ACCV 2024 Open Access Repository

Papers

Generative Self-Supervised Learning for Medical Image Classification: Inhyuk Park,

Sungeun Kim,

Jongbin Ryu; [pdf] [supp]
[bibtex]
@InProceedings{Park_2024_ACCV, author = {Park, Inhyuk and Kim, Sungeun and Ryu, Jongbin}, title = {Generative Self-Supervised Learning for Medical Image Classification}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {976-993} }
Depth Attention for Robust RGB Tracking: Yu Liu,

Arif Mahmood,

Muhammad Haris Khan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_ACCV, author = {Liu, Yu and Mahmood, Arif and Khan, Muhammad Haris}, title = {Depth Attention for Robust RGB Tracking}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {213-231} }
MedBLIP: Bootstrapping Language-Image Pre-training from 3D Medical Images and Texts: Qiuhui Chen,

Yi Hong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_ACCV, author = {Chen, Qiuhui and Hong, Yi}, title = {MedBLIP: Bootstrapping Language-Image Pre-training from 3D Medical Images and Texts}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2404-2420} }
Neural Active Structure-from-Motion in Dark and Textureless Environment: Kazuto Ichimaru,

Diego Thomas,

Takafumi Iwaguchi,

Hiroshi Kawasaki; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ichimaru_2024_ACCV, author = {Ichimaru, Kazuto and Thomas, Diego and Iwaguchi, Takafumi and Kawasaki, Hiroshi}, title = {Neural Active Structure-from-Motion in Dark and Textureless Environment}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2145-2161} }
LoGDesc: Local geometric features aggregation for robust point cloud registration: Karim Slimani,

Brahim Tamadazte,

Catherine Achard; [pdf] [arXiv]
[bibtex]
@InProceedings{Slimani_2024_ACCV, author = {Slimani, Karim and Tamadazte, Brahim and Achard, Catherine}, title = {LoGDesc: Local geometric features aggregation for robust point cloud registration}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1952-1968} }
OmniFusion: Exemplar-based Video Colorization Using OmniMotion and Diffusion Priors: Xiaoyuan Fang,

Longquan Dai,

Jinhui Tang; [pdf]
[bibtex]
@InProceedings{Fang_2024_ACCV, author = {Fang, Xiaoyuan and Dai, Longquan and Tang, Jinhui}, title = {OmniFusion: Exemplar-based Video Colorization Using OmniMotion and Diffusion Priors}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1215-1232} }
Contrastive Learning using Synthetic Images Generated from Real Images: Tenta Sasaya,

Shintaro Yamamoto,

Takashi Ida,

Takahiro Takimoto; [pdf]
[bibtex]
@InProceedings{Sasaya_2024_ACCV, author = {Sasaya, Tenta and Yamamoto, Shintaro and Ida, Takashi and Takimoto, Takahiro}, title = {Contrastive Learning using Synthetic Images Generated from Real Images}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {887-903} }
iS-MAP: Neural Implicit Mapping and Positioning for Structural Environments: Haocheng Wang,

Yanlong Cao,

Yejun Shou,

Lingfeng Shen,

Xiaoyao Wei,

Zhijie Xu,

Kai Ren; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2024_ACCV, author = {Wang, Haocheng and Cao, Yanlong and Shou, Yejun and Shen, Lingfeng and Wei, Xiaoyao and Xu, Zhijie and Ren, Kai}, title = {iS-MAP: Neural Implicit Mapping and Positioning for Structural Environments}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {747-763} }
A Universal Structure of YOLO Series Small Object Detection Models: Shengchao Hu,

Xiao Liu,

Weijun Wang,

Tianlun Huang,

Wei Feng; [pdf]
[bibtex]
@InProceedings{Hu_2024_ACCV, author = {Hu, Shengchao and Liu, Xiao and Wang, Weijun and Huang, Tianlun and Feng, Wei}, title = {A Universal Structure of YOLO Series Small Object Detection Models}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3706-3722} }
Decoupled DETR For Few-shot Object Detection: Zeyu Shangguan,

Lian Huai,

Tong Liu,

Yuyu Liu,

Xingqun Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shangguan_2024_ACCV, author = {Shangguan, Zeyu and Huai, Lian and Liu, Tong and Liu, Yuyu and Jiang, Xingqun}, title = {Decoupled DETR For Few-shot Object Detection}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {286-302} }
GaitW: Enhancing Gait Recognition in the Wild using Dynamic Information: Daksh Thapar,

Jayesh Chaudhari,

Sunny Manchanda,

Aditya Nigam,

Chetan Arora; [pdf] [supp]
[bibtex]
@InProceedings{Thapar_2024_ACCV, author = {Thapar, Daksh and Chaudhari, Jayesh and Manchanda, Sunny and Nigam, Aditya and Arora, Chetan}, title = {GaitW: Enhancing Gait Recognition in the Wild using Dynamic Information}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {268-285} }
ELLAR: An Action Recognition Dataset for Extremely Low-Light Conditions with Dual Gamma Adaptive Modulation: Minse Ha,

Wan-Gi Bae,

Geunyoung Bae,

Jong Taek Lee; [pdf] [supp]
[bibtex]
@InProceedings{Ha_2024_ACCV, author = {Ha, Minse and Bae, Wan-Gi and Bae, Geunyoung and Lee, Jong Taek}, title = {ELLAR: An Action Recognition Dataset for Extremely Low-Light Conditions with Dual Gamma Adaptive Modulation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {800-817} }
EmoTalker: Audio Driven Emotion Aware Talking Head Generation: Xiaoqian Shen,

Faizan Farooq Khan,

Mohamed Elhoseiny; [pdf] [supp]
[bibtex]
@InProceedings{Shen_2024_ACCV, author = {Shen, Xiaoqian and Khan, Faizan Farooq and Elhoseiny, Mohamed}, title = {EmoTalker: Audio Driven Emotion Aware Talking Head Generation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1900-1917} }
Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning: Bin Ren,

Guofeng Mei,

Danda Pani Paudel,

Weijie Wang,

Yawei Li,

Mengyuan Liu,

Rita Cucchiara,

Luc Van Gool,

Nicu Sebe; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ren_2024_ACCV, author = {Ren, Bin and Mei, Guofeng and Paudel, Danda Pani and Wang, Weijie and Li, Yawei and Liu, Mengyuan and Cucchiara, Rita and Van Gool, Luc and Sebe, Nicu}, title = {Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2034-2052} }
Dense Trajectory Fields: Consistent and Efficient Spatio-Temporal Pixel Tracking: Marc Tournadre,

Catherine Soladié,

Nicolas Stoiber,

Pierre-Yves Richard; [pdf]
[bibtex]
@InProceedings{Tournadre_2024_ACCV, author = {Tournadre, Marc and Soladi\'e, Catherine and Stoiber, Nicolas and Richard, Pierre-Yves}, title = {Dense Trajectory Fields: Consistent and Efficient Spatio-Temporal Pixel Tracking}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2212-2230} }
Dual Memory Networks Guided Reverse Distillation for Unsupervised Anomaly Detection: Chi Dai Tran,

Long Hoang Pham,

Duong Nguyen-Ngoc Tran,

Quoc Pham-Nam Ho,

Jae Wook Jeon; [pdf] [supp]
[bibtex]
@InProceedings{Tran_2024_ACCV, author = {Tran, Chi Dai and Pham, Long Hoang and Tran, Duong Nguyen-Ngoc and Ho, Quoc Pham-Nam and Jeon, Jae Wook}, title = {Dual Memory Networks Guided Reverse Distillation for Unsupervised Anomaly Detection}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2650-2666} }
BiEfficient: Bidirectionally Prompting Vision-Language Models for Parameter-Efficient Video Recognition: Haichen He,

Weibin Liu,

Weiwei Xing; [pdf]
[bibtex]
@InProceedings{He_2024_ACCV, author = {He, Haichen and Liu, Weibin and Xing, Weiwei}, title = {BiEfficient: Bidirectionally Prompting Vision-Language Models for Parameter-Efficient Video Recognition}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {108-125} }
Event-based Image Enhancement Under High Dynamic Range Scenarios: Jingchong Weng,

Boyang Li,

Kai Huang; [pdf]
[bibtex]
@InProceedings{Weng_2024_ACCV, author = {Weng, Jingchong and Li, Boyang and Huang, Kai}, title = {Event-based Image Enhancement Under High Dynamic Range Scenarios}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2456-2470} }
PARNet: Aortic Reconstruction from Orthogonal X-rays Using Pre-Trained Generative Adversarial Networks: Chengwei Cao,

Jinhui Zhang,

Yueyang Gao,

Zheng Li; [pdf] [supp]
[bibtex]
@InProceedings{Cao_2024_ACCV, author = {Cao, Chengwei and Zhang, Jinhui and Gao, Yueyang and Li, Zheng}, title = {PARNet: Aortic Reconstruction from Orthogonal X-rays Using Pre-Trained Generative Adversarial Networks}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {852-869} }
Multi-path Segmentation Network Based on CNN and Transformer for Skin Lesion Image: Tianyu Nie,

Yishi Zhao,

Shihong Yao; [pdf]
[bibtex]
@InProceedings{Nie_2024_ACCV, author = {Nie, Tianyu and Zhao, Yishi and Yao, Shihong}, title = {Multi-path Segmentation Network Based on CNN and Transformer for Skin Lesion Image}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3137-3153} }
Hi-NeRF: Hybridizing 2D Inpainting with Neural Radiance Fields for 3D Scene Inpainting: Xianliang Huang,

Shuhang Chen,

Zhizhou Zhong,

Jiajie Gou,

Jihong Guan,

Shuigeng Zhou; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2024_ACCV, author = {Huang, Xianliang and Chen, Shuhang and Zhong, Zhizhou and Gou, Jiajie and Guan, Jihong and Zhou, Shuigeng}, title = {Hi-NeRF: Hybridizing 2D Inpainting with Neural Radiance Fields for 3D Scene Inpainting}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2855-2871} }
Adaptive Bias Discovery for Learning Debiased Classifier: Jun-Hyun Bae,

Minho Lee,

Heechul Jung; [pdf] [supp]
[bibtex]
@InProceedings{Bae_2024_ACCV, author = {Bae, Jun-Hyun and Lee, Minho and Jung, Heechul}, title = {Adaptive Bias Discovery for Learning Debiased Classifier}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3074-3090} }
FocusNet: Cascaded Lightweight Networks and Ascending Feature Enhancement for Efficient Salient Object Detection: Chiheng Zhou,

Yongxia Zhou,

Chen Pan; [pdf]
[bibtex]
@InProceedings{Zhou_2024_ACCV, author = {Zhou, Chiheng and Zhou, Yongxia and Pan, Chen}, title = {FocusNet: Cascaded Lightweight Networks and Ascending Feature Enhancement for Efficient Salient Object Detection}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2388-2403} }
InstantGeoAvatar: Effective Geometry and Appearance Modeling of Animatable Avatars from Monocular Video: Alvaro Budria,

Adrian Lopez-Rodriguez,

Òscar Lorente,

Francesc Moreno-Noguer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Budria_2024_ACCV, author = {Budria, Alvaro and Lopez-Rodriguez, Adrian and Lorente, \`Oscar and Moreno-Noguer, Francesc}, title = {InstantGeoAvatar: Effective Geometry and Appearance Modeling of Animatable Avatars from Monocular Video}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1827-1848} }
Neural Substitution for Branch-level Network Re-parameterization: Seungmin Oh,

Jongbin Ryu; [pdf] [supp]
[bibtex]
@InProceedings{Oh_2024_ACCV, author = {Oh, Seungmin and Ryu, Jongbin}, title = {Neural Substitution for Branch-level Network Re-parameterization}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {959-975} }
ATTIQA: Generalizable Image Quality Feature Extractor using Attribute-aware Pretraining: Daekyu Kwon,

Dongyoung Kim,

Sehwan Ki,

Younghyun Jo,

Hyong-Euk Lee,

Seon Joo Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kwon_2024_ACCV, author = {Kwon, Daekyu and Kim, Dongyoung and Ki, Sehwan and Jo, Younghyun and Lee, Hyong-Euk and Kim, Seon Joo}, title = {ATTIQA: Generalizable Image Quality Feature Extractor using Attribute-aware Pretraining}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4526-4543} }
Seeing Through Expert's Eyes: Leveraging Radiologist Eye Gaze and Speech Report with Graph Neural Networks for Chest X-ray Image Classification: Jamalia Sultana,

Ruwen Qin,

Zhaozheng Yin; [pdf]
[bibtex]
@InProceedings{Sultana_2024_ACCV, author = {Sultana, Jamalia and Qin, Ruwen and Yin, Zhaozheng}, title = {Seeing Through Expert's Eyes: Leveraging Radiologist Eye Gaze and Speech Report with Graph Neural Networks for Chest X-ray Image Classification}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2579-2595} }
Instance-Dependent Noise Refinement in Segment Anything Model for Weakly Supervised Object Detection: Fariborz Taherkhani,

Ehsan Kazemi; [pdf]
[bibtex]
@InProceedings{Taherkhani_2024_ACCV, author = {Taherkhani, Fariborz and Kazemi, Ehsan}, title = {Instance-Dependent Noise Refinement in Segment Anything Model for Weakly Supervised Object Detection}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4505-4525} }
HARD : Hardware-Aware lightweight Real-time semantic segmentation model Deployable from Edge to GPU: YoungWook Kwon,

WanSoo Kim,

HyunJin Kim; [pdf] [supp]
[bibtex]
@InProceedings{Kwon_2024_ACCV, author = {Kwon, YoungWook and Kim, WanSoo and Kim, HyunJin}, title = {HARD : Hardware-Aware lightweight Real-time semantic segmentation model Deployable from Edge to GPU}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3552-3569} }
TAPS: Temporal Attention-based Pruning and Scaling for Efficient Video Action Recognition: Yonatan Dinai,

Avraham Raviv,

Nimrod Harel,

Donghoon Kim,

Ishay Goldin,

Niv Zehngut; [pdf]
[bibtex]
@InProceedings{Dinai_2024_ACCV, author = {Dinai, Yonatan and Raviv, Avraham and Harel, Nimrod and Kim, Donghoon and Goldin, Ishay and Zehngut, Niv}, title = {TAPS: Temporal Attention-based Pruning and Scaling for Efficient Video Action Recognition}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3803-3818} }
Vision language models are blind: Pooyan Rahmanzadehgervi,

Logan Bolton,

Mohammad Reza Taesiri,

Anh Totti Nguyen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rahmanzadehgervi_2024_ACCV, author = {Rahmanzadehgervi, Pooyan and Bolton, Logan and Taesiri, Mohammad Reza and Nguyen, Anh Totti}, title = {Vision language models are blind}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {18-34} }
Bridging the Projection Gap: Overcoming Projection Bias Through Parameterized Distance Learning: Chong Zhang,

Mingyu Jin,

Qinkai Yu,

Haochen Xue,

Shreyank N Gowda,

Xiaobo Jin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_ACCV, author = {Zhang, Chong and Jin, Mingyu and Yu, Qinkai and Xue, Haochen and Gowda, Shreyank N and Jin, Xiaobo}, title = {Bridging the Projection Gap: Overcoming Projection Bias Through Parameterized Distance Learning}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3327-3343} }
RD-Diff: RLTransformer-based Diffusion Model with Diversity-Inducing Modulator for Human Motion Prediction: Haosong Zhang,

Mei Chee Leong,

Liyuan Li,

Weisi Lin; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_ACCV, author = {Zhang, Haosong and Leong, Mei Chee and Li, Liyuan and Lin, Weisi}, title = {RD-Diff: RLTransformer-based Diffusion Model with Diversity-Inducing Modulator for Human Motion Prediction}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3531-3551} }
CCNDF: Curvature Constrained Neural Distance Fields from 3D LiDAR Sequences: Akshit Singh,

Karan Bhakuni,

Rajendra Nagar; [pdf]
[bibtex]
@InProceedings{Singh_2024_ACCV, author = {Singh, Akshit and Bhakuni, Karan and Nagar, Rajendra}, title = {CCNDF: Curvature Constrained Neural Distance Fields from 3D LiDAR Sequences}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {682-698} }
Every Shot Counts: Using Exemplars for Repetition Counting in Videos: Saptarshi Sinha,

