătălin Ristea,

Kamal Nasrollahi,

Thomas B. Moeslund,

Radu Tudor Ionescu; [pdf] [supp]
[bibtex]
@InProceedings{Madan_2024_WACV, author = {Madan, Neelu and Ristea, Nicolae-C\u{a}t\u{a}lin and Nasrollahi, Kamal and Moeslund, Thomas B. and Ionescu, Radu Tudor}, title = {CL-MAE: Curriculum-Learned Masked Autoencoders}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2492-2502} }
Think Before You Simulate: Symbolic Reasoning To Orchestrate Neural Computation for Counterfactual Question Answering: Adam Ishay,

Zhun Yang,

Joohyung Lee,

Ilgu Kang,

Dongjae Lim; [pdf] [supp]
[bibtex]
@InProceedings{Ishay_2024_WACV, author = {Ishay, Adam and Yang, Zhun and Lee, Joohyung and Kang, Ilgu and Lim, Dongjae}, title = {Think Before You Simulate: Symbolic Reasoning To Orchestrate Neural Computation for Counterfactual Question Answering}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6698-6707} }
Robust Object Detection in Challenging Weather Conditions: Himanshu Gupta,

Oleksandr Kotlyar,

Henrik Andreasson,

Achim J. Lilienthal; [pdf]
[bibtex]
@InProceedings{Gupta_2024_WACV, author = {Gupta, Himanshu and Kotlyar, Oleksandr and Andreasson, Henrik and Lilienthal, Achim J.}, title = {Robust Object Detection in Challenging Weather Conditions}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7523-7532} }
DiffBody: Diffusion-Based Pose and Shape Editing of Human Images: Yuta Okuyama,

Yuki Endo,

Yoshihiro Kanamori; [pdf] [supp]
[bibtex]
@InProceedings{Okuyama_2024_WACV, author = {Okuyama, Yuta and Endo, Yuki and Kanamori, Yoshihiro}, title = {DiffBody: Diffusion-Based Pose and Shape Editing of Human Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6333-6342} }
Sound3DVDet: 3D Sound Source Detection Using Multiview Microphone Array and RGB Images: Yuhang He,

Sangyun Shin,

Anoop Cherian,

Niki Trigoni,

Andrew Markham; [pdf] [supp]
[bibtex]
@InProceedings{He_2024_WACV, author = {He, Yuhang and Shin, Sangyun and Cherian, Anoop and Trigoni, Niki and Markham, Andrew}, title = {Sound3DVDet: 3D Sound Source Detection Using Multiview Microphone Array and RGB Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5496-5507} }
Annotation-Free Audio-Visual Segmentation: Jinxiang Liu,

Yu Wang,

Chen Ju,

Chaofan Ma,

Ya Zhang,

Weidi Xie; [pdf] [arXiv]
[bibtex]
@InProceedings{Liu_2024_WACV, author = {Liu, Jinxiang and Wang, Yu and Ju, Chen and Ma, Chaofan and Zhang, Ya and Xie, Weidi}, title = {Annotation-Free Audio-Visual Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5604-5614} }
SC-MIL: Supervised Contrastive Multiple Instance Learning for Imbalanced Classification in Pathology: Dinkar Juyal,

Siddhant Shingi,

Syed Ashar Javed,

Harshith Padigela,

Chintan Shah,

Anand Sampat,

Archit Khosla,

John Abel,

Amaro Taylor-Weiner; [pdf]
[bibtex]
@InProceedings{Juyal_2024_WACV, author = {Juyal, Dinkar and Shingi, Siddhant and Javed, Syed Ashar and Padigela, Harshith and Shah, Chintan and Sampat, Anand and Khosla, Archit and Abel, John and Taylor-Weiner, Amaro}, title = {SC-MIL: Supervised Contrastive Multiple Instance Learning for Imbalanced Classification in Pathology}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7946-7955} }
MetaSeg: MetaFormer-Based Global Contexts-Aware Network for Efficient Semantic Segmentation: Beoungwoo Kang,

Seunghun Moon,

Yubin Cho,

Hyunwoo Yu,

Suk-Ju Kang; [pdf] [supp]
[bibtex]
@InProceedings{Kang_2024_WACV, author = {Kang, Beoungwoo and Moon, Seunghun and Cho, Yubin and Yu, Hyunwoo and Kang, Suk-Ju}, title = {MetaSeg: MetaFormer-Based Global Contexts-Aware Network for Efficient Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {434-443} }
JOADAA: Joint Online Action Detection and Action Anticipation: Mohammed Guermal,

Abid Ali,

Rui Dai,

François Brémond; [pdf] [arXiv]
[bibtex]
@InProceedings{Guermal_2024_WACV, author = {Guermal, Mohammed and Ali, Abid and Dai, Rui and Br\'emond, Fran\c{c}ois}, title = {JOADAA: Joint Online Action Detection and Action Anticipation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6889-6898} }
Denoising and Selecting Pseudo-Heatmaps for Semi-Supervised Human Pose Estimation: Zhuoran Yu,

Manchen Wang,

Yanbei Chen,

Paolo Favaro,

Davide Modolo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2024_WACV, author = {Yu, Zhuoran and Wang, Manchen and Chen, Yanbei and Favaro, Paolo and Modolo, Davide}, title = {Denoising and Selecting Pseudo-Heatmaps for Semi-Supervised Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6280-6289} }
CSAM: A 2.5D Cross-Slice Attention Module for Anisotropic Volumetric Medical Image Segmentation: Alex Ling Yu Hung,

Haoxin Zheng,

Kai Zhao,

Xiaoxi Du,

Kaifeng Pang,

Qi Miao,

Steven S. Raman,

Demetri Terzopoulos,

Kyunghyun Sung; [pdf]
[bibtex]
@InProceedings{Hung_2024_WACV, author = {Hung, Alex Ling Yu and Zheng, Haoxin and Zhao, Kai and Du, Xiaoxi and Pang, Kaifeng and Miao, Qi and Raman, Steven S. and Terzopoulos, Demetri and Sung, Kyunghyun}, title = {CSAM: A 2.5D Cross-Slice Attention Module for Anisotropic Volumetric Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5923-5932} }
Segment Anything, From Space?: Simiao Ren,

Francesco Luzi,

Saad Lahrichi,

Kaleb Kassaw,

Leslie M. Collins,

Kyle Bradbury,

Jordan M. Malof; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ren_2024_WACV, author = {Ren, Simiao and Luzi, Francesco and Lahrichi, Saad and Kassaw, Kaleb and Collins, Leslie M. and Bradbury, Kyle and Malof, Jordan M.}, title = {Segment Anything, From Space?}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8355-8365} }
UOW-Vessel: A Benchmark Dataset of High-Resolution Optical Satellite Images for Vessel Detection and Segmentation: Ly Bui,

Son Lam Phung,

Yang Di,

Thanh Le,

Tran Thanh Phong Nguyen,

Sandy Burden,

Abdesselam Bouzerdoum; [pdf]
[bibtex]
@InProceedings{Bui_2024_WACV, author = {Bui, Ly and Phung, Son Lam and Di, Yang and Le, Thanh and Nguyen, Tran Thanh Phong and Burden, Sandy and Bouzerdoum, Abdesselam}, title = {UOW-Vessel: A Benchmark Dataset of High-Resolution Optical Satellite Images for Vessel Detection and Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4428-4436} }
Single Frame Semantic Segmentation Using Multi-Modal Spherical Images: Suresh Guttikonda,

Jason Rambach; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guttikonda_2024_WACV, author = {Guttikonda, Suresh and Rambach, Jason}, title = {Single Frame Semantic Segmentation Using Multi-Modal Spherical Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3222-3231} }
SynthProv: Interpretable Framework for Profiling Identity Leakage: Jaisidh Singh,

Harshil Bhatia,

Mayank Vatsa,

Richa Singh,

Aparna Bharati; [pdf] [supp]
[bibtex]
@InProceedings{Singh_2024_WACV, author = {Singh, Jaisidh and Bhatia, Harshil and Vatsa, Mayank and Singh, Richa and Bharati, Aparna}, title = {SynthProv: Interpretable Framework for Profiling Identity Leakage}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4746-4756} }
Discovering and Mitigating Biases in CLIP-Based Image Editing: Md Mehrab Tanjim,

Krishna Kumar Singh,

Kushal Kafle,

Ritwik Sinha,

Garrison W. Cottrell; [pdf] [supp]
[bibtex]
@InProceedings{Tanjim_2024_WACV, author = {Tanjim, Md Mehrab and Singh, Krishna Kumar and Kafle, Kushal and Sinha, Ritwik and Cottrell, Garrison W.}, title = {Discovering and Mitigating Biases in CLIP-Based Image Editing}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2984-2993} }
Repetitive Action Counting With Motion Feature Learning: Xinjie Li,

Huijuan Xu; [pdf] [supp]
[bibtex]
@InProceedings{Li_2024_WACV, author = {Li, Xinjie and Xu, Huijuan}, title = {Repetitive Action Counting With Motion Feature Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6499-6508} }
Deep Image Fingerprint: Towards Low Budget Synthetic Image Detection and Model Lineage Analysis: Sergey Sinitsa,

Ohad Fried; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sinitsa_2024_WACV, author = {Sinitsa, Sergey and Fried, Ohad}, title = {Deep Image Fingerprint: Towards Low Budget Synthetic Image Detection and Model Lineage Analysis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4067-4076} }
HALSIE: Hybrid Approach to Learning Segmentation by Simultaneously Exploiting Image and Event Modalities: Shristi Das Biswas,

Adarsh Kosta,

Chamika Liyanagedera,

Marco Apolinario,

Kaushik Roy; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Das_Biswas_2024_WACV, author = {Das Biswas, Shristi and Kosta, Adarsh and Liyanagedera, Chamika and Apolinario, Marco and Roy, Kaushik}, title = {HALSIE: Hybrid Approach to Learning Segmentation by Simultaneously Exploiting Image and Event Modalities}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5964-5974} }
Hierarchical Diffusion Autoencoders and Disentangled Image Manipulation: Zeyu Lu,

