Table of Contents

• Box-Supervised Instance Segmentation with Level Set EvolutionWentong Li, Wenyu Liu 0001, Jianke Zhu, Miaomiao Cui, Xian-Sheng Hua 0001, Lei Zhang 0006. 1-18 [doi]
• Improving Vision Transformers by Revisiting High-Frequency ComponentsJiawang Bai, Li Yuan, Shu-Tao Xia, Shuicheng Yan, Zhifeng Li 0001, Wei Liu 0005. 1-18 [doi]
• Recurrent Bilinear Optimization for Binary Neural NetworksSheng Xu, Yanjing Li, Tiancheng Wang, Teli Ma, Baochang Zhang 0001, Peng Gao, Yu Qiao 0001, Jinhu Lü, Guodong Guo. 19-35 [doi]
• Point Primitive Transformer for Long-Term 4D Point Cloud Video UnderstandingHao Wen, Yunze Liu, Jingwei Huang, Bo Duan, Li Yi. 19-35 [doi]
• Neural Architecture Search for Spiking Neural NetworksYoungeun Kim, Yuhang Li, Hyoungseob Park, Yeshwanth Venkatesha, Priyadarshini Panda. 36-56 [doi]
• Adaptive Agent Transformer for Few-Shot SegmentationYuan Wang, Rui Sun, Zhe Zhang, Tianzhu Zhang. 36-52 [doi]
• Waymo Open Dataset: Panoramic Video Panoptic SegmentationJieru Mei, Alex Zihao Zhu, Xinchen Yan, Hang Yan, Siyuan Qiao, Liang-Chieh Chen, Henrik Kretzschmar. 53-72 [doi]
• Where to Focus: Investigating Hierarchical Attention Relationship for Fine-Grained Visual ClassificationYang Liu, Lei Zhou 0008, Pengcheng Zhang, Xiao Bai 0001, Lin Gu 0003, Xiaohan Yu, Jun Zhou 0001, Edwin R. Hancock. 57-73 [doi]
• TransFGU: A Top-Down Approach to Fine-Grained Unsupervised Semantic SegmentationZhaoyuan Yin, Pichao Wang, Fan Wang, Xianzhe Xu, Hanling Zhang, Hao Li 0030, Rong Jin 0001. 73-89 [doi]
• DaViT: Dual Attention Vision TransformersMingyu Ding, Bin Xiao 0004, Noel Codella, Ping Luo 0002, Jingdong Wang 0001, Lu Yuan. 74-92 [doi]
• AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-Shot InteractionsYian Wang, Ruihai Wu, Kaichun Mo, Jiaqi Ke, Qingnan Fan, Leonidas J. Guibas, Hao Dong 0003. 90-107 [doi]
• Optimal Transport for Label-Efficient Visible-Infrared Person Re-IdentificationJiangming Wang, Zhizhong Zhang, Mingang Chen, Yi Zhang, Cong Wang, Bin Sheng, Yanyun Qu, Yuan Xie 0006. 93-109 [doi]
• Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot SegmentationSunghwan Hong, Seokju Cho, Jisu Nam, Stephen Lin 0001, Seungryong Kim. 108-126 [doi]
• Locality Guidance for Improving Vision Transformers on Tiny DatasetsKehan Li 0002, Runyi Yu, Zhennan Wang, Li Yuan, Guoli Song, Jie Chen. 110-127 [doi]
• Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and ApplicationsLingzhi Zhang, Shenghao Zhou, Simon Stent, Jianbo Shi. 127-145 [doi]
• Neighborhood Collective Estimation for Noisy Label Identification and CorrectionJichang Li, Guanbin Li, Feng Liu 0036, Yizhou Yu. 128-145 [doi]
• Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free ReplayHuan Liu, Li Gu, Zhixiang Chi, Yang Wang 0003, Yuanhao Yu, Jun Chen 0005, Jin Tang. 146-162 [doi]
• Perceptual Artifacts Localization for InpaintingLingzhi Zhang, YuQian Zhou, Connelly Barnes, Sohrab Amirghodsi, Zhe Lin 0001, Eli Shechtman, Jianbo Shi. 146-164 [doi]
• Anti-retroactive Interference for Lifelong LearningRunqi Wang, Yuxiang Bao, Baochang Zhang 0001, Jianzhuang Liu, Wentao Zhu, Guodong Guo. 163-178 [doi]
