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
[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} }