Chengyue Wu,

Xinyuan Chen,

Yaohui Wang,

Lei Bai,

Yu Qiao,

Xihui Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lu_2024_WACV, author = {Lu, Zeyu and Wu, Chengyue and Chen, Xinyuan and Wang, Yaohui and Bai, Lei and Qiao, Yu and Liu, Xihui}, title = {Hierarchical Diffusion Autoencoders and Disentangled Image Manipulation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5374-5383} }
Improved Topological Preservation in 3D Axon Segmentation and Centerline Detection Using Geometric Assessment-Driven Topological Smoothing (GATS): Nina I. Shamsi,

Alec S. Xu,

Lars A. Gjesteby,

Laura J. Brattain; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shamsi_2024_WACV, author = {Shamsi, Nina I. and Xu, Alec S. and Gjesteby, Lars A. and Brattain, Laura J.}, title = {Improved Topological Preservation in 3D Axon Segmentation and Centerline Detection Using Geometric Assessment-Driven Topological Smoothing (GATS)}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8005-8014} }
CycleCL: Self-Supervised Learning for Periodic Videos: Matteo Destro,

Michael Gygli; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Destro_2024_WACV, author = {Destro, Matteo and Gygli, Michael}, title = {CycleCL: Self-Supervised Learning for Periodic Videos}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2861-2870} }
DR10K: Transfer Learning Using Weak Labels for Grading Diabetic Retinopathy on DR10K Dataset: Mohamed ElHabebe,

Shereen ElKordi,

Ahmed Gamal ElDin,

Noha Adly,

Marwan Torki,

Ahmed Elmassry,

Islam SH Ahmed; [pdf] [supp]
[bibtex]
@InProceedings{ElHabebe_2024_WACV, author = {ElHabebe, Mohamed and ElKordi, Shereen and ElDin, Ahmed Gamal and Adly, Noha and Torki, Marwan and Elmassry, Ahmed and Ahmed, Islam SH}, title = {DR10K: Transfer Learning Using Weak Labels for Grading Diabetic Retinopathy on DR10K Dataset}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7748-7758} }
Open-NeRF: Towards Open Vocabulary NeRF Decomposition: Hao Zhang,

Fang Li,

Narendra Ahuja; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Hao and Li, Fang and Ahuja, Narendra}, title = {Open-NeRF: Towards Open Vocabulary NeRF Decomposition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3456-3465} }
Exploiting the Signal-Leak Bias in Diffusion Models: Martin Nicolas Everaert,

Athanasios Fitsios,

Marco Bocchio,

Sami Arpa,

Sabine Süsstrunk,

Radhakrishna Achanta; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Everaert_2024_WACV, author = {Everaert, Martin Nicolas and Fitsios, Athanasios and Bocchio, Marco and Arpa, Sami and S\"usstrunk, Sabine and Achanta, Radhakrishna}, title = {Exploiting the Signal-Leak Bias in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4025-4034} }
Weakly-Supervised Representation Learning for Video Alignment and Analysis: Guy Bar-Shalom,

George Leifman,

Michael Elad; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bar-Shalom_2024_WACV, author = {Bar-Shalom, Guy and Leifman, George and Elad, Michael}, title = {Weakly-Supervised Representation Learning for Video Alignment and Analysis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6909-6919} }
NCIS: Neural Contextual Iterative Smoothing for Purifying Adversarial Perturbations: Sungmin Cha,

Naeun Ko,

Heewoong Choi,

Youngjoon Yoo,

Taesup Moon; [pdf] [supp]
[bibtex]
@InProceedings{Cha_2024_WACV, author = {Cha, Sungmin and Ko, Naeun and Choi, Heewoong and Yoo, Youngjoon and Moon, Taesup}, title = {NCIS: Neural Contextual Iterative Smoothing for Purifying Adversarial Perturbations}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3789-3799} }
D3GU: Multi-Target Active Domain Adaptation via Enhancing Domain Alignment: Lin Zhang,

Linghan Xu,

Saman Motamed,

Shayok Chakraborty,

Fernando De la Torre; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Lin and Xu, Linghan and Motamed, Saman and Chakraborty, Shayok and De la Torre, Fernando}, title = {D3GU: Multi-Target Active Domain Adaptation via Enhancing Domain Alignment}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2577-2586} }
Fixed Pattern Noise Removal for Multi-View Single-Sensor Infrared Camera: Arnaud Barral,

Pablo Arias,

Axel Davy; [pdf] [supp]
[bibtex]
@InProceedings{Barral_2024_WACV, author = {Barral, Arnaud and Arias, Pablo and Davy, Axel}, title = {Fixed Pattern Noise Removal for Multi-View Single-Sensor Infrared Camera}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1669-1678} }
Painterly Image Harmonization via Adversarial Residual Learning: Xudong Wang,

Li Niu,

Junyan Cao,

Yan Hong,

Liqing Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_WACV, author = {Wang, Xudong and Niu, Li and Cao, Junyan and Hong, Yan and Zhang, Liqing}, title = {Painterly Image Harmonization via Adversarial Residual Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5141-5150} }
CoD: Coherent Detection of Entities From Images With Multiple Modalities: Vinay Verma,

Dween Sanny,

Abhishek Singh,

Deepak Gupta; [pdf] [supp]
[bibtex]
@InProceedings{Verma_2024_WACV, author = {Verma, Vinay and Sanny, Dween and Singh, Abhishek and Gupta, Deepak}, title = {CoD: Coherent Detection of Entities From Images With Multiple Modalities}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8015-8024} }
Improving Graph Networks Through Selection-Based Convolution: David Hart,

Bryan Morse; [pdf] [supp]
[bibtex]
@InProceedings{Hart_2024_WACV, author = {Hart, David and Morse, Bryan}, title = {Improving Graph Networks Through Selection-Based Convolution}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1794-1804} }
Beyond Fusion: Modality Hallucination-Based Multispectral Fusion for Pedestrian Detection: Qian Xie,

Ta-Ying Cheng,

Jia-Xing Zhong,

Kaichen Zhou,

Andrew Markham,

Niki Trigoni; [pdf]
[bibtex]
@InProceedings{Xie_2024_WACV, author = {Xie, Qian and Cheng, Ta-Ying and Zhong, Jia-Xing and Zhou, Kaichen and Markham, Andrew and Trigoni, Niki}, title = {Beyond Fusion: Modality Hallucination-Based Multispectral Fusion for Pedestrian Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {655-664} }
BSRAW: Improving Blind RAW Image Super-Resolution: Marcos V. Conde,

Florin Vasluianu,

Radu Timofte; [pdf]
[bibtex]
@InProceedings{Conde_2024_WACV, author = {Conde, Marcos V. and Vasluianu, Florin and Timofte, Radu}, title = {BSRAW: Improving Blind RAW Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8500-8510} }
SICKLE: A Multi-Sensor Satellite Imagery Dataset Annotated With Multiple Key Cropping Parameters: Depanshu Sani,

Sandeep Mahato,

Sourabh Saini,

Harsh Kumar Agarwal,

Charu Chandra Devshali,

Saket Anand,

Gaurav Arora,

Thiagarajan Jayaraman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sani_2024_WACV, author = {Sani, Depanshu and Mahato, Sandeep and Saini, Sourabh and Agarwal, Harsh Kumar and Devshali, Charu Chandra and Anand, Saket and Arora, Gaurav and Jayaraman, Thiagarajan}, title = {SICKLE: A Multi-Sensor Satellite Imagery Dataset Annotated With Multiple Key Cropping Parameters}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5995-6004} }
LatentPaint: Image Inpainting in Latent Space With Diffusion Models: Ciprian Corneanu,

Raghudeep Gadde,

Aleix M. Martinez; [pdf]
[bibtex]
@InProceedings{Corneanu_2024_WACV, author = {Corneanu, Ciprian and Gadde, Raghudeep and Martinez, Aleix M.}, title = {LatentPaint: Image Inpainting in Latent Space With Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4334-4343} }
Efficient Semantic Matching With Hypercolumn Correlation: Seungwook Kim,

Juhong Min,

Minsu Cho; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2024_WACV, author = {Kim, Seungwook and Min, Juhong and Cho, Minsu}, title = {Efficient Semantic Matching With Hypercolumn Correlation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {139-148} }
OptFlow: Fast Optimization-Based Scene Flow Estimation Without Supervision: Rahul Ahuja,

Chris Baker,

Wilko Schwarting; [pdf] [supp]
[bibtex]
@InProceedings{Ahuja_2024_WACV, author = {Ahuja, Rahul and Baker, Chris and Schwarting, Wilko}, title = {OptFlow: Fast Optimization-Based Scene Flow Estimation Without Supervision}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3161-3170} }
HashReID: Dynamic Network With Binary Codes for Efficient Person Re-Identification: Kshitij Nikhal,

Yujunrong Ma,

Shuvra S. Bhattacharyya,

Benjamin S. Riggan; [pdf] [arXiv]
[bibtex]
@InProceedings{Nikhal_2024_WACV, author = {Nikhal, Kshitij and Ma, Yujunrong and Bhattacharyya, Shuvra S. and Riggan, Benjamin S.}, title = {HashReID: Dynamic Network With Binary Codes for Efficient Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6046-6055} }
Conditional Velocity Score Estimation for Image Restoration: Ziqiang Shi,

Rujie Liu; [pdf] [supp]
[bibtex]
@InProceedings{Shi_2024_WACV, author = {Shi, Ziqiang and Liu, Rujie}, title = {Conditional Velocity Score Estimation for Image Restoration}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {179-188} }
Stochastic Binary Network for Universal Domain Adaptation: Saurabh Kumar Jain,

Sukhendu Das; [pdf] [supp]
[bibtex]
@InProceedings{Jain_2024_WACV, author = {Jain, Saurabh Kumar and Das, Sukhendu}, title = {Stochastic Binary Network for Universal Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {107-116} }
FG-Net: Facial Action Unit Detection With Generalizable Pyramidal Features: Yufeng Yin,

Di Chang,

Guoxian Song,

Shen Sang,

Tiancheng Zhi,

Jing Liu,

Linjie Luo,

Mohammad Soleymani; [pdf] [supp]
[bibtex]
@InProceedings{Yin_2024_WACV, author = {Yin, Yufeng and Chang, Di and Song, Guoxian and Sang, Shen and Zhi, Tiancheng and Liu, Jing and Luo, Linjie and Soleymani, Mohammad}, title = {FG-Net: Facial Action Unit Detection With Generalizable Pyramidal Features}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6099-6108} }
Complex Organ Mask Guided Radiology Report Generation: Tiancheng Gu,