Alexandros Stergiou,

Dima Damen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sinha_2024_ACCV, author = {Sinha, Saptarshi and Stergiou, Alexandros and Damen, Dima}, title = {Every Shot Counts: Using Exemplars for Repetition Counting in Videos}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3056-3073} }
Co-Segmentation without any Pixel-level Supervision with Application to Large-Scale Sketch Classification: Nikolaos-Antonios Ypsilantis,

Ondřej Chum; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ypsilantis_2024_ACCV, author = {Ypsilantis, Nikolaos-Antonios and Chum, Ond\v{r}ej}, title = {Co-Segmentation without any Pixel-level Supervision with Application to Large-Scale Sketch Classification}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1849-1865} }
EffiSeaNet: Pioneering Lightweight Network for Underwater Salient Object Detection: Qingyao Wu,

Zhenqi Fu,

Hong Lin,

Chenyu Ma,

Xiaotong Tu,

Xinghao Ding; [pdf]
[bibtex]
@InProceedings{Wu_2024_ACCV, author = {Wu, Qingyao and Fu, Zhenqi and Lin, Hong and Ma, Chenyu and Tu, Xiaotong and Ding, Xinghao}, title = {EffiSeaNet: Pioneering Lightweight Network for Underwater Salient Object Detection}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1486-1501} }
Enhanced Super-Resolution Training via Mimicked Alignment for Real-World Scenes: Omar Elezabi,

Zongwei Wu,

Radu Timofte; [pdf] [arXiv]
[bibtex]
@InProceedings{Elezabi_2024_ACCV, author = {Elezabi, Omar and Wu, Zongwei and Timofte, Radu}, title = {Enhanced Super-Resolution Training via Mimicked Alignment for Real-World Scenes}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4122-4140} }
RayEmb: Arbitrary Landmark Detection in X-Ray Images Using Ray Embedding Subspace: Pragyan Shrestha,

Chun Xie,

Yuichi Yoshii,

Itaru Kitahara; [pdf] [supp]
[bibtex]
@InProceedings{Shrestha_2024_ACCV, author = {Shrestha, Pragyan and Xie, Chun and Yoshii, Yuichi and Kitahara, Itaru}, title = {RayEmb: Arbitrary Landmark Detection in X-Ray Images Using Ray Embedding Subspace}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {665-681} }
FG-CXR: A Radiologist-Aligned Gaze Dataset for Enhancing Interpretability in Chest X-Ray Report Generation: Trong Thang Pham,

Ngoc-Vuong Ho,

Nhat-Tan Bui,

Thinh Phan,

Patel Brijesh,

Donald Adjeroh,

Gianfranco Doretto,

Anh Nguyen,

Carol C. Wu,

Hien Nguyen,

Ngan Le; [pdf]
[bibtex]
@InProceedings{Pham_2024_ACCV, author = {Pham, Trong Thang and Ho, Ngoc-Vuong and Bui, Nhat-Tan and Phan, Thinh and Brijesh, Patel and Adjeroh, Donald and Doretto, Gianfranco and Nguyen, Anh and Wu, Carol C. and Nguyen, Hien and Le, Ngan}, title = {FG-CXR: A Radiologist-Aligned Gaze Dataset for Enhancing Interpretability in Chest X-Ray Report Generation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {941-958} }
Learning 2D Human Poses for Better 3D Lifting via Multi-Model 3D-Guidance: Sanghyeon Lee,

Yoonho Hwang,

Jong Taek Lee; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2024_ACCV, author = {Lee, Sanghyeon and Hwang, Yoonho and Lee, Jong Taek}, title = {Learning 2D Human Poses for Better 3D Lifting via Multi-Model 3D-Guidance}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3344-3361} }
Enhancing Photo Animation: Augmented Stylistic Modules and Prior Knowledge Integration: Zhanyi Lu,

Yue Zhou,

Ao Chen; [pdf] [supp]
[bibtex]
@InProceedings{Lu_2024_ACCV, author = {Lu, Zhanyi and Zhou, Yue and Chen, Ao}, title = {Enhancing Photo Animation: Augmented Stylistic Modules and Prior Knowledge Integration}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1470-1485} }
Sparse Domain Transfer via Elastic Net Regularization: Jingwei Zhang,

Farzan Farnia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_ACCV, author = {Zhang, Jingwei and Farnia, Farzan}, title = {Sparse Domain Transfer via Elastic Net Regularization}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {454-470} }
Redefining Normal: A Novel Object-Level Approach for Multi-Object Novelty Detection: Mohammadreza Salehi,

Nikolaos Apostolikas Efstratios Gavves,

Cees G. M. Snoek,

Yuki M. Asano; [pdf] [supp]
[bibtex]
@InProceedings{Salehi_2024_ACCV, author = {Salehi, Mohammadreza and Gavves, Nikolaos Apostolikas Efstratios and Snoek, Cees G. M. and Asano, Yuki M.}, title = {Redefining Normal: A Novel Object-Level Approach for Multi-Object Novelty Detection}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {402-418} }
TranSPORTmer: A Holistic Approach to Trajectory Understanding in Multi-Agent Sports: Guillem Capellera,

Luis Ferraz,

Antonio Rubio,

Antonio Agudo,

Francesc Moreno-Noguer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Capellera_2024_ACCV, author = {Capellera, Guillem and Ferraz, Luis and Rubio, Antonio and Agudo, Antonio and Moreno-Noguer, Francesc}, title = {TranSPORTmer: A Holistic Approach to Trajectory Understanding in Multi-Agent Sports}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1652-1670} }
Bridging Optimal Transport and Jacobian Regularization by Optimal Trajectory for Enhanced Adversarial Defense: Binh M. Le,

Shahroz Tariq,

Simon S. Woo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Le_2024_ACCV, author = {Le, Binh M. and Tariq, Shahroz and Woo, Simon S.}, title = {Bridging Optimal Transport and Jacobian Regularization by Optimal Trajectory for Enhanced Adversarial Defense}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {419-435} }
Guide3D: A Bi-planar X-ray Dataset for Guidewire Segmentation and 3D Reconstruction: Tudor Jianu,

Baoru Huang,

Hoan Nguyen,

Binod Bhattarai,

Tuong Do,

Erman Tjiputra,

Quang Tran,

Pierre Berthet-Rayne,

Ngan Le,

Sebastiano Fichera,

Anh Nguyen; [pdf]
[bibtex]
@InProceedings{Jianu_2024_ACCV, author = {Jianu, Tudor and Huang, Baoru and Nguyen, Hoan and Bhattarai, Binod and Do, Tuong and Tjiputra, Erman and Tran, Quang and Berthet-Rayne, Pierre and Le, Ngan and Fichera, Sebastiano and Nguyen, Anh}, title = {Guide3D: A Bi-planar X-ray Dataset for Guidewire Segmentation and 3D Reconstruction}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1549-1565} }
DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention: NguyenHuu BaoLong,

Chenyu Zhang,

Yuzhi Shi,

Tsubasa Hirakawa,

Takayoshi Yamashita,

Tohgoroh Matsui,

Hironobu Fujiyoshi; [pdf]
[bibtex]
@InProceedings{BaoLong_2024_ACCV, author = {BaoLong, NguyenHuu and Zhang, Chenyu and Shi, Yuzhi and Hirakawa, Tsubasa and Yamashita, Takayoshi and Matsui, Tohgoroh and Fujiyoshi, Hironobu}, title = {DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4455-4472} }
MGNiceNet: Unified Monocular Geometric Scene Understanding: Markus Schön,

Michael Buchholz,

Klaus Dietmayer; [pdf] [supp]
[bibtex]
@InProceedings{Schon_2024_ACCV, author = {Sch\"on, Markus and Buchholz, Michael and Dietmayer, Klaus}, title = {MGNiceNet: Unified Monocular Geometric Scene Understanding}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1502-1519} }
Window-based Channel Attention for Wavelet-enhanced Learned Image Compression: Heng Xu,

Bowen Hai,

Yushun Tang,

Zhihai He; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2024_ACCV, author = {Xu, Heng and Hai, Bowen and Tang, Yushun and He, Zhihai}, title = {Window-based Channel Attention for Wavelet-enhanced Learned Image Compression}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4334-4351} }
Dual Prototype-driven Objectness Decoupling for Cross-Domain Object Detection in Urban Scene: Taehoon Kim,

Jaemin Na,

Joong-won Hwang,

Hyung Jin Chang,

Wonjun Hwang; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2024_ACCV, author = {Kim, Taehoon and Na, Jaemin and Hwang, Joong-won and Chang, Hyung Jin and Hwang, Wonjun}, title = {Dual Prototype-driven Objectness Decoupling for Cross-Domain Object Detection in Urban Scene}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1148-1165} }
FOTV-HQS: A Fractional-Order Total Variation Model for LiDAR Super-Resolution with Deep Unfolding Network: Huiying Xi,

Xia Yuan,

Shiwei Wu,

Runze Geng,

Kaiyang Wang,

Yongshun Liang,

Chunxia Zhao; [pdf] [supp]
[bibtex]
@InProceedings{Xi_2024_ACCV, author = {Xi, Huiying and Yuan, Xia and Wu, Shiwei and Geng, Runze and Wang, Kaiyang and Liang, Yongshun and Zhao, Chunxia}, title = {FOTV-HQS: A Fractional-Order Total Variation Model for LiDAR Super-Resolution with Deep Unfolding Network}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4034-4050} }
NT-VOT211: A Large-Scale Benchmark for Night-time Visual Object Tracking: Yu Liu,

Arif Mahmood,

Muhammad Haris Khan; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2024_ACCV, author = {Liu, Yu and Mahmood, Arif and Khan, Muhammad Haris}, title = {NT-VOT211: A Large-Scale Benchmark for Night-time Visual Object Tracking}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {194-212} }
StreamMOTP: Streaming and Unified Framework for Joint 3D Multi-Object Tracking and Trajectory Prediction: Jiaheng Zhuang,

Guoan Wang,

Siyu Zhang,

Xiyang Wang,

Hangning Zhou,

Ziyao Xu,

Chi Zhang,

Zhiheng Li; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhuang_2024_ACCV, author = {Zhuang, Jiaheng and Wang, Guoan and Zhang, Siyu and Wang, Xiyang and Zhou, Hangning and Xu, Ziyao and Zhang, Chi and Li, Zhiheng}, title = {StreamMOTP: Streaming and Unified Framework for Joint 3D Multi-Object Tracking and Trajectory Prediction}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3189-3205} }
3D Adaptive Structural Convolution Network for Domain-Invariant Point Cloud Recognition: Younggun Kim,

Soomok Lee; [pdf] [arXiv]
[bibtex]
@InProceedings{Kim_2024_ACCV, author = {Kim, Younggun and Lee, Soomok}, title = {3D Adaptive Structural Convolution Network for Domain-Invariant Point Cloud Recognition}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2002-2017} }
Knowledge Distillation Dealing with Sample-wise Long-tail Problem: Tao Yu,

Xu Zhao,

Yongqi An,

Ming Tang,

Jinqiao Wang; [pdf]
[bibtex]
@InProceedings{Yu_2024_ACCV, author = {Yu, Tao and Zhao, Xu and An, Yongqi and Tang, Ming and Wang, Jinqiao}, title = {Knowledge Distillation Dealing with Sample-wise Long-tail Problem}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2354-2370} }
Mamba-based Light Field Super-Resolution with Efficient Subspace Scanning: Ruisheng Gao,

Zeyu Xiao,

Zhiwei Xiong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2024_ACCV, author = {Gao, Ruisheng and Xiao, Zeyu and Xiong, Zhiwei}, title = {Mamba-based Light Field Super-Resolution with Efficient Subspace Scanning}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {531-547} }
NewMove: Customizing text-to-video models with novel motions: Joanna Materzyńska,

Josef Sivic,

Eli Shechtman,

Antonio Torralba,

Richard Zhang,

Bryan Russell; [pdf] [supp]
[bibtex]
@InProceedings{Materzynska_2024_ACCV, author = {Materzy\'nska, Joanna and Sivic, Josef and Shechtman, Eli and Torralba, Antonio and Zhang, Richard and Russell, Bryan}, title = {NewMove: Customizing text-to-video models with novel motions}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1634-1651} }
QR-DETR : Query Routing for Detection Transformer: Tharsan Senthivel,

Ngoc-Son Vu; [pdf]
[bibtex]
@InProceedings{Senthivel_2024_ACCV, author = {Senthivel, Tharsan and Vu, Ngoc-Son}, title = {QR-DETR : Query Routing for Detection Transformer}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {354-371} }
SurfOcc: Surface-based Feature Lifting for Vision-centric 3D Occupancy Prediction: Tonghui Ye,

Zhi Gao,

Zhipeng Lin,

Xinyi Liu,

Ronghe Jin; [pdf]
[bibtex]
@InProceedings{Ye_2024_ACCV, author = {Ye, Tonghui and Gao, Zhi and Lin, Zhipeng and Liu, Xinyi and Jin, Ronghe}, title = {SurfOcc: Surface-based Feature Lifting for Vision-centric 3D Occupancy Prediction}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2421-2438} }
Hierarchical Prompting for Diffusion Classifiers: Wenxin Ning,

Dongliang Chang,

Yujun Tong,

Zhongjiang He,

Kongming Liang,

Zhanyu Ma; [pdf] [supp]
[bibtex]
@InProceedings{Ning_2024_ACCV, author = {Ning, Wenxin and Chang, Dongliang and Tong, Yujun and He, Zhongjiang and Liang, Kongming and Ma, Zhanyu}, title = {Hierarchical Prompting for Diffusion Classifiers}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1284-1300} }
Enhanced Asymmetric Invertible Network for Neural Video Delivery: Wenbin Tian,

Qingmiao Jiang,

Lu Chen,

Haolin Li,

Jinyao Yan; [pdf]
[bibtex]
@InProceedings{Tian_2024_ACCV, author = {Tian, Wenbin and Jiang, Qingmiao and Chen, Lu and Li, Haolin and Yan, Jinyao}, title = {Enhanced Asymmetric Invertible Network for Neural Video Delivery}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2751-2766} }
DepthSegNet24: A Label-Free Model for Robust Day-Night Depth and Semantics: Phan Thi Huyen Thanh,

The Hiep Nguyen,

Minh Huy Vu Nguyen,

Trung Thai Tran,

Tran Vu Pham,

Duc Dung Nguyen,

Truong Vinh Truong Duy,

Natori Naotake; [pdf] [supp]
[bibtex]
@InProceedings{Thanh_2024_ACCV, author = {Thanh, Phan Thi Huyen and Nguyen, The Hiep and Nguyen, Minh Huy Vu and Tran, Trung Thai and Pham, Tran Vu and Nguyen, Duc Dung and Duy, Truong Vinh Truong and Naotake, Natori}, title = {DepthSegNet24: A Label-Free Model for Robust Day-Night Depth and Semantics}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2716-2733} }
DiffLoss: Unleashing Diffusion Model as Constraint for Training Image Restoration Network: Jiangtong Tan,

Hu Yu,

Jie Huang,

Zizheng Yang,

Feng Zhao; [pdf] [supp]
[bibtex]
@InProceedings{Tan_2024_ACCV, author = {Tan, Jiangtong and Yu, Hu and Huang, Jie and Yang, Zizheng and Zhao, Feng}, title = {DiffLoss: Unleashing Diffusion Model as Constraint for Training Image Restoration Network}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1566-1584} }
3D Prompt Learning for RGB-D Tracking: Bocen Li,

Yunzhi Zhuge,

Shan Jiang,

Lijun Wang,

Yifan Wang,

Huchuan Lu; [pdf] [supp]
[bibtex]
@InProceedings{Li_2024_ACCV, author = {Li, Bocen and Zhuge, Yunzhi and Jiang, Shan and Wang, Lijun and Wang, Yifan and Lu, Huchuan}, title = {3D Prompt Learning for RGB-D Tracking}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2527-2544} }
TANet: Triplet Attention Network for All-In-One Adverse Weather Image Restoration: Hsing-Hua Wang,

Fu-Jen Tsai,

Yen-Yu Lin,

Chia-Wen Lin; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2024_ACCV, author = {Wang, Hsing-Hua and Tsai, Fu-Jen and Lin, Yen-Yu and Lin, Chia-Wen}, title = {TANet: Triplet Attention Network for All-In-One Adverse Weather Image Restoration}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {835-851} }
PMTrack: Multi-object Tracking with Motion-Aware: Xu Guo,