• 2D Amodal Instance Segmentation Guided by 3D Shape PriorZhixuan Li, Weining Ye, Tingting Jiang, Tie-Jun Huang 0001. 165-181 [doi]
• Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-Tailed LearningHualiang Wang, Siming FU, Xiaoxuan He, Hangxiang Fang, Zuozhu Liu, Haoji Hu. 179-196 [doi]
• Data Efficient 3D Learner via Knowledge Transferred from 2D ModelPing-Chung Yu, Cheng Sun 0004, Min Sun. 182-198 [doi]
• Dynamic Metric Learning with Cross-Level Concept DistillationWenzhao Zheng, Yuan Huang 0002, Borui Zhang, Jie Zhou 0001, Jiwen Lu. 197-213 [doi]
• Adaptive Spatial-BCE Loss for Weakly Supervised Semantic SegmentationTong Wu, Guangyu Gao, Junshi Huang, Xiaolin Wei, Xiaoming Wei, Chi Harold Liu. 199-216 [doi]
• MENet: A Memory-Based Network with Dual-Branch for Efficient Event Stream ProcessingLinhui Sun, Yifan Zhang 0001, Ke Cheng, Jian Cheng 0001, Hanqing Lu. 214-234 [doi]
• Dense Gaussian Processes for Few-Shot SegmentationJoakim Johnander, Johan Edstedt, Michael Felsberg, Fahad Shahbaz Khan, Martin Danelljan. 217-234 [doi]
• 3D Instances as 1D KernelsYizheng Wu, Min Shi, Shuaiyuan Du, Hao Lu 0003, Zhiguo Cao 0001, Weicai Zhong. 235-252 [doi]
• Out-of-distribution Detection with Boundary Aware LearningSen Pei, Xin Zhang, Bin Fan, Gaofeng Meng. 235-251 [doi]
• Learning Hierarchy Aware Features for Reducing Mistake SeverityAshima Garg, Depanshu Sani, Saket Anand. 252-267 [doi]
• TransMatting: Enhancing Transparent Objects Matting with TransformersHuanqia Cai, Fanglei Xue, Lele Xu, Lili Guo. 253-269 [doi]
• Learning to Detect Every Thing in an Open WorldKuniaki Saito, Ping Hu, Trevor Darrell, Kate Saenko. 268-284 [doi]
• MVSalNet: Multi-view Augmentation for RGB-D Salient Object DetectionJiayuan Zhou, Lijun Wang, Huchuan Lu, Kaining Huang, Xinchu Shi, Bocong Liu. 270-287 [doi]
• KVT: k-NN Attention for Boosting Vision TransformersPichao Wang, Xue Wang, Fan Wang, Ming Lin, Shuning Chang, Hao Li 0030, Rong Jin 0001. 285-302 [doi]
• k-means Mask TransformerQihang Yu, Huiyu Wang, Siyuan Qiao, Maxwell D. Collins, Yukun Zhu, Hartwig Adam, Alan L. Yuille, Liang-Chieh Chen. 288-307 [doi]
• Registration Based Few-Shot Anomaly DetectionChaoqin Huang, Haoyan Guan, Aofan Jiang, Ya Zhang 0002, Michael W. Spratling, Yan-Feng Wang. 303-319 [doi]
• SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation RobustnessJindong Gu, Hengshuang Zhao, Volker Tresp, Philip H. S. Torr. 308-325 [doi]
• Improving Robustness by Enhancing Weak SubnetsYong Guo, David Stutz, Bernt Schiele. 320-338 [doi]
• Adversarial Erasing Framework via Triplet with Gated Pyramid Pooling Layer for Weakly Supervised Semantic SegmentationSung Hoon Yoon, Hyeokjun Kweon, Jegyeong Cho, Shinjeong Kim, Kuk-Jin Yoon. 326-344 [doi]
• Learning Invariant Visual Representations for Compositional Zero-Shot LearningTian Zhang, Kongming Liang, Ruoyi Du, Xian Sun, Zhanyu Ma, Jun Guo 0002. 339-355 [doi]
• Continual Semantic Segmentation via Structure Preserving and Projected Feature AlignmentZihan Lin, Zilei Wang, Yixin Zhang. 345-361 [doi]
• Improving Covariance Conditioning of the SVD Meta-layer by OrthogonalityYue Song, Nicu Sebe, Wei Wang. 356-372 [doi]