Dongnan Liu,

Zhiyuan Li,

Weidong Cai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gu_2024_WACV, author = {Gu, Tiancheng and Liu, Dongnan and Li, Zhiyuan and Cai, Weidong}, title = {Complex Organ Mask Guided Radiology Report Generation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7995-8004} }
Link Prediction for Flow-Driven Spatial Networks: Bastian Wittmann,

Johannes C. Paetzold,

Chinmay Prabhakar,

Daniel Rueckert,

Bjoern Menze; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wittmann_2024_WACV, author = {Wittmann, Bastian and Paetzold, Johannes C. and Prabhakar, Chinmay and Rueckert, Daniel and Menze, Bjoern}, title = {Link Prediction for Flow-Driven Spatial Networks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2472-2481} }
Training-Free Object Counting With Prompts: Zenglin Shi,

Ying Sun,

Mengmi Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Shi_2024_WACV, author = {Shi, Zenglin and Sun, Ying and Zhang, Mengmi}, title = {Training-Free Object Counting With Prompts}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {323-331} }
SEMA: Semantic Attention for Capturing Long-Range Dependencies in Egocentric Lifelogs: Pravin Nagar,

K.N. Ajay Shastry,

Jayesh Chaudhari,

Chetan Arora; [pdf] [supp]
[bibtex]
@InProceedings{Nagar_2024_WACV, author = {Nagar, Pravin and Shastry, K.N. Ajay and Chaudhari, Jayesh and Arora, Chetan}, title = {SEMA: Semantic Attention for Capturing Long-Range Dependencies in Egocentric Lifelogs}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7025-7035} }
Neural Image Compression Using Masked Sparse Visual Representation: Wei Jiang,

Wei Wang,

Yue Chen; [pdf] [arXiv]
[bibtex]
@InProceedings{Jiang_2024_WACV, author = {Jiang, Wei and Wang, Wei and Chen, Yue}, title = {Neural Image Compression Using Masked Sparse Visual Representation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4189-4197} }
Letting 3D Guide the Way: 3D Guided 2D Few-Shot Image Classification: Jiajing Chen,

Minmin Yang,

Senem Velipasalar; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2024_WACV, author = {Chen, Jiajing and Yang, Minmin and Velipasalar, Senem}, title = {Letting 3D Guide the Way: 3D Guided 2D Few-Shot Image Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2732-2740} }
Specular Object Reconstruction Behind Frosted Glass by Differentiable Rendering: Takafumi Iwaguchi,

Hiroyuki Kubo,

Hiroshi Kawasaki; [pdf]
[bibtex]
@InProceedings{Iwaguchi_2024_WACV, author = {Iwaguchi, Takafumi and Kubo, Hiroyuki and Kawasaki, Hiroshi}, title = {Specular Object Reconstruction Behind Frosted Glass by Differentiable Rendering}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4047-4056} }
Debiasing, Calibrating, and Improving Semi-Supervised Learning Performance via Simple Ensemble Projector: Khanh-Binh Nguyen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nguyen_2024_WACV, author = {Nguyen, Khanh-Binh}, title = {Debiasing, Calibrating, and Improving Semi-Supervised Learning Performance via Simple Ensemble Projector}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2441-2451} }
Privacy-Enhancing Person Re-Identification Framework - A Dual-Stage Approach: Kajal Kansal,

Yongkang Wong,

Mohan Kankanhalli; [pdf]
[bibtex]
@InProceedings{Kansal_2024_WACV, author = {Kansal, Kajal and Wong, Yongkang and Kankanhalli, Mohan}, title = {Privacy-Enhancing Person Re-Identification Framework - A Dual-Stage Approach}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8543-8552} }
Detection Defenses: An Empty Promise Against Adversarial Patch Attacks on Optical Flow: Erik Scheurer,

Jenny Schmalfuss,

Alexander Lis,

Andrés Bruhn; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Scheurer_2024_WACV, author = {Scheurer, Erik and Schmalfuss, Jenny and Lis, Alexander and Bruhn, Andr\'es}, title = {Detection Defenses: An Empty Promise Against Adversarial Patch Attacks on Optical Flow}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6489-6498} }
SAM Fewshot Finetuning for Anatomical Segmentation in Medical Images: Weiyi Xie,

Nathalie Willems,

Shubham Patil,

Yang Li,

Mayank Kumar; [pdf] [supp]
[bibtex]
@InProceedings{Xie_2024_WACV, author = {Xie, Weiyi and Willems, Nathalie and Patil, Shubham and Li, Yang and Kumar, Mayank}, title = {SAM Fewshot Finetuning for Anatomical Segmentation in Medical Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3253-3261} }
BirdSAT: Cross-View Contrastive Masked Autoencoders for Bird Species Classification and Mapping: Srikumar Sastry,

Subash Khanal,

Aayush Dhakal,

Di Huang,

Nathan Jacobs; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sastry_2024_WACV, author = {Sastry, Srikumar and Khanal, Subash and Dhakal, Aayush and Huang, Di and Jacobs, Nathan}, title = {BirdSAT: Cross-View Contrastive Masked Autoencoders for Bird Species Classification and Mapping}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7136-7145} }
FELGA: Unsupervised Fragment Embedding for Fine-Grained Cross-Modal Association: Yaoxin Zhuo,

Baoxin Li; [pdf]
[bibtex]
@InProceedings{Zhuo_2024_WACV, author = {Zhuo, Yaoxin and Li, Baoxin}, title = {FELGA: Unsupervised Fragment Embedding for Fine-Grained Cross-Modal Association}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5635-5645} }
Weakly-Supervised Deepfake Localization in Diffusion-Generated Images: Dragoș-Constantin Țânțaru,

Elisabeta Oneață,

Dan Oneață; [pdf] [supp]
[bibtex]
@InProceedings{Tantaru_2024_WACV, author = {Ț\^anțaru, Dragoș-Constantin and Oneaț\u{a}, Elisabeta and Oneaț\u{a}, Dan}, title = {Weakly-Supervised Deepfake Localization in Diffusion-Generated Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6258-6268} }
Sketch-Based Video Object Localization: Sangmin Woo,

So-Yeong Jeon,

Jinyoung Park,

Minji Son,

Sumin Lee,

Changick Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Woo_2024_WACV, author = {Woo, Sangmin and Jeon, So-Yeong and Park, Jinyoung and Son, Minji and Lee, Sumin and Kim, Changick}, title = {Sketch-Based Video Object Localization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8480-8489} }
Hyperbolic vs Euclidean Embeddings in Few-Shot Learning: Two Sides of the Same Coin: Gabriel Moreira,

Manuel Marques,

João Paulo Costeira,

Alexander Hauptmann; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Moreira_2024_WACV, author = {Moreira, Gabriel and Marques, Manuel and Costeira, Jo\~ao Paulo and Hauptmann, Alexander}, title = {Hyperbolic vs Euclidean Embeddings in Few-Shot Learning: Two Sides of the Same Coin}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2082-2090} }
Attention-Guided Prototype Mixing: Diversifying Minority Context on Imbalanced Whole Slide Images Classification Learning: Farchan Hakim Raswa,

Chun-Shien Lu,

Jia-Ching Wang; [pdf] [supp]
[bibtex]
@InProceedings{Raswa_2024_WACV, author = {Raswa, Farchan Hakim and Lu, Chun-Shien and Wang, Jia-Ching}, title = {Attention-Guided Prototype Mixing: Diversifying Minority Context on Imbalanced Whole Slide Images Classification Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7624-7633} }
StyleAvatar: Stylizing Animatable Head Avatars: Juan C. Pérez,

Thu Nguyen-Phuoc,

Chen Cao,

Artsiom Sanakoyeu,

Tomas Simon,

Pablo Arbeláez,

Bernard Ghanem,

Ali Thabet,

Albert Pumarola; [pdf]
[bibtex]
@InProceedings{Perez_2024_WACV, author = {P\'erez, Juan C. and Nguyen-Phuoc, Thu and Cao, Chen and Sanakoyeu, Artsiom and Simon, Tomas and Arbel\'aez, Pablo and Ghanem, Bernard and Thabet, Ali and Pumarola, Albert}, title = {StyleAvatar: Stylizing Animatable Head Avatars}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8678-8687} }
On the Quantification of Image Reconstruction Uncertainty Without Training Data: Jiaxin Zhang,

Sirui Bi,

Victor Fung; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Jiaxin and Bi, Sirui and Fung, Victor}, title = {On the Quantification of Image Reconstruction Uncertainty Without Training Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2072-2081} }
Sparse Convolutional Networks for Surface Reconstruction From Noisy Point Clouds: Tao Wang,

Jing Wu,

Ze Ji,

Yu-Kun Lai; [pdf]
[bibtex]
@InProceedings{Wang_2024_WACV, author = {Wang, Tao and Wu, Jing and Ji, Ze and Lai, Yu-Kun}, title = {Sparse Convolutional Networks for Surface Reconstruction From Noisy Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3212-3221} }
Self-Sampling Meta SAM: Enhancing Few-Shot Medical Image Segmentation With Meta-Learning: Tianang Leng,

Yiming Zhang,

Kun Han,

Xiaohui Xie; [pdf] [arXiv]
[bibtex]
@InProceedings{Leng_2024_WACV, author = {Leng, Tianang and Zhang, Yiming and Han, Kun and Xie, Xiaohui}, title = {Self-Sampling Meta SAM: Enhancing Few-Shot Medical Image Segmentation With Meta-Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7925-7935} }
LIVENet: A Novel Network for Real-World Low-Light Image Denoising and Enhancement: Dhruv Makwana,

Gayatri Deshmukh,

Onkar Susladkar,

Sparsh Mittal,

Sai Chandra Teja R.; [pdf] [supp]
[bibtex]
@InProceedings{Makwana_2024_WACV, author = {Makwana, Dhruv and Deshmukh, Gayatri and Susladkar, Onkar and Mittal, Sparsh and R., Sai Chandra Teja}, title = {LIVENet: A Novel Network for Real-World Low-Light Image Denoising and Enhancement}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5856-5865} }
Holistic Representation Learning for Multitask Trajectory Anomaly Detection: Alexandros Stergiou,