Yujin Zheng,

Dingwen Wang; [pdf]
[bibtex]
@InProceedings{Guo_2024_ACCV, author = {Guo, Xu and Zheng, Yujin and Wang, Dingwen}, title = {PMTrack: Multi-object Tracking with Motion-Aware}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3091-3106} }
Designing Extremely Memory-Efficient CNNs for On-device Vision Tasks: Jaewook Lee,

Yoel Park,

Seulki Lee; [pdf] [arXiv]
[bibtex]
@InProceedings{Lee_2024_ACCV, author = {Lee, Jaewook and Park, Yoel and Lee, Seulki}, title = {Designing Extremely Memory-Efficient CNNs for On-device Vision Tasks}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {303-318} }
A Multi-Phase Multi-Graph Approach for Focal Liver Lesion Classification on CT Scans: Tran Bao Sam,

Ta Duc Huy,

Cong Tuyen Dao,

Thanh Tin Lam,

Van Ha Tang,

Steven Q.H. Truong; [pdf]
[bibtex]
@InProceedings{Sam_2024_ACCV, author = {Sam, Tran Bao and Huy, Ta Duc and Dao, Cong Tuyen and Lam, Thanh Tin and Tang, Van Ha and Truong, Steven Q.H.}, title = {A Multi-Phase Multi-Graph Approach for Focal Liver Lesion Classification on CT Scans}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3788-3802} }
A Recipe for CAC: Mosaic-based Generalized Loss for Improved Class-Agnostic Counting: Tsung-Han Chou,

Brian Wang,

Wei-Chen Chiu,

Jun-Cheng Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chou_2024_ACCV, author = {Chou, Tsung-Han and Wang, Brian and Chiu, Wei-Chen and Chen, Jun-Cheng}, title = {A Recipe for CAC: Mosaic-based Generalized Loss for Improved Class-Agnostic Counting}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2906-2921} }
RS-SAM: Integrating Multi-Scale Information for Enhanced Remote Sensing Image Segmentation: Enkai Zhang,

Jingjing Liu,

Anda Cao,

Zhen Sun,

Haofei Zhang,

Huiqiong Wang,

Li Sun,

Mingli Song; [pdf]
[bibtex]
@InProceedings{Zhang_2024_ACCV, author = {Zhang, Enkai and Liu, Jingjing and Cao, Anda and Sun, Zhen and Zhang, Haofei and Wang, Huiqiong and Sun, Li and Song, Mingli}, title = {RS-SAM: Integrating Multi-Scale Information for Enhanced Remote Sensing Image Segmentation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {994-1010} }
VIPNet: Combining Viewpoint Information and Shape Priors for Instant Multi-View 3D Reconstruction: Weining Ye,

Zhixuan Li,

Tingting Jiang; [pdf] [supp]
[bibtex]
@InProceedings{Ye_2024_ACCV, author = {Ye, Weining and Li, Zhixuan and Jiang, Tingting}, title = {VIPNet: Combining Viewpoint Information and Shape Priors for Instant Multi-View 3D Reconstruction}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3379-3395} }
Leveraging Semantic Cues from Foundation Vision Models for Enhanced Local Feature Correspondence: Felipe Cadar,

Guilherme Potje,

Renato Martins,

Cédric Demonceaux,

Erickson R. Nascimento; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cadar_2024_ACCV, author = {Cadar, Felipe and Potje, Guilherme and Martins, Renato and Demonceaux, C\'edric and Nascimento, Erickson R.}, title = {Leveraging Semantic Cues from Foundation Vision Models for Enhanced Local Feature Correspondence}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1268-1283} }
SAMIF: Adapting Segment Anything Model for Image Inpainting Forensics: Lan Zhang,

Xinshan Zhu,

Di He,

Xin Liao,

Biao Sun; [pdf]
[bibtex]
@InProceedings{Zhang_2024_ACCV, author = {Zhang, Lan and Zhu, Xinshan and He, Di and Liao, Xin and Sun, Biao}, title = {SAMIF: Adapting Segment Anything Model for Image Inpainting Forensics}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3605-3621} }
Language-Guided Joint Audio-Visual Editing via One-Shot Adaptation: Susan Liang,

Chao Huang,

Yapeng Tian,

Anurag Kumar,

Chenliang Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liang_2024_ACCV, author = {Liang, Susan and Huang, Chao and Tian, Yapeng and Kumar, Anurag and Xu, Chenliang}, title = {Language-Guided Joint Audio-Visual Editing via One-Shot Adaptation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1011-1027} }
Faster convergence and Uncorrelated gradients in Self-Supervised Online Continual Learning: Koyo Imai,

Naoto Hayashi,

Tsubasa Hirakawa,

Takayoshi Yamashita,

Hironobu Fujiyoshi; [pdf] [supp]
[bibtex]
@InProceedings{Imai_2024_ACCV, author = {Imai, Koyo and Hayashi, Naoto and Hirakawa, Tsubasa and Yamashita, Takayoshi and Fujiyoshi, Hironobu}, title = {Faster convergence and Uncorrelated gradients in Self-Supervised Online Continual Learning}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {436-453} }
Dynamic Window Transformer for Image Super-Resolution: Zheng Xie,

Zhongxun Wang,

Tianci Qin,

Zhexuan Han,

Ruoyu Zhou; [pdf]
[bibtex]
@InProceedings{Xie_2024_ACCV, author = {Xie, Zheng and Wang, Zhongxun and Qin, Tianci and Han, Zhexuan and Zhou, Ruoyu}, title = {Dynamic Window Transformer for Image Super-Resolution}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3836-3850} }
Direct Alignment for Robust NeRF Learning: Ravi Garg,

Shin-Fang Chng,

Simon Lucey; [pdf] [supp]
[bibtex]
@InProceedings{Garg_2024_ACCV, author = {Garg, Ravi and Chng, Shin-Fang and Lucey, Simon}, title = {Direct Alignment for Robust NeRF Learning}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3947-3963} }
More and Larger Auxiliary Feature-Guided Spatial-Temporal Super-Resolution for Rendered Sequences: Lijie Zheng,

Xiao Liang; [pdf]
[bibtex]
@InProceedings{Zheng_2024_ACCV, author = {Zheng, Lijie and Liang, Xiao}, title = {More and Larger Auxiliary Feature-Guided Spatial-Temporal Super-Resolution for Rendered Sequences}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1986-2001} }
Strike the Balance: On-the-Fly Uncertainty based User Interactions for Long-Term Video Object Segmentation: Stéphane Vujasinović,

Stefan Becker,

Sebastian Bullinger,

Norbert Scherer-Negenborn,

Michael Arens,

Rainer Stiefelhagen; [pdf] [supp]
[bibtex]
@InProceedings{Vujasinovic_2024_ACCV, author = {Vujasinovi\'c, St\'ephane and Becker, Stefan and Bullinger, Sebastian and Scherer-Negenborn, Norbert and Arens, Michael and Stiefelhagen, Rainer}, title = {Strike the Balance: On-the-Fly Uncertainty based User Interactions for Long-Term Video Object Segmentation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2784-2802} }
Unsupervised Video Summarization via Iterative Training and Simplified GAN: Hanqing Li,

Diego Klabjan,

Jean Utke; [pdf] [supp]
[bibtex]
@InProceedings{Li_2024_ACCV, author = {Li, Hanqing and Klabjan, Diego and Utke, Jean}, title = {Unsupervised Video Summarization via Iterative Training and Simplified GAN}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1585-1601} }
Generalizable Structure-Aware INF: Biplanar-View CT Reconstruction via Disentangled Implicit Neural Field: Bei Huang,

Yuru Pei; [pdf]
[bibtex]
@InProceedings{Huang_2024_ACCV, author = {Huang, Bei and Pei, Yuru}, title = {Generalizable Structure-Aware INF: Biplanar-View CT Reconstruction via Disentangled Implicit Neural Field}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {699-715} }
MECFormer: Multi-task Whole Slide Image Classification with Expert Consultation Network: Doanh C. Bui,

Jin Tae Kwak; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bui_2024_ACCV, author = {Bui, Doanh C. and Kwak, Jin Tae}, title = {MECFormer: Multi-task Whole Slide Image Classification with Expert Consultation Network}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1602-1617} }
SRIL: Selective Regularization for Class-Incremental Learning: Jisu Han,

Jaemin Na,

Wonjun Hwang; [pdf] [arXiv]
[bibtex]
@InProceedings{Han_2024_ACCV, author = {Han, Jisu and Na, Jaemin and Hwang, Wonjun}, title = {SRIL: Selective Regularization for Class-Incremental Learning}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1532-1548} }
DeTurb: Atmospheric Turbulence Mitigation with Deformable 3D Convolutions and 3D Swin Transformers: Zhicheng Zou,

Nantheera Anantrasirichai; [pdf] [arXiv]
[bibtex]
@InProceedings{Zou_2024_ACCV, author = {Zou, Zhicheng and Anantrasirichai, Nantheera}, title = {DeTurb: Atmospheric Turbulence Mitigation with Deformable 3D Convolutions and 3D Swin Transformers}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {904-921} }
DepthBLIP-2: Leveraging Language to Guide BLIP-2 in Understanding Depth Information: Wei Chen,

Changyong Shi,

Chuanxiang Ma,

Wenhao Li,

Shulei Dong; [pdf]
[bibtex]
@InProceedings{Chen_2024_ACCV, author = {Chen, Wei and Shi, Changyong and Ma, Chuanxiang and Li, Wenhao and Dong, Shulei}, title = {DepthBLIP-2: Leveraging Language to Guide BLIP-2 in Understanding Depth Information}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2939-2953} }
Learning Neural Radiance Field from Quasi-Uniformly Sampled Spherical Image for Immersive Virtual Reality: Le Wang,

Shigang Li; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2024_ACCV, author = {Wang, Le and Li, Shigang}, title = {Learning Neural Radiance Field from Quasi-Uniformly Sampled Spherical Image for Immersive Virtual Reality}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1166-1180} }
Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learning: Christoph Hümmer,

Manuel Schwonberg,

Liangwei Zhou,

Hu Cao,

Alois Knoll,

Hanno Gottschalk; [pdf] [supp]
[bibtex]
@InProceedings{Hummer_2024_ACCV, author = {H\"ummer, Christoph and Schwonberg, Manuel and Zhou, Liangwei and Cao, Hu and Knoll, Alois and Gottschalk, Hanno}, title = {Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learning}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4223-4244} }
DFIMat: Decoupled Flexible Interactive Matting in Multi-Person Scenarios: Siyi Jiao,

Wenzheng Zeng,

Changxin Gao,

Nong Sang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiao_2024_ACCV, author = {Jiao, Siyi and Zeng, Wenzheng and Gao, Changxin and Sang, Nong}, title = {DFIMat: Decoupled Flexible Interactive Matting in Multi-Person Scenarios}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2988-3004} }
Multiple active stereo systems calibration method based on Neural SDF using DSSS for wide area 3D reconstruction: Kota Nishihara,

Ryo Furukawa,

Ryusuke Sagawa,

Hiroshi Kawasaki; [pdf]
[bibtex]
@InProceedings{Nishihara_2024_ACCV, author = {Nishihara, Kota and Furukawa, Ryo and Sagawa, Ryusuke and Kawasaki, Hiroshi}, title = {Multiple active stereo systems calibration method based on Neural SDF using DSSS for wide area 3D reconstruction}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2838-2854} }
S2Net: Skeleton-aware SlowFast Network for Efficient Sign Language Recognition: Yifan Yang,

Yuecong Min,

Xilin Chen; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2024_ACCV, author = {Yang, Yifan and Min, Yuecong and Chen, Xilin}, title = {S2Net: Skeleton-aware SlowFast Network for Efficient Sign Language Recognition}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {319-336} }
Rethinking Sampling for Music-Driven Long-Term Dance Generation: Tuong-Vy Truong-Thuy,

Gia-Cat Bui-Le,

Hai-Dang Nguyen,

Trung-Nghia Le; [pdf]
[bibtex]
@InProceedings{Truong-Thuy_2024_ACCV, author = {Truong-Thuy, Tuong-Vy and Bui-Le, Gia-Cat and Nguyen, Hai-Dang and Le, Trung-Nghia}, title = {Rethinking Sampling for Music-Driven Long-Term Dance Generation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2667-2683} }
Continual Learning Improves Zero-Shot Action Recognition: Shreyank N Gowda,

Davide Moltisanti,

Laura Sevilla-Lara; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gowda_2024_ACCV, author = {Gowda, Shreyank N and Moltisanti, Davide and Sevilla-Lara, Laura}, title = {Continual Learning Improves Zero-Shot Action Recognition}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3239-3256} }
Semantic Visual-inertial SLAM for Automated Valet Parking: Seungwon Oh,

Junghoon Seo,

Jungho Park,

Viswanath Veera,

Jersha Felix,

Midhun Menon,

Chinmay Shinde; [pdf]
[bibtex]
@InProceedings{Oh_2024_ACCV, author = {Oh, Seungwon and Seo, Junghoon and Park, Jungho and Veera, Viswanath and Felix, Jersha and Menon, Midhun and Shinde, Chinmay}, title = {Semantic Visual-inertial SLAM for Automated Valet Parking}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {733-746} }
Content-Adaptive Style Transfer: A Training-Free Approach with VQ Autoencoders: Jongmin Gim,

Jihun Park,

Kyoungmin Lee,

Sunghoon Im; [pdf] [supp]
[bibtex]
@InProceedings{Gim_2024_ACCV, author = {Gim, Jongmin and Park, Jihun and Lee, Kyoungmin and Im, Sunghoon}, title = {Content-Adaptive Style Transfer: A Training-Free Approach with VQ Autoencoders}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2337-2353} }
TGCM: Cross-Domain Few-Shot Semantic Segmentation via one-shot Target Guided CutMix: HaiTao Wei,

JianMing Liu,

Tong Chen,

WenLong Qiu; [pdf]
[bibtex]
@InProceedings{Wei_2024_ACCV, author = {Wei, HaiTao and Liu, JianMing and Chen, Tong and Qiu, WenLong}, title = {TGCM: Cross-Domain Few-Shot Semantic Segmentation via one-shot Target Guided CutMix}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1065-1081} }
Latency Attack Resilience in Object Detectors: Insights from Computing Architecture: Erh-Chung Chen,

Pin-Yu Chen,

I-Hsin Chung,

Che-Rung Lee; [pdf]
[bibtex]
@InProceedings{Chen_2024_ACCV, author = {Chen, Erh-Chung and Chen, Pin-Yu and Chung, I-Hsin and Lee, Che-Rung}, title = {Latency Attack Resilience in Object Detectors: Insights from Computing Architecture}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3206-3222} }
Underground Mapping and Localization Based on Ground-Penetrating Radar: Jinchang Zhang,

Guoyu Lu; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_ACCV, author = {Zhang, Jinchang and Lu, Guoyu}, title = {Underground Mapping and Localization Based on Ground-Penetrating Radar}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2018-2033} }
Learning 3D Point Cloud Registration as a Single Optimization Problem: Rintaro Yanagi,

Atsushi Hashimoto,

Naoya Chiba,

Shusaku Sone,

Jiaxin Ma,

Yoshitaka Ushiku; [pdf] [supp]
[bibtex]
@InProceedings{Yanagi_2024_ACCV, author = {Yanagi, Rintaro and Hashimoto, Atsushi and Chiba, Naoya and Sone, Shusaku and Ma, Jiaxin and Ushiku, Yoshitaka}, title = {Learning 3D Point Cloud Registration as a Single Optimization Problem}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3292-3309} }
Amodal Instance Segmentation with Diffusion Shape Prior Estimation: Minh Tran,

Khoa Vo,

Tri Nguyen,

Ngan Le; [pdf] [arXiv]
[bibtex]
@InProceedings{Tran_2024_ACCV, author = {Tran, Minh and Vo, Khoa and Nguyen, Tri and Le, Ngan}, title = {Amodal Instance Segmentation with Diffusion Shape Prior Estimation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1181-1196} }
Polyp-SES: Automatic Polyp Segmentation with Self-Enriched Semantic Model: Quang Vinh Nguyen,

Thanh Hoang Son Vo,

Sae-Ryung Kang,

Soo-Hyung Kim; [pdf]
[bibtex]
@InProceedings{Nguyen_2024_ACCV, author = {Nguyen, Quang Vinh and Vo, Thanh Hoang Son and Kang, Sae-Ryung and Kim, Soo-Hyung}, title = {Polyp-SES: Automatic Polyp Segmentation with Self-Enriched Semantic Model}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2803-2819} }
OneDiff: A Generalist Model for Image Difference Captioning: Erdong Hu,

Longteng Guo,

Tongtian Yue,

Zijia Zhao,

Shuning Xue,

Jing Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hu_2024_ACCV, author = {Hu, Erdong and Guo, Longteng and Yue, Tongtian and Zhao, Zijia and Xue, Shuning and Liu, Jing}, title = {OneDiff: A Generalist Model for Image Difference Captioning}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2439-2455} }
MV2MP: Segmentation Free Performance Capture of Humans in Direct Physical Contact from Sparse Multi-Cam Setups: Sergei Eliseev,

Leonid Shtanko,

Rasim Akhunzianov,

Yaroslav Romanenko,

Anatoly Starostin; [pdf] [supp]
[bibtex]
@InProceedings{Eliseev_2024_ACCV, author = {Eliseev, Sergei and Shtanko, Leonid and Akhunzianov, Rasim and Romanenko, Yaroslav and Starostin, Anatoly}, title = {MV2MP: Segmentation Free Performance Capture of Humans in Direct Physical Contact from Sparse Multi-Cam Setups}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4172-4188} }
Exploiting Cross-modal Cost Volume for Multi-sensor Depth Estimation: Janghyun Kim,

Ukcheol Shin,

Seokyong Heo,

Jinsun Park; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2024_ACCV, author = {Kim, Janghyun and Shin, Ukcheol and Heo, Seokyong and Park, Jinsun}, title = {Exploiting Cross-modal Cost Volume for Multi-sensor Depth Estimation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1420-1436} }
Parameter-Efficient Instance-Adaptive Neural Video Compression: Seungjun Oh,

Hyunmo Yang,

Eunbyung Park; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Oh_2024_ACCV, author = {Oh, Seungjun and Yang, Hyunmo and Park, Eunbyung}, title = {Parameter-Efficient Instance-Adaptive Neural Video Compression}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {250-267} }
Improving Image Clustering with Artifacts Attenuation via Inference-Time Attention Engineering: Kazumoto Nakamura,

Yuji Nozawa,

Yu-Chieh Lin,

Kengo Nakata,

Youyang Ng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nakamura_2024_ACCV, author = {Nakamura, Kazumoto and Nozawa, Yuji and Lin, Yu-Chieh and Nakata, Kengo and Ng, Youyang}, title = {Improving Image Clustering with Artifacts Attenuation via Inference-Time Attention Engineering}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3396-3413} }
Enhanced Kalman with Adaptive Appearance Motion SORT for Grounded Generic Multiple Object Tracking: Duy Le Dinh Anh,

Kim Hoang Tran,

Quang-Thuc Nguyen,

Ngan Hoang Le; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Le_Dinh_Anh_2024_ACCV, author = {Le Dinh Anh, Duy and Tran, Kim Hoang and Nguyen, Quang-Thuc and Le, Ngan Hoang}, title = {Enhanced Kalman with Adaptive Appearance Motion SORT for Grounded Generic Multiple Object Tracking}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {145-161} }
LoCo-MAD: Long-Range Context-Enhanced Model Towards Plot-Centric Movie Audio Description: Jiayi Wang,

Zihao Liu,

Xiaoyu Wu; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2024_ACCV, author = {Wang, Jiayi and Liu, Zihao and Wu, Xiaoyu}, title = {LoCo-MAD: Long-Range Context-Enhanced Model Towards Plot-Centric Movie Audio Description}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1366-1383} }
Dual-path Multimodal Optimal Transport for Composed Image Retrieval: Cairong Yan,

Meng Ma,

Yanting Zhang,

Yongquan Wan; [pdf]
[bibtex]
@InProceedings{Yan_2024_ACCV, author = {Yan, Cairong and Ma, Meng and Zhang, Yanting and Wan, Yongquan}, title = {Dual-path Multimodal Optimal Transport for Composed Image Retrieval}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1741-1755} }
EDeRF: Updating Local Scenes and Editing Across Fields for Real-Time Dynamic Reconstruction of Road Scene: Zhaoxiang Liang,

Wenjun Guo,

Yi Yang,

Tong Liu; [pdf]
[bibtex]
@InProceedings{Liang_2024_ACCV, author = {Liang, Zhaoxiang and Guo, Wenjun and Yang, Yi and Liu, Tong}, title = {EDeRF: Updating Local Scenes and Editing Across Fields for Real-Time Dynamic Reconstruction of Road Scene}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3120-3136} }
Accelerated Deep Nonlinear Dictionary Learning: Benying Tan,

Jie Lin,

Yang Qin,

Shuxue Ding,

Yujie Li; [pdf]
[bibtex]
@InProceedings{Tan_2024_ACCV, author = {Tan, Benying and Lin, Jie and Qin, Yang and Ding, Shuxue and Li, Yujie}, title = {Accelerated Deep Nonlinear Dictionary Learning}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4439-4454} }
PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage: Denis Zavadski,

Damjan Kalšan,

Carsten Rother; [pdf]
[bibtex]
@InProceedings{Zavadski_2024_ACCV, author = {Zavadski, Denis and Kal\v{s}an, Damjan and Rother, Carsten}, title = {PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {922-940} }
GPNF:A Point Cloud Registration Framework Using Sharp Global Linear Attention Prior and Neighborhood Filtering Strategy: Congyang Zhu,

Mengxiao Yin,

Junjie Liao,

Zhijie Liang,

Kan Chang; [pdf] [supp]
[bibtex]
@InProceedings{Zhu_2024_ACCV, author = {Zhu, Congyang and Yin, Mengxiao and Liao, Junjie and Liang, Zhijie and Chang, Kan}, title = {GPNF:A Point Cloud Registration Framework Using Sharp Global Linear Attention Prior and Neighborhood Filtering Strategy}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2489-2506} }
Enhancing Anchor-based Weakly Supervised Referring Expression Comprehension with Cross-Modality Attention: Ting-Yu Chu,

Yong-Xiang Lin,

Ching-Chun Huang,

Kai-Lung Hua; [pdf]
[bibtex]
@InProceedings{Chu_2024_ACCV, author = {Chu, Ting-Yu and Lin, Yong-Xiang and Huang, Ching-Chun and Hua, Kai-Lung}, title = {Enhancing Anchor-based Weakly Supervised Referring Expression Comprehension with Cross-Modality Attention}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2767-2783} }
Deformable Shape-aware Point Generation for 3D Object Detection: Kai Wang,

Xiaowei Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2024_ACCV, author = {Wang, Kai and Zhang, Xiaowei}, title = {Deformable Shape-aware Point Generation for 3D Object Detection}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2699-2715} }
VideoPatchCore: An Effective Method to Memorize Normality for Video Anomaly Detection: Sunghyun Ahn,

Youngwan Jo,

Kijung Lee,

Sanghyun Park; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ahn_2024_ACCV, author = {Ahn, Sunghyun and Jo, Youngwan and Lee, Kijung and Park, Sanghyun}, title = {VideoPatchCore: An Effective Method to Memorize Normality for Video Anomaly Detection}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2179-2195} }
CNG-SFDA: Clean-and-Noisy Region Guided Online-Offline Source-Free Domain Adaptation: Hyeonwoo Cho,

Chanmin Park,

Dong-Hee Kim,

Jinyoung Kim,

Won Hwa Kim; [pdf] [supp]
[bibtex]
@InProceedings{Cho_2024_ACCV, author = {Cho, Hyeonwoo and Park, Chanmin and Kim, Dong-Hee and Kim, Jinyoung and Kim, Won Hwa}, title = {CNG-SFDA: Clean-and-Noisy Region Guided Online-Offline Source-Free Domain Adaptation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1723-1740} }
HT-SSPG:Hierarchical Transformers for Semantic Surface Point Generation in 3D Object Detection: Wenhao Kong,

Xiaowei Zhang; [pdf]
[bibtex]
@InProceedings{Kong_2024_ACCV, author = {Kong, Wenhao and Zhang, Xiaowei}, title = {HT-SSPG:Hierarchical Transformers for Semantic Surface Point Generation in 3D Object Detection}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3672-3688} }
O1O: Grouping of Known Classes to Identify Unknown Objects as Odd-One-Out: Mısra Yavuz,

Fatma Güney; [pdf] [supp]
[bibtex]
@InProceedings{Yavuz_2024_ACCV, author = {Yavuz, M{\i}sra and G\"uney, Fatma}, title = {O1O: Grouping of Known Classes to Identify Unknown Objects as Odd-One-Out}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {614-629} }
Real-SRGD: Enhancing Real-World Image Super-Resolution with Classifier-Free Guided Diffusion: Kenji Doi,

Shuntaro Okada,

Ryota Yoshihashi,

Hirokatsu Kataoka; [pdf] [supp]
[bibtex]
@InProceedings{Doi_2024_ACCV, author = {Doi, Kenji and Okada, Shuntaro and Yoshihashi, Ryota and Kataoka, Hirokatsu}, title = {Real-SRGD: Enhancing Real-World Image Super-Resolution with Classifier-Free Guided Diffusion}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3739-3755} }
HDNeXt: Hybrid Dynamic MedNeXt with Level Set Regularization for Medical Image Segmentation: Haoyu Cao,

Tianyi Han,

Yunyun Yang; [pdf]
[bibtex]
@InProceedings{Cao_2024_ACCV, author = {Cao, Haoyu and Han, Tianyi and Yang, Yunyun}, title = {HDNeXt: Hybrid Dynamic MedNeXt with Level Set Regularization for Medical Image Segmentation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {597-613} }
VIP: Versatile Image Outpainting Empowered by Multimodal Large Language Model: Jinze Yang,

Haoran Wang,

Zining Zhu,

Chenglong Liu,

Meng Wu,

Mingming Sun; [pdf] [arXiv]
[bibtex]
@InProceedings{Yang_2024_ACCV, author = {Yang, Jinze and Wang, Haoran and Zhu, Zining and Liu, Chenglong and Wu, Meng and Sun, Mingming}, title = {VIP: Versatile Image Outpainting Empowered by Multimodal Large Language Model}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1082-1099} }
Capture Concept through Comparison: Vision-and-Language Representation Learning with Intrinsic Information Mining: Yun-Zhu Song,

Yi-Syuan Chen,

Tzu-Ling Lin,

Bei Liu,

Jianlong Fu,

Hong-Han Shuai; [pdf]
[bibtex]
@InProceedings{Song_2024_ACCV, author = {Song, Yun-Zhu and Chen, Yi-Syuan and Lin, Tzu-Ling and Liu, Bei and Fu, Jianlong and Shuai, Hong-Han}, title = {Capture Concept through Comparison: Vision-and-Language Representation Learning with Intrinsic Information Mining}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4299-4317} }
Image Deraining with Frequency-Enhanced State Space Model: Shugo Yamashita,

Masaaki Ikehara; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yamashita_2024_ACCV, author = {Yamashita, Shugo and Ikehara, Masaaki}, title = {Image Deraining with Frequency-Enhanced State Space Model}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3655-3671} }
3D-Aware Instance Segmentation and Tracking in Egocentric Videos: Yash Bhalgat,

Vadim Tschernezki,

Iro Laina,

João F. Henriques,

Andrea Vedaldi,

Andrew Zisserman; [pdf] [arXiv]
[bibtex]
@InProceedings{Bhalgat_2024_ACCV, author = {Bhalgat, Yash and Tschernezki, Vadim and Laina, Iro and Henriques, Jo\~ao F. and Vedaldi, Andrea and Zisserman, Andrew}, title = {3D-Aware Instance Segmentation and Tracking in Egocentric Videos}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2562-2578} }
FedRepOpt: Gradient Re-parametrized Optimizers in Federated Learning: Kin Wai Lau,

Yasar Abbas Ur Rehman,

Pedro Porto Buarque de Gusmão,

Lai-Man Po,

Lan Ma,

Yuyang Xie; [pdf] [supp]
[bibtex]
@InProceedings{Lau_2024_ACCV, author = {Lau, Kin Wai and Rehman, Yasar Abbas Ur and de Gusm\~ao, Pedro Porto Buarque and Po, Lai-Man and Ma, Lan and Xie, Yuyang}, title = {FedRepOpt: Gradient Re-parametrized Optimizers in Federated Learning}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1866-1882} }
Facing Asymmetry - Uncovering the Causal Link between Facial Symmetry and Expression Classifiers using Synthetic Interventions: Tim Büchner,

Niklas Penzel,

Orlando Guntinas-Lichius,

Joachim Denzler; [pdf] [supp]
[bibtex]
@InProceedings{Buchner_2024_ACCV, author = {B\"uchner, Tim and Penzel, Niklas and Guntinas-Lichius, Orlando and Denzler, Joachim}, title = {Facing Asymmetry - Uncovering the Causal Link between Facial Symmetry and Expression Classifiers using Synthetic Interventions}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4100-4121} }
Boosting Few-Shot Detection with Large Language Models and Layout-to-Image Synthesis: Ahmed Abdullah,

Nikolas Ebert,

Oliver Wasenmüller; [pdf]
[bibtex]
@InProceedings{Abdullah_2024_ACCV, author = {Abdullah, Ahmed and Ebert, Nikolas and Wasenm\"uller, Oliver}, title = {Boosting Few-Shot Detection with Large Language Models and Layout-to-Image Synthesis}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3517-3530} }
Attention4Align: Align Multi-View Parts Via Part2Part Hierarchical Attention Maps for Fine-Grained 3D Object Classification: Runchu Zhang,

Jiahe Yue,

Zhe Zhang,

Jie Ma; [pdf]
[bibtex]
@InProceedings{Zhang_2024_ACCV, author = {Zhang, Runchu and Yue, Jiahe and Zhang, Zhe and Ma, Jie}, title = {Attention4Align: Align Multi-View Parts Via Part2Part Hierarchical Attention Maps for Fine-Grained 3D Object Classification}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4245-4261} }
Relative pose from cylinder silhouettes: Anna Gummeson,

Magnus Oskarsson; [pdf]
[bibtex]
@InProceedings{Gummeson_2024_ACCV, author = {Gummeson, Anna and Oskarsson, Magnus}, title = {Relative pose from cylinder silhouettes}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2545-2561} }
UAGE: A Supervised Contrastive Method for Unconstrained Adaptive Gaze Estimation: Enfan Lan,

Zhengxi Hu,

Jingtai Liu; [pdf]
[bibtex]
@InProceedings{Lan_2024_ACCV, author = {Lan, Enfan and Hu, Zhengxi and Liu, Jingtai}, title = {UAGE: A Supervised Contrastive Method for Unconstrained Adaptive Gaze Estimation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2231-2247} }
ReLUifying Smooth Functions: Low-Cost Knowledge Distillation to Obtain High-Performance ReLU Networks: Soosung Kim,

Yeonhong Park,

Hyunseung Lee,

Sungchan Yi,

Jae W. Lee; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2024_ACCV, author = {Kim, Soosung and Park, Yeonhong and Lee, Hyunseung and Yi, Sungchan and Lee, Jae W.}, title = {ReLUifying Smooth Functions: Low-Cost Knowledge Distillation to Obtain High-Performance ReLU Networks}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2162-2178} }
Frequency Learning Network with Dual-Guidance Calibration for Camouflaged Object Detection: Yilin Zhao,

Qing Zhang,

Yuetong Li; [pdf]
[bibtex]
@InProceedings{Zhao_2024_ACCV, author = {Zhao, Yilin and Zhang, Qing and Li, Yuetong}, title = {Frequency Learning Network with Dual-Guidance Calibration for Camouflaged Object Detection}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3851-3864} }
Telling Stories for Common Sense Zero-shot Action Recognition: Shreyank N Gowda,

Laura Sevilla-Lara; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gowda_2024_ACCV, author = {Gowda, Shreyank N and Sevilla-Lara, Laura}, title = {Telling Stories for Common Sense Zero-shot Action Recognition}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4577-4594} }
Federated Class Incremental Learning: A Pseudo Feature Based Approach Without Exemplars: Min Kyoon Yoo,