Brent De Weerdt,

Nikos Deligiannis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Stergiou_2024_WACV, author = {Stergiou, Alexandros and De Weerdt, Brent and Deligiannis, Nikos}, title = {Holistic Representation Learning for Multitask Trajectory Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6729-6739} }
Text-Guided Face Recognition Using Multi-Granularity Cross-Modal Contrastive Learning: Md Mahedi Hasan,

Shoaib Meraj Sami,

Nasser Nasrabadi; [pdf] [arXiv]
[bibtex]
@InProceedings{Hasan_2024_WACV, author = {Hasan, Md Mahedi and Sami, Shoaib Meraj and Nasrabadi, Nasser}, title = {Text-Guided Face Recognition Using Multi-Granularity Cross-Modal Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5784-5793} }
Computer Vision on the Edge: Individual Cattle Identification in Real-Time With ReadMyCow System: Moniek Smink,

Haotian Liu,

Dörte Döpfer,

Yong Jae Lee; [pdf]
[bibtex]
@InProceedings{Smink_2024_WACV, author = {Smink, Moniek and Liu, Haotian and D\"opfer, D\"orte and Lee, Yong Jae}, title = {Computer Vision on the Edge: Individual Cattle Identification in Real-Time With ReadMyCow System}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7056-7065} }
SynergyNet: Bridging the Gap Between Discrete and Continuous Representations for Precise Medical Image Segmentation: Vandan Gorade,

Sparsh Mittal,

Debesh Jha,

Ulas Bagci; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gorade_2024_WACV, author = {Gorade, Vandan and Mittal, Sparsh and Jha, Debesh and Bagci, Ulas}, title = {SynergyNet: Bridging the Gap Between Discrete and Continuous Representations for Precise Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7768-7777} }
Rethinking Visibility in Human Pose Estimation: Occluded Pose Reasoning via Transformers: Pengzhan Sun,

Kerui Gu,

Yunsong Wang,

Linlin Yang,

Angela Yao; [pdf]
[bibtex]
@InProceedings{Sun_2024_WACV, author = {Sun, Pengzhan and Gu, Kerui and Wang, Yunsong and Yang, Linlin and Yao, Angela}, title = {Rethinking Visibility in Human Pose Estimation: Occluded Pose Reasoning via Transformers}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5903-5912} }
CCMR: High Resolution Optical Flow Estimation via Coarse-To-Fine Context-Guided Motion Reasoning: Azin Jahedi,

Maximilian Luz,

Marc Rivinius,

Andrés Bruhn; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jahedi_2024_WACV, author = {Jahedi, Azin and Luz, Maximilian and Rivinius, Marc and Bruhn, Andr\'es}, title = {CCMR: High Resolution Optical Flow Estimation via Coarse-To-Fine Context-Guided Motion Reasoning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6899-6908} }
ReConPatch: Contrastive Patch Representation Learning for Industrial Anomaly Detection: Jeeho Hyun,

Sangyun Kim,

Giyoung Jeon,

Seung Hwan Kim,

Kyunghoon Bae,

Byung Jun Kang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hyun_2024_WACV, author = {Hyun, Jeeho and Kim, Sangyun and Jeon, Giyoung and Kim, Seung Hwan and Bae, Kyunghoon and Kang, Byung Jun}, title = {ReConPatch: Contrastive Patch Representation Learning for Industrial Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2052-2061} }
Are Natural Domain Foundation Models Useful for Medical Image Classification?: Joana Palés Huix,

Adithya Raju Ganeshan,

Johan Fredin Haslum,

Magnus Söderberg,

Christos Matsoukas,

Kevin Smith; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huix_2024_WACV, author = {Huix, Joana Pal\'es and Ganeshan, Adithya Raju and Haslum, Johan Fredin and S\"oderberg, Magnus and Matsoukas, Christos and Smith, Kevin}, title = {Are Natural Domain Foundation Models Useful for Medical Image Classification?}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7634-7643} }
Favoring One Among Equals - Not a Good Idea: Many-to-One Matching for Robust Transformer Based Pedestrian Detection: K.N. Ajay Shastry,

K. Ravi Sri Teja,

Aditya Nigam,

Chetan Arora; [pdf] [supp]
[bibtex]
@InProceedings{Shastry_2024_WACV, author = {Shastry, K.N. Ajay and Teja, K. Ravi Sri and Nigam, Aditya and Arora, Chetan}, title = {Favoring One Among Equals - Not a Good Idea: Many-to-One Matching for Robust Transformer Based Pedestrian Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {759-768} }
MACP: Efficient Model Adaptation for Cooperative Perception: Yunsheng Ma,

Juanwu Lu,

Can Cui,

Sicheng Zhao,

Xu Cao,

Wenqian Ye,

Ziran Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2024_WACV, author = {Ma, Yunsheng and Lu, Juanwu and Cui, Can and Zhao, Sicheng and Cao, Xu and Ye, Wenqian and Wang, Ziran}, title = {MACP: Efficient Model Adaptation for Cooperative Perception}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3373-3382} }
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-Free Continual Learning: Filip Szatkowski,

Mateusz Pyla,

Marcin Przewięźlikowski,

Sebastian Cygert,

Bartłomiej Twardowski,

Tomasz Trzciński; [pdf] [supp]
[bibtex]
@InProceedings{Szatkowski_2024_WACV, author = {Szatkowski, Filip and Pyla, Mateusz and Przewi\k{e}\'zlikowski, Marcin and Cygert, Sebastian and Twardowski, Bart{\l}omiej and Trzci\'nski, Tomasz}, title = {Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-Free Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1977-1987} }
Content-Aware Image Color Editing With Auxiliary Color Restoration Tasks: Yixuan Ren,

Jing Shi,

Zhifei Zhang,

Yifei Fan,

Zhe Lin,

Bo He,

Abhinav Shrivastava; [pdf] [supp]
[bibtex]
@InProceedings{Ren_2024_WACV, author = {Ren, Yixuan and Shi, Jing and Zhang, Zhifei and Fan, Yifei and Lin, Zhe and He, Bo and Shrivastava, Abhinav}, title = {Content-Aware Image Color Editing With Auxiliary Color Restoration Tasks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5192-5201} }
Self-Supervised Representation Learning With Cross-Context Learning Between Global and Hypercolumn Features: Zheng Gao,

Chen Feng,

Ioannis Patras; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2024_WACV, author = {Gao, Zheng and Feng, Chen and Patras, Ioannis}, title = {Self-Supervised Representation Learning With Cross-Context Learning Between Global and Hypercolumn Features}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1773-1783} }
Constrained Probabilistic Mask Learning for Task-Specific Undersampled MRI Reconstruction: Tobias Weber,

Michael Ingrisch,

Bernd Bischl,

David Rügamer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Weber_2024_WACV, author = {Weber, Tobias and Ingrisch, Michael and Bischl, Bernd and R\"ugamer, David}, title = {Constrained Probabilistic Mask Learning for Task-Specific Undersampled MRI Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7665-7674} }
CPSeg: Finer-Grained Image Semantic Segmentation via Chain-of-Thought Language Prompting: Lei Li; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2024_WACV, author = {Li, Lei}, title = {CPSeg: Finer-Grained Image Semantic Segmentation via Chain-of-Thought Language Prompting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {513-522} }
Hyb-NeRF: A Multiresolution Hybrid Encoding for Neural Radiance Fields: Yifan Wang,

Yi Gong,

Yuan Zeng; [pdf]
[bibtex]
@InProceedings{Wang_2024_WACV, author = {Wang, Yifan and Gong, Yi and Zeng, Yuan}, title = {Hyb-NeRF: A Multiresolution Hybrid Encoding for Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3689-3698} }
SequenceMatch: Revisiting the Design of Weak-Strong Augmentations for Semi-Supervised Learning: Khanh-Binh Nguyen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nguyen_2024_WACV, author = {Nguyen, Khanh-Binh}, title = {SequenceMatch: Revisiting the Design of Weak-Strong Augmentations for Semi-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {96-106} }
Robust Learning via Conditional Prevalence Adjustment: Minh Nguyen,

Alan Q. Wang,

Heejong Kim,

Mert R. Sabuncu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nguyen_2024_WACV, author = {Nguyen, Minh and Wang, Alan Q. and Kim, Heejong and Sabuncu, Mert R.}, title = {Robust Learning via Conditional Prevalence Adjustment}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2741-2750} }
GRIT: GAN Residuals for Paired Image-to-Image Translation: Saksham Suri,

Moustafa Meshry,

Larry S. Davis,

Abhinav Shrivastava; [pdf] [supp]
[bibtex]
@InProceedings{Suri_2024_WACV, author = {Suri, Saksham and Meshry, Moustafa and Davis, Larry S. and Shrivastava, Abhinav}, title = {GRIT: GAN Residuals for Paired Image-to-Image Translation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4965-4975} }
Embodied Human Activity Recognition: Sha Hu,

Yu Gong,

Greg Mori; [pdf] [supp]
[bibtex]
@InProceedings{Hu_2024_WACV, author = {Hu, Sha and Gong, Yu and Mori, Greg}, title = {Embodied Human Activity Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6447-6457} }
INCODE: Implicit Neural Conditioning With Prior Knowledge Embeddings: Amirhossein Kazerouni,

Reza Azad,

Alireza Hosseini,

Dorit Merhof,

Ulas Bagci; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kazerouni_2024_WACV, author = {Kazerouni, Amirhossein and Azad, Reza and Hosseini, Alireza and Merhof, Dorit and Bagci, Ulas}, title = {INCODE: Implicit Neural Conditioning With Prior Knowledge Embeddings}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1298-1307} }
Effective Restoration of Source Knowledge in Continual Test Time Adaptation: Fahim Faisal Niloy,