Yu Rang Park; [pdf]
[bibtex]
@InProceedings{Yoo_2024_ACCV, author = {Yoo, Min Kyoon and Park, Yu Rang}, title = {Federated Class Incremental Learning: A Pseudo Feature Based Approach Without Exemplars}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {488-498} }
Progressive Target Refinement by Self-Distillation for Human Pose Estimation: Jingtian Li,

Lin Fang,

Yi Wu,

Shangfei Wang; [pdf]
[bibtex]
@InProceedings{Li_2024_ACCV, author = {Li, Jingtian and Fang, Lin and Wu, Yi and Wang, Shangfei}, title = {Progressive Target Refinement by Self-Distillation for Human Pose Estimation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3934-3946} }
IDDiffuse: Dual-Conditional Diffusion Model for Enhanced Facial Image Anonymization: Muhammad Shaheryar,

Jong Taek Lee,

Soon Ki Jung; [pdf]
[bibtex]
@InProceedings{Shaheryar_2024_ACCV, author = {Shaheryar, Muhammad and Lee, Jong Taek and Jung, Soon Ki}, title = {IDDiffuse: Dual-Conditional Diffusion Model for Enhanced Facial Image Anonymization}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4017-4033} }
CrossViT-ReID: Cross-Attention Vision Transformer for Occluded Cloth-Changing Person Re-Identification: Vuong D. Nguyen,

Pranav Mantini,

Shishir K. Shah; [pdf]
[bibtex]
@InProceedings{Nguyen_2024_ACCV, author = {Nguyen, Vuong D. and Mantini, Pranav and Shah, Shishir K.}, title = {CrossViT-ReID: Cross-Attention Vision Transformer for Occluded Cloth-Changing Person Re-Identification}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3982-3999} }
Enhancing 3D Human Pose Estimation with Bone Length Adjustment: Chih-Hsiang Hsu,

Jyh-Shing Roger Jang; [pdf] [arXiv]
[bibtex]
@InProceedings{Hsu_2024_ACCV, author = {Hsu, Chih-Hsiang and Jang, Jyh-Shing Roger}, title = {Enhancing 3D Human Pose Estimation with Bone Length Adjustment}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3723-3738} }
COCA: Classifier-Oriented Calibration via Textual Prototype for Source-Free Universal Domain Adaptation: Xinghong Liu,

Yi Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_ACCV, author = {Liu, Xinghong and Zhou, Yi}, title = {COCA: Classifier-Oriented Calibration via Textual Prototype for Source-Free Universal Domain Adaptation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1671-1687} }
Enhancing Object Detection in Adverse Weather Conditions through Entropy and Guided Multimodal Fusion: Zhenrong Zhang,

Haoyan Gong,

Yuzheng Feng,

Zixuan Chu,

Hongbin Liu; [pdf]
[bibtex]
@InProceedings{Zhang_2024_ACCV, author = {Zhang, Zhenrong and Gong, Haoyan and Feng, Yuzheng and Chu, Zixuan and Liu, Hongbin}, title = {Enhancing Object Detection in Adverse Weather Conditions through Entropy and Guided Multimodal Fusion}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2922-2938} }
GReFEL: Geometry-Aware Reliable Facial Expression Learning under Bias and Imbalanced Data Distribution: Azmine Toushik Wasi,

Taki Hasan Rafi,

Raima Islam,

Karlo Šerbetar,

Dong-Kyu Chae; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wasi_2024_ACCV, author = {Wasi, Azmine Toushik and Rafi, Taki Hasan and Islam, Raima and \v{S}erbetar, Karlo and Chae, Dong-Kyu}, title = {GReFEL: Geometry-Aware Reliable Facial Expression Learning under Bias and Imbalanced Data Distribution}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4368-4384} }
Scene-Adaptive SVAD Based On Multi-modal Action-based Feature Extraction: Shibo Gao,

Peipei Yang,

Linlin Huang; [pdf] [supp]
[bibtex]
@InProceedings{Gao_2024_ACCV, author = {Gao, Shibo and Yang, Peipei and Huang, Linlin}, title = {Scene-Adaptive SVAD Based On Multi-modal Action-based Feature Extraction}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2471-2488} }
LoG-VMamba: Local-Global Vision Mamba for Medical Image Segmentation: Trung Dinh Quoc Dang,

Huy Hoang Nguyen,

Aleksei Tiulpin; [pdf] [supp]
[bibtex]
@InProceedings{Dang_2024_ACCV, author = {Dang, Trung Dinh Quoc and Nguyen, Huy Hoang and Tiulpin, Aleksei}, title = {LoG-VMamba: Local-Global Vision Mamba for Medical Image Segmentation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {548-565} }
Domain Aware Multi-Task Pre-Training of 3D Swin Transformer for Brain MRI: Jonghun Kim,

Mansu Kim,

Hyunjin Park; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2024_ACCV, author = {Kim, Jonghun and Kim, Mansu and Park, Hyunjin}, title = {Domain Aware Multi-Task Pre-Training of 3D Swin Transformer for Brain MRI}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2124-2144} }
CoVLM: Leveraging Consensus from Vision-Language Models for Semi-supervised Multimodal Fake News Detection: Devank,

Jayateja Kalla,

Soma Biswas; [pdf]
[bibtex]
@InProceedings{Devank_2024_ACCV, author = {Devank and Kalla, Jayateja and Biswas, Soma}, title = {CoVLM: Leveraging Consensus from Vision-Language Models for Semi-supervised Multimodal Fake News Detection}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1197-1214} }
Graph Cut-guided Maximal Coding Rate Reduction for Learning Image Embedding and Clustering: Wei He,

Zhiyuan Huang,

Xianghan Meng,

Xianbiao Qi,

Rong Xiao,

Chun-Guang Li; [pdf] [supp]
[bibtex]
@InProceedings{He_2024_ACCV, author = {He, Wei and Huang, Zhiyuan and Meng, Xianghan and Qi, Xianbiao and Xiao, Rong and Li, Chun-Guang}, title = {Graph Cut-guided Maximal Coding Rate Reduction for Learning Image Embedding and Clustering}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1883-1899} }
Tails Tell Tales: Chapter-wide Manga Transcriptions with Character Names: Ragav Sachdeva,

Gyungin Shin,

Andrew Zisserman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sachdeva_2024_ACCV, author = {Sachdeva, Ragav and Shin, Gyungin and Zisserman, Andrew}, title = {Tails Tell Tales: Chapter-wide Manga Transcriptions with Character Names}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2053-2069} }
Interaction-Guided Two-Branch Image Dehazing Network: Huichun Liu,

Xiaosong Li,

Tianshu Tan; [pdf] [arXiv]
[bibtex]
@InProceedings{Liu_2024_ACCV, author = {Liu, Huichun and Li, Xiaosong and Tan, Tianshu}, title = {Interaction-Guided Two-Branch Image Dehazing Network}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4069-4084} }
Auxiliary Domain-guided Adaptive Detection in Adverse Weather Conditions: Zhuobin Fu,

Kan Chang,

Mingyang Ling,

Qingzhi Zhang,

Enze Qi; [pdf]
[bibtex]
@InProceedings{Fu_2024_ACCV, author = {Fu, Zhuobin and Chang, Kan and Ling, Mingyang and Zhang, Qingzhi and Qi, Enze}, title = {Auxiliary Domain-guided Adaptive Detection in Adverse Weather Conditions}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3964-3981} }
OccFusion: Depth Estimation Free Multi-sensor Fusion for 3D Occupancy Prediction: Ji Zhang,

Yiran Ding,

Zixin Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_ACCV, author = {Zhang, Ji and Ding, Yiran and Liu, Zixin}, title = {OccFusion: Depth Estimation Free Multi-sensor Fusion for 3D Occupancy Prediction}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3587-3604} }
Diffusion-based Multimodal Video Captioning: Jaakko Kainulainen,

Zixin Guo,

Jorma Laaksonen; [pdf] [supp]
[bibtex]
@InProceedings{Kainulainen_2024_ACCV, author = {Kainulainen, Jaakko and Guo, Zixin and Laaksonen, Jorma}, title = {Diffusion-based Multimodal Video Captioning}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2820-2837} }
Estimating Soil Organic Carbon from Multispectral Images using Physics-Informed Neural Networks: James Sargeant,

Shyh Wei Teng,

Manzur Murshed,

Manoranjan Paul,

David Brennan; [pdf]
[bibtex]
@InProceedings{Sargeant_2024_ACCV, author = {Sargeant, James and Teng, Shyh Wei and Murshed, Manzur and Paul, Manoranjan and Brennan, David}, title = {Estimating Soil Organic Carbon from Multispectral Images using Physics-Informed Neural Networks}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2632-2649} }
RNA: Video Editing with ROI-based Neural Atlas: Jaekyeong Lee,

Geonung Kim,

Sunghyun Cho; [pdf] [arXiv]
[bibtex]
@InProceedings{Lee_2024_ACCV, author = {Lee, Jaekyeong and Kim, Geonung and Cho, Sunghyun}, title = {RNA: Video Editing with ROI-based Neural Atlas}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1936-1951} }
Masking Cascaded Self-Attentions for Few-Shot Font-Generation Transformer: Jing Ma,

Xiang Xiang,

Yan He; [pdf] [supp]
[bibtex]
@InProceedings{Ma_2024_ACCV, author = {Ma, Jing and Xiang, Xiang and He, Yan}, title = {Masking Cascaded Self-Attentions for Few-Shot Font-Generation Transformer}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2734-2750} }
PixMamba: Leveraging State Space Models in a Dual-Level Architecture for Underwater Image Enhancement: Wei-Tung Lin,

Yong-Xiang Lin,

Jyun-Wei Chen,

Kai-Lung Hua; [pdf] [arXiv]
[bibtex]
@InProceedings{Lin_2024_ACCV, author = {Lin, Wei-Tung and Lin, Yong-Xiang and Chen, Jyun-Wei and Hua, Kai-Lung}, title = {PixMamba: Leveraging State Space Models in a Dual-Level Architecture for Underwater Image Enhancement}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3622-3637} }
OneBEV: Using One Panoramic Image for Bird,Aos-Eye-View Semantic Mapping: Jiale Wei,

Junwei Zheng,

Ruiping Liu,

Jie Hu,

Jiaming Zhang,

Rainer Stiefelhagen; [pdf]
[bibtex]
@InProceedings{Wei_2024_ACCV, author = {Wei, Jiale and Zheng, Junwei and Liu, Ruiping and Hu, Jie and Zhang, Jiaming and Stiefelhagen, Rainer}, title = {OneBEV: Using One Panoramic Image for Bird,Aos-Eye-View Semantic Mapping}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {583-596} }
Seamless-Through-Breaking: Rethinking Image Stitching for Optimal Alignment: KuanYan Chen,

Atik Garg,

Yu-Shuen Wang; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2024_ACCV, author = {Chen, KuanYan and Garg, Atik and Wang, Yu-Shuen}, title = {Seamless-Through-Breaking: Rethinking Image Stitching for Optimal Alignment}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4352-4367} }
Spatiotemporal Pooling on Appropriate Topological Maps Represented as Two-Dimensional Images for EEG Classification: Takuto Fukushima,

Ryusuke Miyamoto; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fukushima_2024_ACCV, author = {Fukushima, Takuto and Miyamoto, Ryusuke}, title = {Spatiotemporal Pooling on Appropriate Topological Maps Represented as Two-Dimensional Images for EEG Classification}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1401-1419} }
TexDC: Text-Driven Disease-Aware 4D Cardiac Cine MRI Images Generation: Cong Liu,

Xiaohan Yuan,

ZhiPeng Yu,

Yangang Wang; [pdf]
[bibtex]
@InProceedings{Liu_2024_ACCV, author = {Liu, Cong and Yuan, Xiaohan and Yu, ZhiPeng and Wang, Yangang}, title = {TexDC: Text-Driven Disease-Aware 4D Cardiac Cine MRI Images Generation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3005-3021} }
4DPV: 4D Pet from Videos by Coarse-to-Fine Non-Rigid Radiance Fields: Sergio M. de Paco,

Antonio Agudo; [pdf] [arXiv]
[bibtex]
@InProceedings{de_Paco_2024_ACCV, author = {de Paco, Sergio M. and Agudo, Antonio}, title = {4DPV: 4D Pet from Videos by Coarse-to-Fine Non-Rigid Radiance Fields}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2596-2612} }
A computational model for color assimilation illusions and color constancy: Oguzhan Ulucan,

Diclehan Ulucan,

Marc Ebner; [pdf] [supp]
[bibtex]
@InProceedings{Ulucan_2024_ACCV, author = {Ulucan, Oguzhan and Ulucan, Diclehan and Ebner, Marc}, title = {A computational model for color assimilation illusions and color constancy}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {630-647} }
TaE: Task-aware Expandable Representation for Long Tail Class Incremental Learning: Linjie Li,

Zhenyu Wu,

Jiaming Liu,

Yang Ji; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2024_ACCV, author = {Li, Linjie and Wu, Zhenyu and Liu, Jiaming and Ji, Yang}, title = {TaE: Task-aware Expandable Representation for Long Tail Class Incremental Learning}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3917-3933} }
Feature Generator for Few-Shot Learning: Heethanjan Kanagalingam,

Thenukan Pathmanathan,

Navaneethan Ketheeswaran,

Mokeeshan Vathanakumar,

Mohamed Afham,

Ranga Rodrigo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kanagalingam_2024_ACCV, author = {Kanagalingam, Heethanjan and Pathmanathan, Thenukan and Ketheeswaran, Navaneethan and Vathanakumar, Mokeeshan and Afham, Mohamed and Rodrigo, Ranga}, title = {Feature Generator for Few-Shot Learning}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3901-3916} }
SeSame: Simple, Easy 3D Object Detection with Point-Wise Semantics: Hayeon O,

Chanuk Yang,

Kunsoo Huh; [pdf] [arXiv]
[bibtex]
@InProceedings{O_2024_ACCV, author = {O, Hayeon and Yang, Chanuk and Huh, Kunsoo}, title = {SeSame: Simple, Easy 3D Object Detection with Point-Wise Semantics}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2889-2905} }
Act Like a Radiologist: Radiology Report Generation across Anatomical Regions: Qi Chen,

Yutong Xie,

Biao Wu,

Xiaomin Chen,

James Ang,

Minh-Son To,

Xiaojun Chang,

Qi Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_ACCV, author = {Chen, Qi and Xie, Yutong and Wu, Biao and Chen, Xiaomin and Ang, James and To, Minh-Son and Chang, Xiaojun and Wu, Qi}, title = {Act Like a Radiologist: Radiology Report Generation across Anatomical Regions}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1-17} }
PlainUSR: Chasing Faster ConvNet for Efficient Super-Resolution: Yan Wang,

Yusen Li,

Gang Wang,

Xiaoguang Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2024_ACCV, author = {Wang, Yan and Li, Yusen and Wang, Gang and Liu, Xiaoguang}, title = {PlainUSR: Chasing Faster ConvNet for Efficient Super-Resolution}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4262-4279} }
VIFA: An Efficient Visible and Infrared Image Fusion Architecture for Multi-task Applications via Continual Learning: Jiaxing Shi,

Ao Ren,

Wei Zhuang,

Yang Hua,

ZhiYong Qin,

Zhenyu Wang,

Yang Song,

Yujuan Tan,

Duo Liu; [pdf]
[bibtex]
@InProceedings{Shi_2024_ACCV, author = {Shi, Jiaxing and Ren, Ao and Zhuang, Wei and Hua, Yang and Qin, ZhiYong and Wang, Zhenyu and Song, Yang and Tan, Yujuan and Liu, Duo}, title = {VIFA: An Efficient Visible and Infrared Image Fusion Architecture for Multi-task Applications via Continual Learning}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2872-2888} }
TCL-Net: A Lightweight and Efficient Dehazing Network with Frequency-Domain Fusion and Multi-Angle Attention: Cheng Tang,

Wenqi Lou; [pdf]
[bibtex]
@InProceedings{Tang_2024_ACCV, author = {Tang, Cheng and Lou, Wenqi}, title = {TCL-Net: A Lightweight and Efficient Dehazing Network with Frequency-Domain Fusion and Multi-Angle Attention}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {566-582} }
Blind Super Resolution with Reference Images and Implicit Degradation Representation: Huu-Phu Do,

Po-Chih Hu,

Hao-Chien Hsueh,

Che-Kai Liu,

Vu-Hoang Tran,

Ching-Chun Huang; [pdf] [supp]
[bibtex]
@InProceedings{Do_2024_ACCV, author = {Do, Huu-Phu and Hu, Po-Chih and Hsueh, Hao-Chien and Liu, Che-Kai and Tran, Vu-Hoang and Huang, Ching-Chun}, title = {Blind Super Resolution with Reference Images and Implicit Degradation Representation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1100-1115} }
DA^2: Degree-Accumulated Data Augmentation on Point Clouds with Curriculum Dynamic Threshold Selection: Ta Chun Tai,

Nhat-Tuong Do-Tran,

Ngoc-Hoang-Lam Le,

Yung-Hui Li,

Ching-Chun Huang; [pdf] [supp]
[bibtex]
@InProceedings{Tai_2024_ACCV, author = {Tai, Ta Chun and Do-Tran, Nhat-Tuong and Le, Ngoc-Hoang-Lam and Li, Yung-Hui and Huang, Ching-Chun}, title = {DA{\textasciicircum}2: Degree-Accumulated Data Augmentation on Point Clouds with Curriculum Dynamic Threshold Selection}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2196-2211} }
FaRE: A Feature-aware Radical Encoding Strategy for Zero-shot Chinese Character Recognition: Hongjian Zhan,

Yangfu Li,

Yu-jie Xiong,

Yue Lu; [pdf]
[bibtex]
@InProceedings{Zhan_2024_ACCV, author = {Zhan, Hongjian and Li, Yangfu and Xiong, Yu-jie and Lu, Yue}, title = {FaRE: A Feature-aware Radical Encoding Strategy for Zero-shot Chinese Character Recognition}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {390-401} }
KEM: SGW-based Multi-Task Learning in Vision Tasks: Ruiyuan Zhang,

Yuyao Chen,

Jiaxiang Liu,

Dianbing Xi,

Yuchi Huo,

Jie Liu,

Chao Wu; [pdf]
[bibtex]
@InProceedings{Zhang_2024_ACCV, author = {Zhang, Ruiyuan and Chen, Yuyao and Liu, Jiaxiang and Xi, Dianbing and Huo, Yuchi and Liu, Jie and Wu, Chao}, title = {KEM: SGW-based Multi-Task Learning in Vision Tasks}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1688-1705} }
It's Just Another Day: Unique Video Captioning by Discriminative Prompting: Toby Perrett,

Tengda Han,

Dima Damen,

Andrew Zisserman; [pdf] [supp]
[bibtex]
@InProceedings{Perrett_2024_ACCV, author = {Perrett, Toby and Han, Tengda and Damen, Dima and Zisserman, Andrew}, title = {It's Just Another Day: Unique Video Captioning by Discriminative Prompting}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {232-249} }
Learning Classwise Untangled Continuums for Conditional Normalizing Flows: Victor Enescu,

Hichem Sahbi; [pdf] [supp]
[bibtex]
@InProceedings{Enescu_2024_ACCV, author = {Enescu, Victor and Sahbi, Hichem}, title = {Learning Classwise Untangled Continuums for Conditional Normalizing Flows}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3038-3055} }
Full-body Human De-lighting with Semi-Supervised Learning: Joshua Weir,

Junhong Zhao,

Andrew Chalmers,

Taehyun Rhee; [pdf]
[bibtex]
@InProceedings{Weir_2024_ACCV, author = {Weir, Joshua and Zhao, Junhong and Chalmers, Andrew and Rhee, Taehyun}, title = {Full-body Human De-lighting with Semi-Supervised Learning}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {648-664} }
Parameter-Selective Continual Test-Time Adaptation: Jiaxu Tian,

Fan Lyu; [pdf] [arXiv]
[bibtex]
@InProceedings{Tian_2024_ACCV, author = {Tian, Jiaxu and Lyu, Fan}, title = {Parameter-Selective Continual Test-Time Adaptation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1384-1400} }
EDAF: Early Detection of Atrial Fibrillation from Post-Stroke Brain MRI: Mohammad Javad Shokri,

Nandakishor Desai,

Aravinda S. Rao,

Angelos Sharobeam,

Bernard Yan,

Marimuthu Palaniswami; [pdf]
[bibtex]
@InProceedings{Shokri_2024_ACCV, author = {Shokri, Mohammad Javad and Desai, Nandakishor and Rao, Aravinda S. and Sharobeam, Angelos and Yan, Bernard and Palaniswami, Marimuthu}, title = {EDAF: Early Detection of Atrial Fibrillation from Post-Stroke Brain MRI}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1969-1985} }
Chinese Character Component Segmentation Based on Character Structure Masks: Haiyan Li,

Fang Yang; [pdf]
[bibtex]
@InProceedings{Li_2024_ACCV, author = {Li, Haiyan and Yang, Fang}, title = {Chinese Character Component Segmentation Based on Character Structure Masks}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1316-1331} }
MeshGS: Adaptive Mesh-Aligned Gaussian Splatting for High-Quality Rendering: Jaehoon Choi,

Yonghan Lee,

Hyungtae Lee,

Heesung Kwon,

Dinesh Manocha; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Choi_2024_ACCV, author = {Choi, Jaehoon and Lee, Yonghan and Lee, Hyungtae and Kwon, Heesung and Manocha, Dinesh}, title = {MeshGS: Adaptive Mesh-Aligned Gaussian Splatting for High-Quality Rendering}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3310-3326} }
Learning Interval-Aware Embedding for Macro- and Micro-expression Spotting: Xiaodong Li,

Jiajun Li,

Wenchao Du,

Hu Chen,

Hongyu Yang; [pdf]
[bibtex]
@InProceedings{Li_2024_ACCV, author = {Li, Xiaodong and Li, Jiajun and Du, Wenchao and Chen, Hu and Yang, Hongyu}, title = {Learning Interval-Aware Embedding for Macro- and Micro-expression Spotting}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {337-353} }
Learning Complementary Maps for Light Field Salient Object Detection: Zeyu Xiao,

Jiateng Shou,

Zhiwei Xiong; [pdf] [supp]
[bibtex]
@InProceedings{Xiao_2024_ACCV, author = {Xiao, Zeyu and Shou, Jiateng and Xiong, Zhiwei}, title = {Learning Complementary Maps for Light Field Salient Object Detection}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4403-4421} }
MS-UMLP: Medical Image Segmentation via Multi-Scale U-shape MLP-Mixer: Bin Xie,

Hao Tang,

Dawen Cai,

Yan Yan; [pdf]
[bibtex]
@InProceedings{Xie_2024_ACCV, author = {Xie, Bin and Tang, Hao and Cai, Dawen and Yan, Yan}, title = {MS-UMLP: Medical Image Segmentation via Multi-Scale U-shape MLP-Mixer}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1793-1808} }
A StyleCLIP-based Facial Emotion Manipulation Method for Discrepant Emotion Transitions: Qi Guo,

Xiaodong Gu; [pdf]
[bibtex]
@InProceedings{Guo_2024_ACCV, author = {Guo, Qi and Gu, Xiaodong}, title = {A StyleCLIP-based Facial Emotion Manipulation Method for Discrepant Emotion Transitions}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3414-3431} }
Few Exemplar-Based General Medical Image Segmentation via Domain-Aware Selective Adaptation: Chen Xu,

Qiming Huang,

Yuqi Hou,

Jiangxing Wu,

Fan Zhang,

Hyung Jin Chang,

Jianbo Jiao; [pdf] [arXiv]
[bibtex]
@InProceedings{Xu_2024_ACCV, author = {Xu, Chen and Huang, Qiming and Hou, Yuqi and Wu, Jiangxing and Zhang, Fan and Chang, Hyung Jin and Jiao, Jianbo}, title = {Few Exemplar-Based General Medical Image Segmentation via Domain-Aware Selective Adaptation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2684-2698} }
Tracking Reflected Objects: A Benchmark: Xiaoyu Guo,

Pengzhi Zhong,

Lizhi Lin,

Hao Zhang,

Ling Huang,

Shuiwang Li; [pdf] [arXiv]
[bibtex]
@InProceedings{Guo_2024_ACCV, author = {Guo, Xiaoyu and Zhong, Pengzhi and Lin, Lizhi and Zhang, Hao and Huang, Ling and Li, Shuiwang}, title = {Tracking Reflected Objects: A Benchmark}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1756-1776} }
CrossPAR: Enhancing Pedestrian Attribute Recognition with Vision-Language Fusion and Human-Centric Pre-training: Bach-Hoang Ngo,

Si-Tri Ngo,

Phu-Duc Le,

Quang-Minh Phan,

Minh-Triet Tran,

Trung-Nghia Le; [pdf]
[bibtex]
@InProceedings{Ngo_2024_ACCV, author = {Ngo, Bach-Hoang and Ngo, Si-Tri and Le, Phu-Duc and Phan, Quang-Minh and Tran, Minh-Triet and Le, Trung-Nghia}, title = {CrossPAR: Enhancing Pedestrian Attribute Recognition with Vision-Language Fusion and Human-Centric Pre-training}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1301-1315} }
GSMNet: Towards Long-term Trajectory Prediction by Integrating Multi-Scale Information: Shaohua Liu,

Yisu Wang,

Yinglong Zhu,

Pengfei Yao,

Tianlu Mao,

Zhaoqi Wang; [pdf]
[bibtex]
@InProceedings{Liu_2024_ACCV, author = {Liu, Shaohua and Wang, Yisu and Zhu, Yinglong and Yao, Pengfei and Mao, Tianlu and Wang, Zhaoqi}, title = {GSMNet: Towards Long-term Trajectory Prediction by Integrating Multi-Scale Information}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2954-2969} }
Structure-Centric Robust Monocular Depth Estimation via Knowledge Distillation: Runze Chen,

Haiyong Luo,

Fang Zhao,

Jingze Yu,

Yupeng Jia,

Juan Wang,

Xuepeng Ma; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_ACCV, author = {Chen, Runze and Luo, Haiyong and Zhao, Fang and Yu, Jingze and Jia, Yupeng and Wang, Juan and Ma, Xuepeng}, title = {Structure-Centric Robust Monocular Depth Estimation via Knowledge Distillation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2970-2987} }
High-Quality Visually-Guided Sound Separation from Diverse Categories: Chao Huang,

Susan Liang,

Yapeng Tian,

Anurag Kumar,

Chenliang Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2024_ACCV, author = {Huang, Chao and Liang, Susan and Tian, Yapeng and Kumar, Anurag and Xu, Chenliang}, title = {High-Quality Visually-Guided Sound Separation from Diverse Categories}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {35-49} }
FSGait: Fine Grained Self-Supervised Gait Abnormality Detection: Bingzhi Duan,

Xiaoyue Wan,

Xu Zhao; [pdf]
[bibtex]
@InProceedings{Duan_2024_ACCV, author = {Duan, Bingzhi and Wan, Xiaoyue and Zhao, Xu}, title = {FSGait: Fine Grained Self-Supervised Gait Abnormality Detection}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2248-2264} }
Spotlight on Small-scale Ship Detection: Empowering YOLO with Advanced Techniques and a Novel Dataset: Lingya Li,

Zhixing Hou,

Ming Ma,

Jing Xiang,

Chuangxin Yuan,

Guihua Xia; [pdf] [supp]
[bibtex]
@InProceedings{Li_2024_ACCV, author = {Li, Lingya and Hou, Zhixing and Ma, Ming and Xiang, Jing and Yuan, Chuangxin and Xia, Guihua}, title = {Spotlight on Small-scale Ship Detection: Empowering YOLO with Advanced Techniques and a Novel Dataset}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {784-799} }
Foundation Model-Powered 3D Few-Shot Class Incremental Learning via Training-free Adaptor: Sahar Ahmadi,

Ali Cheraghian,

Morteza Saberi,

Md.Towsif Abir,

Hamidreza Dastmalchi,

Farookh Hussain,

Shafin Rahman; [pdf] [arXiv]
[bibtex]
@InProceedings{Ahmadi_2024_ACCV, author = {Ahmadi, Sahar and Cheraghian, Ali and Saberi, Morteza and Abir, Md.Towsif and Dastmalchi, Hamidreza and Hussain, Farookh and Rahman, Shafin}, title = {Foundation Model-Powered 3D Few-Shot Class Incremental Learning via Training-free Adaptor}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2282-2299} }
Calibration Transfer via Knowledge Distillation: Ramya Hebbalaguppe,

Mayank Baranwal,

Kartik Anand,

Chetan Arora; [pdf] [supp]
[bibtex]
@InProceedings{Hebbalaguppe_2024_ACCV, author = {Hebbalaguppe, Ramya and Baranwal, Mayank and Anand, Kartik and Arora, Chetan}, title = {Calibration Transfer via Knowledge Distillation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {513-530} }
TuneVLSeg: Prompt Tuning Benchmark for Vision-Language Segmentation Models: Rabin Adhikari,

Safal Thapaliya,

Manish Dhakal,

Bishesh Khanal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Adhikari_2024_ACCV, author = {Adhikari, Rabin and Thapaliya, Safal and Dhakal, Manish and Khanal, Bishesh}, title = {TuneVLSeg: Prompt Tuning Benchmark for Vision-Language Segmentation Models}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {126-144} }
DENEB: A Hallucination-Robust Automatic Evaluation Metric for Image Captioning: Kazuki Matsuda,

Yuiga Wada,

Komei Sugiura; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Matsuda_2024_ACCV, author = {Matsuda, Kazuki and Wada, Yuiga and Sugiura, Komei}, title = {DENEB: A Hallucination-Robust Automatic Evaluation Metric for Image Captioning}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3570-3586} }
EgoCoord: Self-calibrated Egocentric 3D Body Pose Estimation using Pixel-wise Coordinate Encoding: Jong-Bae Lee,

Hyoung Lee,

Beom-Ryeol Lee,

Byung-Gook Lee,

Wook-Ho Son; [pdf]
[bibtex]
@InProceedings{Lee_2024_ACCV, author = {Lee, Jong-Bae and Lee, Hyoung and Lee, Beom-Ryeol and Lee, Byung-Gook and Son, Wook-Ho}, title = {EgoCoord: Self-calibrated Egocentric 3D Body Pose Estimation using Pixel-wise Coordinate Encoding}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1233-1249} }
Match-free Inbetweening Assistant (MIBA): A Practical Animation Tool without User Stroke Correspondence: Shuhong Chen,

Matthias Zwicker; [pdf]
[bibtex]
@InProceedings{Chen_2024_ACCV, author = {Chen, Shuhong and Zwicker, Matthias}, title = {Match-free Inbetweening Assistant (MIBA): A Practical Animation Tool without User Stroke Correspondence}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {179-193} }
LCM: Log Conformal Maps for Robust Representation Learning to Mitigate Perspective Distortion: Meenakshi Subhash Chippa,

Prakash Chandra Chhipa,

Kanjar De,

Marcus Liwicki,

Rajkumar Saini; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chippa_2024_ACCV, author = {Chippa, Meenakshi Subhash and Chhipa, Prakash Chandra and De, Kanjar and Liwicki, Marcus and Saini, Rajkumar}, title = {LCM: Log Conformal Maps for Robust Representation Learning to Mitigate Perspective Distortion}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3275-3291} }
Reference-Based Face Super-Resolution Using the Spatial Transformer: Varun Ramesh Jois,

Antonella DiLillo,

James Storer; [pdf]
[bibtex]
@InProceedings{Jois_2024_ACCV, author = {Jois, Varun Ramesh and DiLillo, Antonella and Storer, James}, title = {Reference-Based Face Super-Resolution Using the Spatial Transformer}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3689-3705} }
Tracking Correction Method for Rapid and Random Protein Molecules Movement: Satoshi Kamiya,

Keisuke Toida,

Taka-aki Tsunoyama,

Kazuhiro Hotta; [pdf]
[bibtex]
@InProceedings{Kamiya_2024_ACCV, author = {Kamiya, Satoshi and Toida, Keisuke and Tsunoyama, Taka-aki and Hotta, Kazuhiro}, title = {Tracking Correction Method for Rapid and Random Protein Molecules Movement}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3022-3037} }
PSG-Adapter: Controllable Planning Scene Graph for Improving Text-to-Image Diffusion: Yi Gao; [pdf] [supp]
[bibtex]
@InProceedings{Gao_2024_ACCV, author = {Gao, Yi}, title = {PSG-Adapter: Controllable Planning Scene Graph for Improving Text-to-Image Diffusion}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2371-2387} }
BoT-FaceSORT: Bag-of-Tricks for Robust Multi-Face Tracking in Unconstrained Videos: Jonghyeon Kim,