Sk Miraj Ahmed,

Dripta S. Raychaudhuri,

Samet Oymak,

Amit K. Roy-Chowdhury; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Niloy_2024_WACV, author = {Niloy, Fahim Faisal and Ahmed, Sk Miraj and Raychaudhuri, Dripta S. and Oymak, Samet and Roy-Chowdhury, Amit K.}, title = {Effective Restoration of Source Knowledge in Continual Test Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2091-2100} }
Unsupervised Model-Based Learning for Simultaneous Video Deflickering and Deblotching: Anuj Fulari,

Satish Mulleti,

Ajit Rajwade; [pdf] [supp]
[bibtex]
@InProceedings{Fulari_2024_WACV, author = {Fulari, Anuj and Mulleti, Satish and Rajwade, Ajit}, title = {Unsupervised Model-Based Learning for Simultaneous Video Deflickering and Deblotching}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4117-4125} }
Gradual Source Domain Expansion for Unsupervised Domain Adaptation: Thomas Westfechtel,

Hao-Wei Yeh,

Dexuan Zhang,

Tatsuya Harada; [pdf] [arXiv]
[bibtex]
@InProceedings{Westfechtel_2024_WACV, author = {Westfechtel, Thomas and Yeh, Hao-Wei and Zhang, Dexuan and Harada, Tatsuya}, title = {Gradual Source Domain Expansion for Unsupervised Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1946-1955} }
Towards Better Structured Pruning Saliency by Reorganizing Convolution: Xinglong Sun,

Humphrey Shi; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2024_WACV, author = {Sun, Xinglong and Shi, Humphrey}, title = {Towards Better Structured Pruning Saliency by Reorganizing Convolution}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2204-2214} }
Controllable Text-to-Image Synthesis for Multi-Modality MR Images: Kyuri Kim,

Yoonho Na,

Sung-Joon Ye,

Jimin Lee,

Sung Soo Ahn,

Ji Eun Park,

Hwiyoung Kim; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2024_WACV, author = {Kim, Kyuri and Na, Yoonho and Ye, Sung-Joon and Lee, Jimin and Ahn, Sung Soo and Park, Ji Eun and Kim, Hwiyoung}, title = {Controllable Text-to-Image Synthesis for Multi-Modality MR Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7936-7945} }
CATS: Combined Activation and Temporal Suppression for Efficient Network Inference: Zeqi Zhu,

Arash Pourtaherian,

Luc Waeijen,

Ibrahim Batuhan Akkaya,

Egor Bondarev,

Orlando Moreira; [pdf] [supp]
[bibtex]
@InProceedings{Zhu_2024_WACV, author = {Zhu, Zeqi and Pourtaherian, Arash and Waeijen, Luc and Akkaya, Ibrahim Batuhan and Bondarev, Egor and Moreira, Orlando}, title = {CATS: Combined Activation and Temporal Suppression for Efficient Network Inference}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8166-8175} }
Learnable Cube-Based Video Encryption for Privacy-Preserving Action Recognition: Yuchi Ishikawa,

Masayoshi Kondo,

Hirokatsu Kataoka; [pdf] [supp]
[bibtex]
@InProceedings{Ishikawa_2024_WACV, author = {Ishikawa, Yuchi and Kondo, Masayoshi and Kataoka, Hirokatsu}, title = {Learnable Cube-Based Video Encryption for Privacy-Preserving Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7003-7013} }
Learning To Generate Training Datasets for Robust Semantic Segmentation: Marwane Hariat,

Olivier Laurent,

Rémi Kazmierczak,

Shihao Zhang,

Andrei Bursuc,

Angela Yao,

Gianni Franchi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hariat_2024_WACV, author = {Hariat, Marwane and Laurent, Olivier and Kazmierczak, R\'emi and Zhang, Shihao and Bursuc, Andrei and Yao, Angela and Franchi, Gianni}, title = {Learning To Generate Training Datasets for Robust Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3894-3905} }
Stereo Conversion With Disparity-Aware Warping, Compositing and Inpainting: Lukas Mehl,

Andrés Bruhn,

Markus Gross,

Christopher Schroers; [pdf] [supp]
[bibtex]
@InProceedings{Mehl_2024_WACV, author = {Mehl, Lukas and Bruhn, Andr\'es and Gross, Markus and Schroers, Christopher}, title = {Stereo Conversion With Disparity-Aware Warping, Compositing and Inpainting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4260-4269} }
GTP-ViT: Efficient Vision Transformers via Graph-Based Token Propagation: Xuwei Xu,

Sen Wang,

Yudong Chen,

Yanping Zheng,

Zhewei Wei,

Jiajun Liu; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2024_WACV, author = {Xu, Xuwei and Wang, Sen and Chen, Yudong and Zheng, Yanping and Wei, Zhewei and Liu, Jiajun}, title = {GTP-ViT: Efficient Vision Transformers via Graph-Based Token Propagation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {86-95} }
HaGRID -- HAnd Gesture Recognition Image Dataset: Alexander Kapitanov,

Karina Kvanchiani,

Alexander Nagaev,

Roman Kraynov,

Andrei Makhliarchuk; [pdf] [supp]
[bibtex]
@InProceedings{Kapitanov_2024_WACV, author = {Kapitanov, Alexander and Kvanchiani, Karina and Nagaev, Alexander and Kraynov, Roman and Makhliarchuk, Andrei}, title = {HaGRID -- HAnd Gesture Recognition Image Dataset}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4572-4581} }
Beyond RGB: A Real World Dataset for Multispectral Imaging in Mobile Devices: Ortal Glatt,

Yotam Ater,

Woo-Shik Kim,

Shira Werman,

Oded Berby,

Yael Zini,

Shay Zelinger,

Sangyoon Lee,

Heejin Choi,

Evgeny Soloveichik; [pdf] [supp]
[bibtex]
@InProceedings{Glatt_2024_WACV, author = {Glatt, Ortal and Ater, Yotam and Kim, Woo-Shik and Werman, Shira and Berby, Oded and Zini, Yael and Zelinger, Shay and Lee, Sangyoon and Choi, Heejin and Soloveichik, Evgeny}, title = {Beyond RGB: A Real World Dataset for Multispectral Imaging in Mobile Devices}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4344-4354} }
Lightweight Portrait Matting via Regional Attention and Refinement: Yatao Zhong,

Ilya Zharkov; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhong_2024_WACV, author = {Zhong, Yatao and Zharkov, Ilya}, title = {Lightweight Portrait Matting via Regional Attention and Refinement}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4158-4167} }
Analyzing the Domain Shift Immunity of Deep Homography Estimation: Mingzhen Shao,

Tolga Tasdizen,

Sarang Joshi; [pdf] [arXiv]
[bibtex]
@InProceedings{Shao_2024_WACV, author = {Shao, Mingzhen and Tasdizen, Tolga and Joshi, Sarang}, title = {Analyzing the Domain Shift Immunity of Deep Homography Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4800-4808} }
Gradient Coreset for Federated Learning: Durga Sivasubramanian,

Lokesh Nagalapatti,

Rishabh Iyer,

Ganesh Ramakrishnan; [pdf] [supp]
[bibtex]
@InProceedings{Sivasubramanian_2024_WACV, author = {Sivasubramanian, Durga and Nagalapatti, Lokesh and Iyer, Rishabh and Ramakrishnan, Ganesh}, title = {Gradient Coreset for Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2648-2657} }
Semantic Fusion Augmentation and Semantic Boundary Detection: A Novel Approach to Multi-Target Video Moment Retrieval: Cheng Huang,

Yi-Lun Wu,

Hong-Han Shuai,

Ching-Chun Huang; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2024_WACV, author = {Huang, Cheng and Wu, Yi-Lun and Shuai, Hong-Han and Huang, Ching-Chun}, title = {Semantic Fusion Augmentation and Semantic Boundary Detection: A Novel Approach to Multi-Target Video Moment Retrieval}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6783-6792} }
CHAI: Craters in Historical Aerial Images: Marvin Burges,

Sebastian Zambanini,

Philipp Pirker; [pdf] [supp]
[bibtex]
@InProceedings{Burges_2024_WACV, author = {Burges, Marvin and Zambanini, Sebastian and Pirker, Philipp}, title = {CHAI: Craters in Historical Aerial Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8256-8265} }
PDA-RWSR: Pixel-Wise Degradation Adaptive Real-World Super-Resolution: Andreas Aakerberg,

Majed El Helou,

Kamal Nasrollahi,

Thomas Moeslund; [pdf] [supp]
[bibtex]
@InProceedings{Aakerberg_2024_WACV, author = {Aakerberg, Andreas and El Helou, Majed and Nasrollahi, Kamal and Moeslund, Thomas}, title = {PDA-RWSR: Pixel-Wise Degradation Adaptive Real-World Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4097-4107} }
Zero-Shot Video Moment Retrieval From Frozen Vision-Language Models: Dezhao Luo,

Jiabo Huang,

Shaogang Gong,

Hailin Jin,

Yang Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Luo_2024_WACV, author = {Luo, Dezhao and Huang, Jiabo and Gong, Shaogang and Jin, Hailin and Liu, Yang}, title = {Zero-Shot Video Moment Retrieval From Frozen Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5464-5473} }
Image Denoising and the Generative Accumulation of Photons: Alexander Krull,

Hector Basevi,

Benjamin Salmon,

Andre Zeug,

Franziska Müller,

Samuel Tonks,

Leela Muppala,

Aleš Leonardis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Krull_2024_WACV, author = {Krull, Alexander and Basevi, Hector and Salmon, Benjamin and Zeug, Andre and M\"uller, Franziska and Tonks, Samuel and Muppala, Leela and Leonardis, Ale\v{s}}, title = {Image Denoising and the Generative Accumulation of Photons}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1528-1537} }
Ordinal Classification With Distance Regularization for Robust Brain Age Prediction: Jay Shah,

Md Mahfuzur Rahman Siddiquee,

Yi Su,

Teresa Wu,

Baoxin Li; [pdf]
[bibtex]
@InProceedings{Shah_2024_WACV, author = {Shah, Jay and Siddiquee, Md Mahfuzur Rahman and Su, Yi and Wu, Teresa and Li, Baoxin}, title = {Ordinal Classification With Distance Regularization for Robust Brain Age Prediction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7882-7891} }
The Growing Strawberries Dataset: Tracking Multiple Objects With Biological Development Over an Extended Period: Junhan Wen,

Camiel R. Verschoor,

Chengming Feng,

Irina-Mona Epure,

Thomas Abeel,

Mathijs de Weerdt; [pdf] [supp]
[bibtex]
@InProceedings{Wen_2024_WACV, author = {Wen, Junhan and Verschoor, Camiel R. and Feng, Chengming and Epure, Irina-Mona and Abeel, Thomas and de Weerdt, Mathijs}, title = {The Growing Strawberries Dataset: Tracking Multiple Objects With Biological Development Over an Extended Period}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7104-7114} }
Face Presentation Attack Detection by Excavating Causal Clues and Adapting Embedding Statistics: Meiling Fang,

Naser Damer; [pdf] [arXiv]
[bibtex]
@InProceedings{Fang_2024_WACV, author = {Fang, Meiling and Damer, Naser}, title = {Face Presentation Attack Detection by Excavating Causal Clues and Adapting Embedding Statistics}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6269-6279} }
Glance To Count: Learning To Rank With Anchors for Weakly-Supervised Crowd Counting: Zheng Xiong,

Liangyu Chai,

Wenxi Liu,

Yongtuo Liu,

Sucheng Ren,

Shengfeng He; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiong_2024_WACV, author = {Xiong, Zheng and Chai, Liangyu and Liu, Wenxi and Liu, Yongtuo and Ren, Sucheng and He, Shengfeng}, title = {Glance To Count: Learning To Rank With Anchors for Weakly-Supervised Crowd Counting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {343-352} }
Gradient-Guided Knowledge Distillation for Object Detectors: Qizhen Lan,

Qing Tian; [pdf] [arXiv]
[bibtex]
@InProceedings{Lan_2024_WACV, author = {Lan, Qizhen and Tian, Qing}, title = {Gradient-Guided Knowledge Distillation for Object Detectors}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {424-433} }
SciOL and MuLMS-Img: Introducing a Large-Scale Multimodal Scientific Dataset and Models for Image-Text Tasks in the Scientific Domain: Tim Tarsi,

Heike Adel,

Jan Hendrik Metzen,

Dan Zhang,

Matteo Finco,

Annemarie Friedrich; [pdf] [supp]
[bibtex]
@InProceedings{Tarsi_2024_WACV, author = {Tarsi, Tim and Adel, Heike and Metzen, Jan Hendrik and Zhang, Dan and Finco, Matteo and Friedrich, Annemarie}, title = {SciOL and MuLMS-Img: Introducing a Large-Scale Multimodal Scientific Dataset and Models for Image-Text Tasks in the Scientific Domain}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4560-4571} }
Few-Shot Event Classification in Images Using Knowledge Graphs for Prompting: Golsa Tahmasebzadeh,

Matthias Springstein,

Ralph Ewerth,

Eric Müller-Budack; [pdf] [supp]
[bibtex]
@InProceedings{Tahmasebzadeh_2024_WACV, author = {Tahmasebzadeh, Golsa and Springstein, Matthias and Ewerth, Ralph and M\"uller-Budack, Eric}, title = {Few-Shot Event Classification in Images Using Knowledge Graphs for Prompting}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7286-7295} }
Simple Token-Level Confidence Improves Caption Correctness: Suzanne Petryk,

Spencer Whitehead,

Joseph E. Gonzalez,

Trevor Darrell,

Anna Rohrbach,

Marcus Rohrbach; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Petryk_2024_WACV, author = {Petryk, Suzanne and Whitehead, Spencer and Gonzalez, Joseph E. and Darrell, Trevor and Rohrbach, Anna and Rohrbach, Marcus}, title = {Simple Token-Level Confidence Improves Caption Correctness}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5742-5752} }
Defending Object Detection Models Against Image Distortions: Mark Ofori-Oduro,

Maria Amer; [pdf]
[bibtex]
@InProceedings{Ofori-Oduro_2024_WACV, author = {Ofori-Oduro, Mark and Amer, Maria}, title = {Defending Object Detection Models Against Image Distortions}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3854-3863} }
Graph Neural Networks for End-to-End Information Extraction From Handwritten Documents: Yessine Khanfir,

Marwa Dhiaf,

Emna Ghodhbani,

Ahmed Cheikh Rouhou,

Yousri Kessentini; [pdf]
[bibtex]
@InProceedings{Khanfir_2024_WACV, author = {Khanfir, Yessine and Dhiaf, Marwa and Ghodhbani, Emna and Rouhou, Ahmed Cheikh and Kessentini, Yousri}, title = {Graph Neural Networks for End-to-End Information Extraction From Handwritten Documents}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {504-512} }
Automated Monitoring of Ear Biting in Pigs by Tracking Individuals and Events: Anicetus Odo,

Niall McLaughlin,

Ilias Kyriazakis; [pdf]
[bibtex]
@InProceedings{Odo_2024_WACV, author = {Odo, Anicetus and McLaughlin, Niall and Kyriazakis, Ilias}, title = {Automated Monitoring of Ear Biting in Pigs by Tracking Individuals and Events}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7095-7103} }
RSMPNet: Relationship Guided Semantic Map Prediction: Jingwen Sun,

Jing Wu,

Ze Ji,

Yu-Kun Lai; [pdf]
[bibtex]
@InProceedings{Sun_2024_WACV, author = {Sun, Jingwen and Wu, Jing and Ji, Ze and Lai, Yu-Kun}, title = {RSMPNet: Relationship Guided Semantic Map Prediction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {303-312} }
CARE: Counterfactual-Based Algorithmic Recourse for Explainable Pose Correction: Bhat Dittakavi,

Bharathi Callepalli,

Aleti Vardhan,

Sai Vikas Desai,

Vineeth N. Balasubramanian; [pdf] [supp]
[bibtex]
@InProceedings{Dittakavi_2024_WACV, author = {Dittakavi, Bhat and Callepalli, Bharathi and Vardhan, Aleti and Desai, Sai Vikas and Balasubramanian, Vineeth N.}, title = {CARE: Counterfactual-Based Algorithmic Recourse for Explainable Pose Correction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4902-4911} }
Monocular 3D Object Detection With LiDAR Guided Semi Supervised Active Learning: Aral Hekimoglu,

Michael Schmidt,

Alvaro Marcos-Ramiro; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hekimoglu_2024_WACV, author = {Hekimoglu, Aral and Schmidt, Michael and Marcos-Ramiro, Alvaro}, title = {Monocular 3D Object Detection With LiDAR Guided Semi Supervised Active Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2346-2355} }
S3AD: Semi-Supervised Small Apple Detection in Orchard Environments: Robert Johanson,

Christian Wilms,

Ole Johannsen,

Simone Frintrop; [pdf] [supp]
[bibtex]
@InProceedings{Johanson_2024_WACV, author = {Johanson, Robert and Wilms, Christian and Johannsen, Ole and Frintrop, Simone}, title = {S3AD: Semi-Supervised Small Apple Detection in Orchard Environments}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7076-7085} }
Task-Oriented Human-Object Interactions Generation With Implicit Neural Representations: Quanzhou Li,

Jingbo Wang,

Chen Change Loy,

Bo Dai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_WACV, author = {Li, Quanzhou and Wang, Jingbo and Loy, Chen Change and Dai, Bo}, title = {Task-Oriented Human-Object Interactions Generation With Implicit Neural Representations}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3035-3044} }
Convolutional Masked Image Modeling for Dense Prediction Tasks on Pathology Images: Yan Yang,

Liyuan Pan,

Liu Liu,

Eric A. Stone; [pdf]
[bibtex]
@InProceedings{Yang_2024_WACV, author = {Yang, Yan and Pan, Liyuan and Liu, Liu and Stone, Eric A.}, title = {Convolutional Masked Image Modeling for Dense Prediction Tasks on Pathology Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7798-7808} }
Controlling Virtual Try-On Pipeline Through Rendering Policies: Kedan Li,

Jeffrey Zhang,

Shao-Yu Chang,

David Forsyth; [pdf] [supp]
[bibtex]
@InProceedings{Li_2024_WACV, author = {Li, Kedan and Zhang, Jeffrey and Chang, Shao-Yu and Forsyth, David}, title = {Controlling Virtual Try-On Pipeline Through Rendering Policies}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5866-5875} }
Interpretable Object Recognition by Semantic Prototype Analysis: Qiyang Wan,

Ruiping Wang,

Xilin Chen; [pdf] [supp]
[bibtex]
@InProceedings{Wan_2024_WACV, author = {Wan, Qiyang and Wang, Ruiping and Chen, Xilin}, title = {Interpretable Object Recognition by Semantic Prototype Analysis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {800-809} }
Assist Is Just As Important as the Goal: Image Resurfacing To Aid Model's Robust Prediction: Abhijith Sharma,

Phil Munz,

Apurva Narayan; [pdf]
[bibtex]
@InProceedings{Sharma_2024_WACV, author = {Sharma, Abhijith and Munz, Phil and Narayan, Apurva}, title = {Assist Is Just As Important as the Goal: Image Resurfacing To Aid Model's Robust Prediction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3833-3842} }
Prompting Classes: Exploring the Power of Prompt Class Learning in Weakly Supervised Semantic Segmentation: Balamurali Murugesan,

Rukhshanda Hussain,

Rajarshi Bhattacharya,

Ismail Ben Ayed,

Jose Dolz; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Murugesan_2024_WACV, author = {Murugesan, Balamurali and Hussain, Rukhshanda and Bhattacharya, Rajarshi and Ben Ayed, Ismail and Dolz, Jose}, title = {Prompting Classes: Exploring the Power of Prompt Class Learning in Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {291-302} }
From Denoising Training To Test-Time Adaptation: Enhancing Domain Generalization for Medical Image Segmentation: Ruxue Wen,

Hangjie Yuan,

Dong Ni,

Wenbo Xiao,

Yaoyao Wu; [pdf] [arXiv]
[bibtex]
@InProceedings{Wen_2024_WACV, author = {Wen, Ruxue and Yuan, Hangjie and Ni, Dong and Xiao, Wenbo and Wu, Yaoyao}, title = {From Denoising Training To Test-Time Adaptation: Enhancing Domain Generalization for Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {464-474} }
Implicit Neural Image Stitching With Enhanced and Blended Feature Reconstruction: Minsu Kim,