Chan-Yang Ju,

Gun-Woo Kim,

Dong-Ho Lee; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2024_ACCV, author = {Kim, Jonghyeon and Ju, Chan-Yang and Kim, Gun-Woo and Lee, Dong-Ho}, title = {BoT-FaceSORT: Bag-of-Tricks for Robust Multi-Face Tracking in Unconstrained Videos}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1437-1453} }
ADSP: Advanced Dataset for Shadow Processing, enabling visible occluders via synthesizing strategy.: Chang-Yu Hsieh,

Jian-Jiun Ding; [pdf] [supp]
[bibtex]
@InProceedings{Hsieh_2024_ACCV, author = {Hsieh, Chang-Yu and Ding, Jian-Jiun}, title = {ADSP: Advanced Dataset for Shadow Processing, enabling visible occluders via synthesizing strategy.}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1028-1045} }
ObjectCompose: Evaluating Resilience of Vision-Based Models on Object-to-Background Compositional Changes: Hashmat Shadab Malik,

Muhammad Huzaifa,

Muzammal Naseer,

Salman Khan,

Fahad Shahbaz Khan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Malik_2024_ACCV, author = {Malik, Hashmat Shadab and Huzaifa, Muhammad and Naseer, Muzammal and Khan, Salman and Khan, Fahad Shahbaz}, title = {ObjectCompose: Evaluating Resilience of Vision-Based Models on Object-to-Background Compositional Changes}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {372-389} }
Feature Estimation of Global Language Processing in EEG Using Attention Maps: Dai Shimizu,

Ko Watanabe,

Andreas Dengel; [pdf] [arXiv]
[bibtex]
@InProceedings{Shimizu_2024_ACCV, author = {Shimizu, Dai and Watanabe, Ko and Dengel, Andreas}, title = {Feature Estimation of Global Language Processing in EEG Using Attention Maps}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1706-1722} }
Efficient Implicit SDF and Color Reconstruction via Shared Feature Field: Shuangkang Fang,

Dacheng Qi,

Weixin Xu,

Yufeng Wang,

Zehao Zhang,

Xiaorong Zhang,

Huayu Zhang,

Zeqi Shao,

Wenrui Ding; [pdf]
[bibtex]
@InProceedings{Fang_2024_ACCV, author = {Fang, Shuangkang and Qi, Dacheng and Xu, Weixin and Wang, Yufeng and Zhang, Zehao and Zhang, Xiaorong and Zhang, Huayu and Shao, Zeqi and Ding, Wenrui}, title = {Efficient Implicit SDF and Color Reconstruction via Shared Feature Field}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3499-3516} }
BAMG: Text-based Person Re-identification via Bottlenecks Attention and Masked Graph Modeling: Keyang Cheng,

Wenxuan Zou,

Hongjian Gu,

Anxiang Ouyang; [pdf]
[bibtex]
@InProceedings{Cheng_2024_ACCV, author = {Cheng, Keyang and Zou, Wenxuan and Gu, Hongjian and Ouyang, Anxiang}, title = {BAMG: Text-based Person Re-identification via Bottlenecks Attention and Masked Graph Modeling}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1809-1826} }
Nash Meets Wertheimer: Using Good Continuation in Jigsaw Puzzles: Marina Khoroshiltseva,

Luca Palmieri,

Sinem Aslan,

Sebastiano Vascon,

Marcello Pelillo; [pdf] [arXiv]
[bibtex]
@InProceedings{Khoroshiltseva_2024_ACCV, author = {Khoroshiltseva, Marina and Palmieri, Luca and Aslan, Sinem and Vascon, Sebastiano and Pelillo, Marcello}, title = {Nash Meets Wertheimer: Using Good Continuation in Jigsaw Puzzles}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3223-3238} }
A Simple Finetuning Strategy Based on Bias-Variance Ratios of Layer-Wise Gradients: Mao Tomita,

Ikuro Sato,

Rei Kawakami,

Nakamasa Inoue,

Satoshi Ikehata,

Masayuki Tanaka; [pdf]
[bibtex]
@InProceedings{Tomita_2024_ACCV, author = {Tomita, Mao and Sato, Ikuro and Kawakami, Rei and Inoue, Nakamasa and Ikehata, Satoshi and Tanaka, Masayuki}, title = {A Simple Finetuning Strategy Based on Bias-Variance Ratios of Layer-Wise Gradients}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {471-487} }
Adapting Models to Scarce Target Data without Source Samples: JoonHo Lee,

Gyemin Lee; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2024_ACCV, author = {Lee, JoonHo and Lee, Gyemin}, title = {Adapting Models to Scarce Target Data without Source Samples}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1618-1633} }
SSTHyper: Sparse Spectral Transformer for Hyperspectral Image Reconstruction: Meng Xu,

Mingying Lin,

Qi Ren,

Sen Jia; [pdf]
[bibtex]
@InProceedings{Xu_2024_ACCV, author = {Xu, Meng and Lin, Mingying and Ren, Qi and Jia, Sen}, title = {SSTHyper: Sparse Spectral Transformer for Hyperspectral Image Reconstruction}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1918-1935} }
Conditional Distribution Modelling for Few-Shot Image Synthesis with Diffusion Models: Parul Gupta,

Munawar Hayat,

Abhinav Dhall,

Thanh-Toan Do; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gupta_2024_ACCV, author = {Gupta, Parul and Hayat, Munawar and Dhall, Abhinav and Do, Thanh-Toan}, title = {Conditional Distribution Modelling for Few-Shot Image Synthesis with Diffusion Models}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {818-834} }
The Devil is in the Details: Simple Remedies for Image-to-LiDAR Representation Learning: Wonjun Jo,

Kwon Byung-Ki,

Kim Ji-Yeon,

Hawook Jeong,

Kyungdon Joo,

Tae-Hyun Oh; [pdf] [supp]
[bibtex]
@InProceedings{Jo_2024_ACCV, author = {Jo, Wonjun and Byung-Ki, Kwon and Ji-Yeon, Kim and Jeong, Hawook and Joo, Kyungdon and Oh, Tae-Hyun}, title = {The Devil is in the Details: Simple Remedies for Image-to-LiDAR Representation Learning}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3172-3188} }
SCCA-Net: A Novel Network for Image Manipulation Localization Using Split-Channel Contextual Attention: Yan Xiang,

Kaiqi Zhao,

Haichang Yin; [pdf]
[bibtex]
@InProceedings{Xiang_2024_ACCV, author = {Xiang, Yan and Zhao, Kaiqi and Yin, Haichang}, title = {SCCA-Net: A Novel Network for Image Manipulation Localization Using Split-Channel Contextual Attention}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4473-4487} }
Revealing Hidden Context in Camouflage Instance Segmentation: Thanh-Hai Phung,

Hong-Han Shuai; [pdf] [supp]
[bibtex]
@InProceedings{Phung_2024_ACCV, author = {Phung, Thanh-Hai and Shuai, Hong-Han}, title = {Revealing Hidden Context in Camouflage Instance Segmentation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2319-2336} }
Dessie: Disentanglement for Articulated 3D Horse Shape and Pose Estimation from Images: Ci Li,

Yi Yang,

Zehang Weng,

Elin Hernlund,

Silvia Zuffi,

Hedvig Kjellström; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_ACCV, author = {Li, Ci and Yang, Yi and Weng, Zehang and Hernlund, Elin and Zuffi, Silvia and Kjellstr\"om, Hedvig}, title = {Dessie: Disentanglement for Articulated 3D Horse Shape and Pose Estimation from Images}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {764-783} }
Greit-HRNet: Grouped Lightweight High-Resolution Network for Human Pose Estimation: Junjia Han,

Yanxia Wang; [pdf]
[bibtex]
@InProceedings{Han_2024_ACCV, author = {Han, Junjia and Wang, Yanxia}, title = {Greit-HRNet: Grouped Lightweight High-Resolution Network for Human Pose Estimation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3771-3787} }
Improve Model Robustness in Less Time Than It Takes to Drink A Cup of Coffee with Plug-and-Play Plugins.: Jiang Fang,

Zhicheng Zhang,

Jiyan Sun,

Jiadong Fu,

Haonan He,

Yinlong Liu,

Wei Ma; [pdf]
[bibtex]
@InProceedings{Fang_2024_ACCV, author = {Fang, Jiang and Zhang, Zhicheng and Sun, Jiyan and Fu, Jiadong and He, Haonan and Liu, Yinlong and Ma, Wei}, title = {Improve Model Robustness in Less Time Than It Takes to Drink A Cup of Coffee with Plug-and-Play Plugins.}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1520-1531} }
Locate n' Rotate: Two-stage Openable Part Detection with Geometric Foundation Model Priors: Siqi Li,

Xiaoxue Chen,

Haoyu Cheng,

Guyue Zhou,

Hao Zhao,

Guanzhong Tian; [pdf]
[bibtex]
@InProceedings{Li_2024_ACCV, author = {Li, Siqi and Chen, Xiaoxue and Cheng, Haoyu and Zhou, Guyue and Zhao, Hao and Tian, Guanzhong}, title = {Locate n' Rotate: Two-stage Openable Part Detection with Geometric Foundation Model Priors}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {716-732} }
Character-aware audio-visual subtitling in context: Jaesung Huh,

Andrew Zisserman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huh_2024_ACCV, author = {Huh, Jaesung and Zisserman, Andrew}, title = {Character-aware audio-visual subtitling in context}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2613-2631} }
A Generic Autoregressive Predictive Feedback Framework for Skeleton-Based Action Recognition: Xinpeng Yin,

Jing Hu,

Wenming Cao; [pdf]
[bibtex]
@InProceedings{Yin_2024_ACCV, author = {Yin, Xinpeng and Hu, Jing and Cao, Wenming}, title = {A Generic Autoregressive Predictive Feedback Framework for Skeleton-Based Action Recognition}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3465-3479} }
Exploring Limits of Diffusion-Synthetic Training with Weakly Supervised Semantic Segmentation: Ryota Yoshihashi,

Yuya Otsuka,

Kenji Doi,

Tomohiro Tanaka,

Hirokatsu Kataoka; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yoshihashi_2024_ACCV, author = {Yoshihashi, Ryota and Otsuka, Yuya and Doi, Kenji and Tanaka, Tomohiro and Kataoka, Hirokatsu}, title = {Exploring Limits of Diffusion-Synthetic Training with Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2300-2318} }
ESM-YOLO: Enhanced Small Target Detection Based on Visible and Infrared Multi-modal Fusion: Qianqian Zhang,

Linwei Qiu,

Li Zhou,

Junshe An; [pdf]
[bibtex]
@InProceedings{Zhang_2024_ACCV, author = {Zhang, Qianqian and Qiu, Linwei and Zhou, Li and An, Junshe}, title = {ESM-YOLO: Enhanced Small Target Detection Based on Visible and Infrared Multi-modal Fusion}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1454-1469} }
Diffusing Background Dictionary for Hyperspectral Anomaly Detection: Yaochen Wu,

Yu Meng,

Lei Sun; [pdf]
[bibtex]
@InProceedings{Wu_2024_ACCV, author = {Wu, Yaochen and Meng, Yu and Sun, Lei}, title = {Diffusing Background Dictionary for Hyperspectral Anomaly Detection}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1046-1064} }
Robust Single-view 3D Human Digitization via Explicit Geometric Field with Semantic Guidance: Ruizhi Liu,

Paolo Remagnino; [pdf]
[bibtex]
@InProceedings{Liu_2024_ACCV, author = {Liu, Ruizhi and Remagnino, Paolo}, title = {Robust Single-view 3D Human Digitization via Explicit Geometric Field with Semantic Guidance}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3362-3378} }
Learning Dual Hierarchical Representation for 3D Surface Reconstruction: Jiyoon Shin,

Youngwook Kim,

Sangwoo Hong,

Jungwoo Lee; [pdf] [supp]
[bibtex]
@InProceedings{Shin_2024_ACCV, author = {Shin, Jiyoon and Kim, Youngwook and Hong, Sangwoo and Lee, Jungwoo}, title = {Learning Dual Hierarchical Representation for 3D Surface Reconstruction}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4422-4438} }
Joint Image Super-resolution and Low-light Enhancement in the Dark: Feihu Zhou,

Kan Chang,

Mingyang Ling,

Hengxin Li,

Shucheng Xia; [pdf] [supp]
[bibtex]
@InProceedings{Zhou_2024_ACCV, author = {Zhou, Feihu and Chang, Kan and Ling, Mingyang and Li, Hengxin and Xia, Shucheng}, title = {Joint Image Super-resolution and Low-light Enhancement in the Dark}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1332-1349} }
Beyond Coarse-Grained Matching in Video-Text Retrieval: Aozhu Chen,

Hazel Doughty,

Xirong Li,

Cees G. M. Snoek; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_ACCV, author = {Chen, Aozhu and Doughty, Hazel and Li, Xirong and Snoek, Cees G. M.}, title = {Beyond Coarse-Grained Matching in Video-Text Retrieval}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {71-87} }
UNet--: Memory-Efficient and Feature-Enhanced Network Architecture based on U-Net with Reduced Skip-Connections: Lingxiao Yin,

Wei Tao,

Dongyue Zhao,

Tadayuki Ito,

Kinya Osa,

Masami Kato,

Tse-Wei Chen; [pdf]
[bibtex]
@InProceedings{Yin_2024_ACCV, author = {Yin, Lingxiao and Tao, Wei and Zhao, Dongyue and Ito, Tadayuki and Osa, Kinya and Kato, Masami and Chen, Tse-Wei}, title = {UNet--: Memory-Efficient and Feature-Enhanced Network Architecture based on U-Net with Reduced Skip-Connections}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4085-4099} }
Enhancing Multimedia Applications by Removing Dynamic Objects in Neural Radiance Fields: XianBen Yang,

Tao Wang,

He Liu,

Yi Jin,

Congyan Lang,

Yidong Li; [pdf]
[bibtex]
@InProceedings{Yang_2024_ACCV, author = {Yang, XianBen and Wang, Tao and Liu, He and Jin, Yi and Lang, Congyan and Li, Yidong}, title = {Enhancing Multimedia Applications by Removing Dynamic Objects in Neural Radiance Fields}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2070-2086} }
Revisiting sample weights based method for noisy-label detection and classification: Tuan Hoang,

Hung Tran,

Santu Rana,

Sunil Gupta,

Svetha Venkatesh; [pdf]
[bibtex]
@InProceedings{Hoang_2024_ACCV, author = {Hoang, Tuan and Tran, Hung and Rana, Santu and Gupta, Sunil and Venkatesh, Svetha}, title = {Revisiting sample weights based method for noisy-label detection and classification}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4189-4204} }
Enhancing Robustness to Noise Corruption for Point Cloud Recognition via Spatial Sorting and Set-Mixing Aggregation Module: Dingxin Zhang,

Jianhui Yu,

Tengfei Xue,

Chaoyi Zhang,

Dongnan Liu,

Weidong Cai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_ACCV, author = {Zhang, Dingxin and Yu, Jianhui and Xue, Tengfei and Zhang, Chaoyi and Liu, Dongnan and Cai, Weidong}, title = {Enhancing Robustness to Noise Corruption for Point Cloud Recognition via Spatial Sorting and Set-Mixing Aggregation Module}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4205-4222} }
Hybrid and Non-minimal Planar Motion Estimation from Point Correspondences: Juan Carlos Dibene Simental,

Enrique Dunn; [pdf] [supp]
[bibtex]
@InProceedings{Simental_2024_ACCV, author = {Simental, Juan Carlos Dibene and Dunn, Enrique}, title = {Hybrid and Non-minimal Planar Motion Estimation from Point Correspondences}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4561-4576} }
Text Query to Web Image to Video: A Comprehensive Ad-hoc Video Search: Nhat-Minh Nguyen,

Tien-Dung Mai,

Duy-Dinh Le; [pdf] [supp]
[bibtex]
@InProceedings{Nguyen_2024_ACCV, author = {Nguyen, Nhat-Minh and Mai, Tien-Dung and Le, Duy-Dinh}, title = {Text Query to Web Image to Video: A Comprehensive Ad-hoc Video Search}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4141-4155} }
GeoRefineNet: A Multistage Framework for Enhanced Cephalometric Landmark Detection in CBCT Images Using 3D Geometric Information: Thanaporn Viriyasaranon,