Jaewon Lee,

Byeonghun Lee,

Sunghoon Im,

Kyong Hwan Jin; [pdf] [arXiv]
[bibtex]
@InProceedings{Kim_2024_WACV, author = {Kim, Minsu and Lee, Jaewon and Lee, Byeonghun and Im, Sunghoon and Jin, Kyong Hwan}, title = {Implicit Neural Image Stitching With Enhanced and Blended Feature Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4087-4096} }
360BEV: Panoramic Semantic Mapping for Indoor Bird's-Eye View: Zhifeng Teng,

Jiaming Zhang,

Kailun Yang,

Kunyu Peng,

Hao Shi,

Simon Reiß,

Ke Cao,

Rainer Stiefelhagen; [pdf] [supp]
[bibtex]
@InProceedings{Teng_2024_WACV, author = {Teng, Zhifeng and Zhang, Jiaming and Yang, Kailun and Peng, Kunyu and Shi, Hao and Rei{\ss}, Simon and Cao, Ke and Stiefelhagen, Rainer}, title = {360BEV: Panoramic Semantic Mapping for Indoor Bird's-Eye View}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {373-382} }
Semi-Supervised Semantic Depth Estimation Using Symbiotic Transformer and NearFarMix Augmentation: Md Awsafur Rahman,

Shaikh Anowarul Fattah; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rahman_2024_WACV, author = {Rahman, Md Awsafur and Fattah, Shaikh Anowarul}, title = {Semi-Supervised Semantic Depth Estimation Using Symbiotic Transformer and NearFarMix Augmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {250-259} }
Query-Guided Attention in Vision Transformers for Localizing Objects Using a Single Sketch: Aditay Tripathi,

Anand Mishra,

Anirban Chakraborty; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tripathi_2024_WACV, author = {Tripathi, Aditay and Mishra, Anand and Chakraborty, Anirban}, title = {Query-Guided Attention in Vision Transformers for Localizing Objects Using a Single Sketch}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1083-1092} }
I-AI: A Controllable & Interpretable AI System for Decoding Radiologists' Intense Focus for Accurate CXR Diagnoses: Trong Thang Pham,

Jacob Brecheisen,

Anh Nguyen,

Hien Nguyen,

Ngan Le; [pdf]
[bibtex]
@InProceedings{Pham_2024_WACV, author = {Pham, Trong Thang and Brecheisen, Jacob and Nguyen, Anh and Nguyen, Hien and Le, Ngan}, title = {I-AI: A Controllable \& Interpretable AI System for Decoding Radiologists' Intense Focus for Accurate CXR Diagnoses}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7850-7859} }
Diffuse and Restore: A Region-Adaptive Diffusion Model for Identity-Preserving Blind Face Restoration: Maitreya Suin,

Nithin Gopalakrishnan Nair,

Chun Pong Lau,

Vishal M. Patel,

Rama Chellappa; [pdf]
[bibtex]
@InProceedings{Suin_2024_WACV, author = {Suin, Maitreya and Nair, Nithin Gopalakrishnan and Lau, Chun Pong and Patel, Vishal M. and Chellappa, Rama}, title = {Diffuse and Restore: A Region-Adaptive Diffusion Model for Identity-Preserving Blind Face Restoration}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6343-6352} }
Interaction Region Visual Transformer for Egocentric Action Anticipation: Debaditya Roy,

Ramanathan Rajendiran,

Basura Fernando; [pdf] [supp]
[bibtex]
@InProceedings{Roy_2024_WACV, author = {Roy, Debaditya and Rajendiran, Ramanathan and Fernando, Basura}, title = {Interaction Region Visual Transformer for Egocentric Action Anticipation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6740-6750} }
Preserving Image Properties Through Initializations in Diffusion Models: Jeffrey Zhang,

Shao-Yu Chang,

Kedan Li,

David Forsyth; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_WACV, author = {Zhang, Jeffrey and Chang, Shao-Yu and Li, Kedan and Forsyth, David}, title = {Preserving Image Properties Through Initializations in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5242-5250} }
Limited Data, Unlimited Potential: A Study on ViTs Augmented by Masked Autoencoders: Srijan Das,

Tanmay Jain,

Dominick Reilly,

Pranav Balaji,

Soumyajit Karmakar,

Shyam Marjit,

Xiang Li,

Abhijit Das,

Michael S. Ryoo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Das_2024_WACV, author = {Das, Srijan and Jain, Tanmay and Reilly, Dominick and Balaji, Pranav and Karmakar, Soumyajit and Marjit, Shyam and Li, Xiang and Das, Abhijit and Ryoo, Michael S.}, title = {Limited Data, Unlimited Potential: A Study on ViTs Augmented by Masked Autoencoders}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6878-6888} }
Unsupervised Co-Generation of Foreground-Background Segmentation From Text-to-Image Synthesis: Yeruru Asrar Ahmed,

Anurag Mittal; [pdf] [supp]
[bibtex]
@InProceedings{Ahmed_2024_WACV, author = {Ahmed, Yeruru Asrar and Mittal, Anurag}, title = {Unsupervised Co-Generation of Foreground-Background Segmentation From Text-to-Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5058-5069} }
High-Fidelity Zero-Shot Texture Anomaly Localization Using Feature Correspondence Analysis: Andrei-Timotei Ardelean,

Tim Weyrich; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ardelean_2024_WACV, author = {Ardelean, Andrei-Timotei and Weyrich, Tim}, title = {High-Fidelity Zero-Shot Texture Anomaly Localization Using Feature Correspondence Analysis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1134-1144} }
Hierarchical Text Spotter for Joint Text Spotting and Layout Analysis: Shangbang Long,

Siyang Qin,

Yasuhisa Fujii,

Alessandro Bissacco,

Michalis Raptis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Long_2024_WACV, author = {Long, Shangbang and Qin, Siyang and Fujii, Yasuhisa and Bissacco, Alessandro and Raptis, Michalis}, title = {Hierarchical Text Spotter for Joint Text Spotting and Layout Analysis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {903-913} }
Label-Free Synthetic Pretraining of Object Detectors: Hei Law,

Jia Deng; [pdf] [arXiv]
[bibtex]
@InProceedings{Law_2024_WACV, author = {Law, Hei and Deng, Jia}, title = {Label-Free Synthetic Pretraining of Object Detectors}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {946-956} }
Tracking Tiny Insects in Cluttered Natural Environments Using Refinable Recurrent Neural Networks: Lars Haalck,

Sebastian Thiele,

Benjamin Risse; [pdf] [supp]
[bibtex]
@InProceedings{Haalck_2024_WACV, author = {Haalck, Lars and Thiele, Sebastian and Risse, Benjamin}, title = {Tracking Tiny Insects in Cluttered Natural Environments Using Refinable Recurrent Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7126-7135} }
RGB-X Object Detection via Scene-Specific Fusion Modules: Sri Aditya Deevi,

Connor Lee,

Lu Gan,

Sushruth Nagesh,

Gaurav Pandey,

Soon-Jo Chung; [pdf]
[bibtex]
@InProceedings{Deevi_2024_WACV, author = {Deevi, Sri Aditya and Lee, Connor and Gan, Lu and Nagesh, Sushruth and Pandey, Gaurav and Chung, Soon-Jo}, title = {RGB-X Object Detection via Scene-Specific Fusion Modules}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7366-7375} }
3D-Aware Talking-Head Video Motion Transfer: Haomiao Ni,

Jiachen Liu,

Yuan Xue,

Sharon X. Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ni_2024_WACV, author = {Ni, Haomiao and Liu, Jiachen and Xue, Yuan and Huang, Sharon X.}, title = {3D-Aware Talking-Head Video Motion Transfer}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4954-4964} }
Lightweight Thermal Super-Resolution and Object Detection for Robust Perception in Adverse Weather Conditions: Pranjay Shyam,

HyunJin Yoo; [pdf] [supp]
[bibtex]
@InProceedings{Shyam_2024_WACV, author = {Shyam, Pranjay and Yoo, HyunJin}, title = {Lightweight Thermal Super-Resolution and Object Detection for Robust Perception in Adverse Weather Conditions}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7471-7482} }
Revolutionize the Oceanic Drone RGB Imagery With Pioneering Sun Glint Detection and Removal Techniques: Jiangying Qin,

Ming Li,

Jie Zhao,

Jiageng Zhong,

Hanqi Zhang; [pdf]
[bibtex]
@InProceedings{Qin_2024_WACV, author = {Qin, Jiangying and Li, Ming and Zhao, Jie and Zhong, Jiageng and Zhang, Hanqi}, title = {Revolutionize the Oceanic Drone RGB Imagery With Pioneering Sun Glint Detection and Removal Techniques}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8326-8335} }
Revisiting Pixel-Level Contrastive Pre-Training on Scene Images: Zongshang Pang,

Yuta Nakashima,

Mayu Otani,

Hajime Nagahara; [pdf] [supp]
[bibtex]
@InProceedings{Pang_2024_WACV, author = {Pang, Zongshang and Nakashima, Yuta and Otani, Mayu and Nagahara, Hajime}, title = {Revisiting Pixel-Level Contrastive Pre-Training on Scene Images}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1784-1793} }
Neural Textured Deformable Meshes for Robust Analysis-by-Synthesis: Angtian Wang,

Wufei Ma,

Alan Yuille,

Adam Kortylewski; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_WACV, author = {Wang, Angtian and Ma, Wufei and Yuille, Alan and Kortylewski, Adam}, title = {Neural Textured Deformable Meshes for Robust Analysis-by-Synthesis}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3108-3117} }
PsyMo: A Dataset for Estimating Self-Reported Psychological Traits From Gait: Adrian Cosma,

Emilian Radoi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cosma_2024_WACV, author = {Cosma, Adrian and Radoi, Emilian}, title = {PsyMo: A Dataset for Estimating Self-Reported Psychological Traits From Gait}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4603-4613} }
Back to Optimization: Diffusion-Based Zero-Shot 3D Human Pose Estimation: Zhongyu Jiang,

Zhuoran Zhou,

Lei Li,

Wenhao Chai,

Cheng-Yen Yang,

Jenq-Neng Hwang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2024_WACV, author = {Jiang, Zhongyu and Zhou, Zhuoran and Li, Lei and Chai, Wenhao and Yang, Cheng-Yen and Hwang, Jenq-Neng}, title = {Back to Optimization: Diffusion-Based Zero-Shot 3D Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6142-6152} }
IKEA Ego 3D Dataset: Understanding Furniture Assembly Actions From Ego-View 3D Point Clouds: Yizhak Ben-Shabat,

Jonathan Paul,

Eviatar Segev,

Oren Shrout,

Stephen Gould; [pdf] [supp]
[bibtex]
@InProceedings{Ben-Shabat_2024_WACV, author = {Ben-Shabat, Yizhak and Paul, Jonathan and Segev, Eviatar and Shrout, Oren and Gould, Stephen}, title = {IKEA Ego 3D Dataset: Understanding Furniture Assembly Actions From Ego-View 3D Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4355-4364} }
Concept-Centric Transformers: Enhancing Model Interpretability Through Object-Centric Concept Learning Within a Shared Global Workspace: Jinyung Hong,

Keun Hee Park,

Theodore P. Pavlic; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hong_2024_WACV, author = {Hong, Jinyung and Park, Keun Hee and Pavlic, Theodore P.}, title = {Concept-Centric Transformers: Enhancing Model Interpretability Through Object-Centric Concept Learning Within a Shared Global Workspace}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4880-4891} }
What's in the Flow? Exploiting Temporal Motion Cues for Unsupervised Generic Event Boundary Detection: Sourabh Vasant Gothe,

Vibhav Agarwal,

Sourav Ghosh,

Jayesh Rajkumar Vachhani,

Pranay Kashyap,

Barath Raj Kandur Raja; [pdf] [supp]
[bibtex]
@InProceedings{Gothe_2024_WACV, author = {Gothe, Sourabh Vasant and Agarwal, Vibhav and Ghosh, Sourav and Vachhani, Jayesh Rajkumar and Kashyap, Pranay and Raja, Barath Raj Kandur}, title = {What's in the Flow? Exploiting Temporal Motion Cues for Unsupervised Generic Event Boundary Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6941-6950} }
SyntheWorld: A Large-Scale Synthetic Dataset for Land Cover Mapping and Building Change Detection: Jian Song,

Hongruixuan Chen,

Naoto Yokoya; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Song_2024_WACV, author = {Song, Jian and Chen, Hongruixuan and Yokoya, Naoto}, title = {SyntheWorld: A Large-Scale Synthetic Dataset for Land Cover Mapping and Building Change Detection}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8287-8296} }
Generalizing to Unseen Domains in Diabetic Retinopathy Classification: Chamuditha Jayanga Galappaththige,

Gayal Kuruppu,

Muhammad Haris Khan; [pdf] [arXiv]
[bibtex]
@InProceedings{Galappaththige_2024_WACV, author = {Galappaththige, Chamuditha Jayanga and Kuruppu, Gayal and Khan, Muhammad Haris}, title = {Generalizing to Unseen Domains in Diabetic Retinopathy Classification}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7685-7695} }
A Generic and Flexible Regularization Framework for NeRFs: Thibaud Ehret,

Roger Marí,

Gabriele Facciolo; [pdf] [supp]
[bibtex]
@InProceedings{Ehret_2024_WACV, author = {Ehret, Thibaud and Mar{\'\i}, Roger and Facciolo, Gabriele}, title = {A Generic and Flexible Regularization Framework for NeRFs}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {3088-3097} }
MarsLS-Net: Martian Landslides Segmentation Network and Benchmark Dataset: Sidike Paheding,

Abel A. Reyes,

A. Rajaneesh,

K.S. Sajinkumar,

Thomas Oommen; [pdf]
[bibtex]
@InProceedings{Paheding_2024_WACV, author = {Paheding, Sidike and Reyes, Abel A. and Rajaneesh, A. and Sajinkumar, K.S. and Oommen, Thomas}, title = {MarsLS-Net: Martian Landslides Segmentation Network and Benchmark Dataset}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8236-8245} }
You Can Run but Not Hide: Improving Gait Recognition With Intrinsic Occlusion Type Awareness: Ayush Gupta,

Rama Chellappa; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gupta_2024_WACV, author = {Gupta, Ayush and Chellappa, Rama}, title = {You Can Run but Not Hide: Improving Gait Recognition With Intrinsic Occlusion Type Awareness}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5893-5902} }
SphereCraft: A Dataset for Spherical Keypoint Detection, Matching and Camera Pose Estimation: Christiano Gava,

Yunmin Cho,

Federico Raue,

Sebastian Palacio,

Alain Pagani,

Andreas Dengel; [pdf] [supp]
[bibtex]
@InProceedings{Gava_2024_WACV, author = {Gava, Christiano and Cho, Yunmin and Raue, Federico and Palacio, Sebastian and Pagani, Alain and Dengel, Andreas}, title = {SphereCraft: A Dataset for Spherical Keypoint Detection, Matching and Camera Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4408-4417} }
Best of Both Worlds: Learning Arbitrary-Scale Blind Super-Resolution via Dual Degradation Representations and Cycle-Consistency: Shao-Yu Weng,

Hsuan Yuan,

Yu-Syuan Xu,

Ching-Chun Huang,

Wei-Chen Chiu; [pdf] [supp]
[bibtex]
@InProceedings{Weng_2024_WACV, author = {Weng, Shao-Yu and Yuan, Hsuan and Xu, Yu-Syuan and Huang, Ching-Chun and Chiu, Wei-Chen}, title = {Best of Both Worlds: Learning Arbitrary-Scale Blind Super-Resolution via Dual Degradation Representations and Cycle-Consistency}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1547-1556} }
VMFormer: End-to-End Video Matting With Transformer: Jiachen Li,

Vidit Goel,

Marianna Ohanyan,

Shant Navasardyan,

Yunchao Wei,

Humphrey Shi; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2024_WACV, author = {Li, Jiachen and Goel, Vidit and Ohanyan, Marianna and Navasardyan, Shant and Wei, Yunchao and Shi, Humphrey}, title = {VMFormer: End-to-End Video Matting With Transformer}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6678-6687} }
Feed-Forward Latent Domain Adaptation: Ondrej Bohdal,

Da Li,

Shell Xu Hu,

Timothy Hospedales; [pdf] [supp]
[bibtex]
@InProceedings{Bohdal_2024_WACV, author = {Bohdal, Ondrej and Li, Da and Hu, Shell Xu and Hospedales, Timothy}, title = {Feed-Forward Latent Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8490-8499} }
Triplet Attention Transformer for Spatiotemporal Predictive Learning: Xuesong Nie,

Xi Chen,

Haoyuan Jin,

Zhihang Zhu,

Yunfeng Yan,

Donglian Qi; [pdf] [arXiv]
[bibtex]
@InProceedings{Nie_2024_WACV, author = {Nie, Xuesong and Chen, Xi and Jin, Haoyuan and Zhu, Zhihang and Yan, Yunfeng and Qi, Donglian}, title = {Triplet Attention Transformer for Spatiotemporal Predictive Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {7036-7045} }
Arbitrary-Resolution and Arbitrary-Scale Face Super-Resolution With Implicit Representation Networks: Yi Ting Tsai,

Yu Wei Chen,

Hong-Han Shuai,

Ching-Chun Huang; [pdf] [supp]
[bibtex]
@InProceedings{Tsai_2024_WACV, author = {Tsai, Yi Ting and Chen, Yu Wei and Shuai, Hong-Han and Huang, Ching-Chun}, title = {Arbitrary-Resolution and Arbitrary-Scale Face Super-Resolution With Implicit Representation Networks}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {4270-4279} }
FPGAN-Control: A Controllable Fingerprint Generator for Training With Synthetic Data: Alon Shoshan,

Nadav Bhonker,

Emanuel Ben Baruch,

Ori Nizan,

Igor Kviatkovsky,

Joshua Engelsma,

Manoj Aggarwal,

Gérard Medioni; [pdf] [supp]
[bibtex]
@InProceedings{Shoshan_2024_WACV, author = {Shoshan, Alon and Bhonker, Nadav and Ben Baruch, Emanuel and Nizan, Ori and Kviatkovsky, Igor and Engelsma, Joshua and Aggarwal, Manoj and Medioni, G\'erard}, title = {FPGAN-Control: A Controllable Fingerprint Generator for Training With Synthetic Data}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {6067-6076} }
Continual Learning of Unsupervised Monocular Depth From Videos: Hemang Chawla,

Arnav Varma,

Elahe Arani,

Bahram Zonooz; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chawla_2024_WACV, author = {Chawla, Hemang and Varma, Arnav and Arani, Elahe and Zonooz, Bahram}, title = {Continual Learning of Unsupervised Monocular Depth From Videos}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {8419-8429} }
CXR-IRGen: An Integrated Vision and Language Model for the Generation of Clinically Accurate Chest X-Ray Image-Report Pairs: Junjie Shentu,

Noura Al Moubayed; [pdf]
[bibtex]
@InProceedings{Shentu_2024_WACV, author = {Shentu, Junjie and Al Moubayed, Noura}, title = {CXR-IRGen: An Integrated Vision and Language Model for the Generation of Clinically Accurate Chest X-Ray Image-Report Pairs}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {5212-5221} }
Overcoming Catastrophic Forgetting for Multi-Label Class-Incremental Learning: Xiang Song,

Kuang Shu,

Songlin Dong,

Jie Cheng,

Xing Wei,

Yihong Gong; [pdf]
[bibtex]
@InProceedings{Song_2024_WACV, author = {Song, Xiang and Shu, Kuang and Dong, Songlin and Cheng, Jie and Wei, Xing and Gong, Yihong}, title = {Overcoming Catastrophic Forgetting for Multi-Label Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {2389-2398} }
PatchRefineNet: Improving Binary Segmentation by Incorporating Signals From Optimal Patch-Wise Binarization: Savinay Nagendra,

Daniel Kifer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nagendra_2024_WACV, author = {Nagendra, Savinay and Kifer, Daniel}, title = {PatchRefineNet: Improving Binary Segmentation by Incorporating Signals From Optimal Patch-Wise Binarization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2024}, pages = {1361-1372} }