Serie Ma,

Jang-Hwan Choi; [pdf]
[bibtex]
@InProceedings{Viriyasaranon_2024_ACCV, author = {Viriyasaranon, Thanaporn and Ma, Serie and Choi, Jang-Hwan}, title = {GeoRefineNet: A Multistage Framework for Enhanced Cephalometric Landmark Detection in CBCT Images Using 3D Geometric Information}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3107-3119} }
AutoAD-Zero: A Training-Free Framework for Zero-Shot Audio Description: Junyu Xie,

Tengda Han,

Max Bain,

Arsha Nagrani,

Gül Varol,

Weidi Xie,

Andrew Zisserman; [pdf]
[bibtex]
@InProceedings{Xie_2024_ACCV, author = {Xie, Junyu and Han, Tengda and Bain, Max and Nagrani, Arsha and Varol, G\"ul and Xie, Weidi and Zisserman, Andrew}, title = {AutoAD-Zero: A Training-Free Framework for Zero-Shot Audio Description}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2265-2281} }
LocoMotion: Learning Motion-Focused Video-Language Representations: Hazel Doughty,

Fida Mohammad Thoker,

Cees G. M. Snoek; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Doughty_2024_ACCV, author = {Doughty, Hazel and Thoker, Fida Mohammad and Snoek, Cees G. M.}, title = {LocoMotion: Learning Motion-Focused Video-Language Representations}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {50-70} }
D'OH: Decoder-Only Random Hypernetworks for Implicit Neural Representations: Cameron Gordon,

Lachlan E. MacDonald,

Hemanth Saratchandran,

Simon Lucey; [pdf] [supp]
[bibtex]
@InProceedings{Gordon_2024_ACCV, author = {Gordon, Cameron and MacDonald, Lachlan E. and Saratchandran, Hemanth and Lucey, Simon}, title = {D'OH: Decoder-Only Random Hypernetworks for Implicit Neural Representations}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2507-2526} }
Cross Feature Fusion of Fundus Image and Generated Lesion Map for Referable Diabetic Retinopathy Classification: Dahyun Mok,

Junghyun Bum,

Le Duc Tai,

Hyunseung Choo; [pdf] [arXiv]
[bibtex]
@InProceedings{Mok_2024_ACCV, author = {Mok, Dahyun and Bum, Junghyun and Tai, Le Duc and Choo, Hyunseung}, title = {Cross Feature Fusion of Fundus Image and Generated Lesion Map for Referable Diabetic Retinopathy Classification}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1350-1365} }
Randomized Channel-pass Mask for Channel-wise Explanation of Black-box Models: Hirotaka Hachiya,

Daiki Nisawa; [pdf]
[bibtex]
@InProceedings{Hachiya_2024_ACCV, author = {Hachiya, Hirotaka and Nisawa, Daiki}, title = {Randomized Channel-pass Mask for Channel-wise Explanation of Black-box Models}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3756-3770} }
DPL: Cross-quality DeepFake Detection via Dual Progressive Learning: Dongliang Zhang,

Yunfei Li,

Jiaran Zhou,

Yuezun Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_ACCV, author = {Zhang, Dongliang and Li, Yunfei and Zhou, Jiaran and Li, Yuezun}, title = {DPL: Cross-quality DeepFake Detection via Dual Progressive Learning}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1116-1132} }
Diffusion Model Compression for Image-to-Image Translation: Geonung Kim,

Beomsu Kim,

Eunhyeok Park,

Sunghyun Cho; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2024_ACCV, author = {Kim, Geonung and Kim, Beomsu and Park, Eunhyeok and Cho, Sunghyun}, title = {Diffusion Model Compression for Image-to-Image Translation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2105-2123} }
Contrastive Max-correlation for Multi-view Clustering: Yanghao Deng,

Zenghui Wang,

Songlin Du; [pdf]
[bibtex]
@InProceedings{Deng_2024_ACCV, author = {Deng, Yanghao and Wang, Zenghui and Du, Songlin}, title = {Contrastive Max-correlation for Multi-view Clustering}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {499-512} }
Robust Visual Reinforcement Learning by Prompt Tuning: Tung Tran,

Khoat Than,

Danilo Vargas; [pdf] [supp]
[bibtex]
@InProceedings{Tran_2024_ACCV, author = {Tran, Tung and Than, Khoat and Vargas, Danilo}, title = {Robust Visual Reinforcement Learning by Prompt Tuning}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1133-1147} }
LoLI-Street: Benchmarking Low-light Image Enhancement and Beyond: Md Tanvir Islam,

Inzamamul Alam,

Simon S. Woo,

Saeed Anwar,

IK Hyun Lee,

Khan Muhammad; [pdf] [supp]
[bibtex]
@InProceedings{Islam_2024_ACCV, author = {Islam, Md Tanvir and Alam, Inzamamul and Woo, Simon S. and Anwar, Saeed and Lee, IK Hyun and Muhammad, Khan}, title = {LoLI-Street: Benchmarking Low-light Image Enhancement and Beyond}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1250-1267} }
Fine-tuning Large Language Models for Automatic Font Skeleton Generation: Exploration and Analysis: Yuxuan Liu,

Yasuhisa Fujii,

Xinru Zhu,

Kayoko Nohara; [pdf]
[bibtex]
@InProceedings{Liu_2024_ACCV, author = {Liu, Yuxuan and Fujii, Yasuhisa and Zhu, Xinru and Nohara, Kayoko}, title = {Fine-tuning Large Language Models for Automatic Font Skeleton Generation: Exploration and Analysis}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4156-4171} }
Pluggable Style Representation Learning for Multi-Style Transfer: Hongda Liu,

Longguang Wang,

Weijun Guan,

Ye Zhang,

Yulan Guo; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2024_ACCV, author = {Liu, Hongda and Wang, Longguang and Guan, Weijun and Zhang, Ye and Guo, Yulan}, title = {Pluggable Style Representation Learning for Multi-Style Transfer}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {2087-2104} }
CNN Mixture-of-Depths: Rinor Cakaj,

Jens Mehnert,

Bin Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cakaj_2024_ACCV, author = {Cakaj, Rinor and Mehnert, Jens and Yang, Bin}, title = {CNN Mixture-of-Depths}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3480-3498} }
Optimized Breast Lesion Segmentation in Ultrasound Videos Across Varied Resource-Scant Environments: Yunhao Li,

Zibin Chen,

Junming Yan,

Ziyu Ding,

Jie Li,

Teng Huang,

Xiaoqing Pei,

Zheng Zhang,

Qiong Wang,

Yan Pang; [pdf]
[bibtex]
@InProceedings{Li_2024_ACCV, author = {Li, Yunhao and Chen, Zibin and Yan, Junming and Ding, Ziyu and Li, Jie and Huang, Teng and Pei, Xiaoqing and Zhang, Zheng and Wang, Qiong and Pang, Yan}, title = {Optimized Breast Lesion Segmentation in Ultrasound Videos Across Varied Resource-Scant Environments}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4318-4333} }
Wavelet-based Mamba with Fourier Adjustment for Low-light Image Enhancement: Junhao Tan,

Songwen Pei,

Wei Qin,

Bo Fu,

Ximing Li,

Libo Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tan_2024_ACCV, author = {Tan, Junhao and Pei, Songwen and Qin, Wei and Fu, Bo and Li, Ximing and Huang, Libo}, title = {Wavelet-based Mamba with Fourier Adjustment for Low-light Image Enhancement}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3449-3464} }
Spectral Modality-Aware Interactive Fusion Network for HSI Super-Resolution: Meng Xu,

Jiayou Mao,

Ziqian Mo,

Xiyou Fu,

Sen Jia; [pdf]
[bibtex]
@InProceedings{Xu_2024_ACCV, author = {Xu, Meng and Mao, Jiayou and Mo, Ziqian and Fu, Xiyou and Jia, Sen}, title = {Spectral Modality-Aware Interactive Fusion Network for HSI Super-Resolution}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4544-4560} }
MonoDSSMs: Efficient Monocular 3D Object Detection with Depth-Aware State Space Models: Kiet Dang Vu,

Trung Thai Tran,

Duc Dung Nguyen; [pdf]
[bibtex]
@InProceedings{Vu_2024_ACCV, author = {Vu, Kiet Dang and Tran, Trung Thai and Nguyen, Duc Dung}, title = {MonoDSSMs: Efficient Monocular 3D Object Detection with Depth-Aware State Space Models}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3883-3900} }
BootsTAP: Bootstrapped Training for Tracking-Any-Point: Carl Doersch,

Pauline Luc,

Yi Yang,

Dilara Gokay,

Skanda Koppula,

Ankush Gupta,

Joseph Heyward,

Ignacio Rocco,

Ross Goroshin,

João Carreira,

Andrew Zisserman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Doersch_2024_ACCV, author = {Doersch, Carl and Luc, Pauline and Yang, Yi and Gokay, Dilara and Koppula, Skanda and Gupta, Ankush and Heyward, Joseph and Rocco, Ignacio and Goroshin, Ross and Carreira, Jo\~ao and Zisserman, Andrew}, title = {BootsTAP: Bootstrapped Training for Tracking-Any-Point}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3257-3274} }
Match me if you can: Semi-Supervised Semantic Correspondence Learning with Unpaired Images: Jiwon Kim,

Byeongho Heo,

Sangdoo Yun,

Seungryong Kim,

Dongyoon Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2024_ACCV, author = {Kim, Jiwon and Heo, Byeongho and Yun, Sangdoo and Kim, Seungryong and Han, Dongyoon}, title = {Match me if you can: Semi-Supervised Semantic Correspondence Learning with Unpaired Images}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3154-3171} }
HMGS: Hybrid Model of Gaussian Splatting for Enhancing 3D Reconstruction with Reflections: Hengbin Zhang,

Chengliang Wang,

Ji Liu,

Tian Jiang,

Yonggang Luo,

Lecheng Xie; [pdf]
[bibtex]
@InProceedings{Zhang_2024_ACCV, author = {Zhang, Hengbin and Wang, Chengliang and Liu, Ji and Jiang, Tian and Luo, Yonggang and Xie, Lecheng}, title = {HMGS: Hybrid Model of Gaussian Splatting for Enhancing 3D Reconstruction with Reflections}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3819-3835} }
Do they Share the Same Tail? Learning Individual Compositional Attribute Prototype for Generalized Zero-Shot Learning: Yuyan Shi,

Chenyi Jiang,

Run Shi,

Haofeng Zhang; [pdf]
[bibtex]
@InProceedings{Shi_2024_ACCV, author = {Shi, Yuyan and Jiang, Chenyi and Shi, Run and Zhang, Haofeng}, title = {Do they Share the Same Tail? Learning Individual Compositional Attribute Prototype for Generalized Zero-Shot Learning}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4595-4611} }
Multiview Detection with Cardboard Human Modeling: Jiahao Ma,

Zicheng Duan,

Liang Zheng,

Chuong Nguyen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2024_ACCV, author = {Ma, Jiahao and Duan, Zicheng and Zheng, Liang and Nguyen, Chuong}, title = {Multiview Detection with Cardboard Human Modeling}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {870-886} }
Class-Aware Contrastive Learning for Fine-Grained Skeleton-Based Action Recognition: Xinyu Bian,

Dongliang Chang,

Yuqi Yang,

Zhongjiang He,

Kongming Liang,

Zhanyu Ma; [pdf]
[bibtex]
@InProceedings{Bian_2024_ACCV, author = {Bian, Xinyu and Chang, Dongliang and Yang, Yuqi and He, Zhongjiang and Liang, Kongming and Ma, Zhanyu}, title = {Class-Aware Contrastive Learning for Fine-Grained Skeleton-Based Action Recognition}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3638-3654} }
HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Prior: David Svitov,

Pietro Morerio,

Lourdes Agapito,

Alessio Del Bue; [pdf] [arXiv]
[bibtex]
@InProceedings{Svitov_2024_ACCV, author = {Svitov, David and Morerio, Pietro and Agapito, Lourdes and Del Bue, Alessio}, title = {HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Prior}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4051-4068} }
Moving Object Segmentation: All You Need Is SAM (and Flow): Junyu Xie,

Charig Yang,

Weidi Xie,

Andrew Zisserman; [pdf] [arXiv]
[bibtex]
@InProceedings{Xie_2024_ACCV, author = {Xie, Junyu and Yang, Charig and Xie, Weidi and Zisserman, Andrew}, title = {Moving Object Segmentation: All You Need Is SAM (and Flow)}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {162-178} }
EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectors: Sangwon Kim,

Dasom Ahn,

Byoung Chul Ko,

In-su Jang,

Kwang-Ju Kim; [pdf]
[bibtex]
@InProceedings{Kim_2024_ACCV, author = {Kim, Sangwon and Ahn, Dasom and Ko, Byoung Chul and Jang, In-su and Kim, Kwang-Ju}, title = {EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectors}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3432-3448} }
SpikeGS: Learning 3D Gaussian Fields from Continuous Spike Stream: Jinze Yu,

Xin Peng,

Zhengda Lu,

Laurent Kneip,

Yiqun Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2024_ACCV, author = {Yu, Jinze and Peng, Xin and Lu, Zhengda and Kneip, Laurent and Wang, Yiqun}, title = {SpikeGS: Learning 3D Gaussian Fields from Continuous Spike Stream}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4280-4298} }
M-RAT: a Multi-grained Retrieval Augmentation Transformer for Image Captioning: Jiayan Song,

Renjie Pan,

Jun Zhou,

Hua Yang; [pdf]
[bibtex]
@InProceedings{Song_2024_ACCV, author = {Song, Jiayan and Pan, Renjie and Zhou, Jun and Yang, Hua}, title = {M-RAT: a Multi-grained Retrieval Augmentation Transformer for Image Captioning}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {3865-3882} }
Cross-Modality Complementary Learning for Video-based Cloth-Changing Person Re-Identification: Vuong D. Nguyen,

Pranav Mantini,

Shishir K. Shah; [pdf] [supp]
[bibtex]
@InProceedings{Nguyen_2024_ACCV, author = {Nguyen, Vuong D. and Mantini, Pranav and Shah, Shishir K.}, title = {Cross-Modality Complementary Learning for Video-based Cloth-Changing Person Re-Identification}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {88-107} }
ULTRON: Unifying Local Transformer and Convolution for Large-scale Image Retrieval: Minseong Kweon,

Jinsun Park; [pdf] [supp]
[bibtex]
@InProceedings{Kweon_2024_ACCV, author = {Kweon, Minseong and Park, Jinsun}, title = {ULTRON: Unifying Local Transformer and Convolution for Large-scale Image Retrieval}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4000-4016} }
KhmerST: A Low-Resource Khmer Scene Text Detection and Recognition Benchmark: Vannkinh Nom,

Souhail Bakkali,

Muhammad Muzzamil Luqman,

Mickaël Coustaty,

Jean-Marc Ogier; [pdf] [arXiv]
[bibtex]
@InProceedings{Nom_2024_ACCV, author = {Nom, Vannkinh and Bakkali, Souhail and Luqman, Muhammad Muzzamil and Coustaty, Micka\"el and Ogier, Jean-Marc}, title = {KhmerST: A Low-Resource Khmer Scene Text Detection and Recognition Benchmark}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {1777-1792} }
On Unsupervised Partial Shape Correspondence: Amit Bracha,

Thomas Dagès,

Ron Kimmel; [pdf] [supp]
[bibtex]
@InProceedings{Bracha_2024_ACCV, author = {Bracha, Amit and Dag\`es, Thomas and Kimmel, Ron}, title = {On Unsupervised Partial Shape Correspondence}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4488-4504} }
Learning Non-Uniform Step Sizes for Neural Network Quantization: Shinya Gongyo,

Jinrong Liang,

Mitsuru Ambai,

Rei Kawakami,

Ikuro Sato; [pdf] [supp]
[bibtex]
@InProceedings{Gongyo_2024_ACCV, author = {Gongyo, Shinya and Liang, Jinrong and Ambai, Mitsuru and Kawakami, Rei and Sato, Ikuro}, title = {Learning Non-Uniform Step Sizes for Neural Network Quantization}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2024}, pages = {4385-4402} }