• Interclass Prototype Relation for Few-Shot SegmentationAtsuro Okazawa. 362-378 [doi]
• Out-of-Distribution Detection with Semantic Mismatch Under MaskingYijun Yang, Ruiyuan Gao 0001, Qiang Xu 0001. 373-390 [doi]
• Slim Scissors: Segmenting Thin Object from Synthetic BackgroundKunyang Han, Jun Hao Liew, Jiashi Feng, Huawei Tian, Yao Zhao 0001, Yunchao Wei. 379-395 [doi]
• Data-Free Neural Architecture Search via Recursive Label CalibrationZechun Liu, Zhiqiang Shen, Yun Long, Eric P. Xing, Kwang-Ting Cheng, Chas Leichner. 391-406 [doi]
• Abstracting Sketches Through Simple PrimitivesStephan Alaniz, Massimiliano Mancini, Anjan Dutta 0001, Diego Marcos, Zeynep Akata. 396-412 [doi]
• Learning from Multiple Annotator Noisy Labels via Sample-Wise Label FusionZhengqi Gao, Fan-Keng Sun, Mingran Yang, Sucheng Ren, Zikai Xiong, Marc Engeler, Antonio Burazer, Linda Wildling, Luca Daniel, Duane S. Boning. 407-422 [doi]
• Multi-scale and Cross-scale Contrastive Learning for Semantic SegmentationTheodoros Pissas, Claudio S. Ravasio, Lyndon Da Cruz, Christos Bergeles. 413-429 [doi]
• Acknowledging the Unknown for Multi-label Learning with Single Positive LabelsDonghao Zhou, Pengfei Chen, Qiong Wang 0001, Guangyong Chen, Pheng-Ann Heng. 423-440 [doi]
• One-Trimap Video MattingHongje Seong, Seoung Wug Oh, Brian Price, Euntai Kim, Joon-Young Lee. 430-448 [doi]
• AutoMix: Unveiling the Power of Mixup for Stronger ClassifiersZicheng Liu 0006, Siyuan Li, Di Wu, Zihan Liu, Zhiyuan Chen 0008, Lirong Wu, Stan Z. Li. 441-458 [doi]
• $\mathrm {D^2ADA}$: Dynamic Density-Aware Active Domain Adaptation for Semantic SegmentationTsung-Han Wu, Yi-Syuan Liou, Shao-Ji Yuan, Hsin-Ying Lee, Tung-I Chen, Kuan-Chih Huang, Winston H. Hsu. 449-467 [doi]
• MaxViT: Multi-axis Vision TransformerZhengzhong Tu, Hossein Talebi, Han Zhang, Feng Yang, Peyman Milanfar, Alan C. Bovik, Yinxiao Li. 459-479 [doi]
• Learning Quality-aware Dynamic Memory for Video Object SegmentationYong Liu, Ran Yu, Fei Yin, Xinyuan Zhao, Wei Zhao, Weihao Xia, Yujiu Yang. 468-486 [doi]
• ScalableViT: Rethinking the Context-Oriented Generalization of Vision TransformerRui Yang, Hailong Ma, Jie Wu, Yansong Tang, XueFeng Xiao, Min Zheng, Xiu Li. 480-496 [doi]
• Learning Implicit Feature Alignment Function for Semantic SegmentationHanzhe Hu, Yinbo Chen, Jiarui Xu, Shubhankar Borse, Hong Cai, Fatih Porikli, Xiaolong Wang. 487-505 [doi]
• Three Things Everyone Should Know About Vision TransformersHugo Touvron, Matthieu Cord, Alaaeldin El-Nouby, Jakob Verbeek, Hervé Jégou. 497-515 [doi]
• Quantum Motion SegmentationFederica Arrigoni, Willi Menapace, Marcel Seelbach Benkner, Elisa Ricci 0001, Vladislav Golyanik. 506-523 [doi]
• DeiT III: Revenge of the ViTHugo Touvron, Matthieu Cord, Hervé Jégou. 516-533 [doi]
• Instance as Identity: A Generic Online Paradigm for Video Instance SegmentationFeng Zhu 0005, Zongxin Yang, Xin Yu 0002, Yi Yang, Yunchao Wei. 524-540 [doi]
• MixSKD: Self-Knowledge Distillation from Mixup for Image RecognitionChuanguang Yang, Zhulin An, Helong Zhou, Linhang Cai, Xiang-zhi, Jiwen Wu, Yongjun Xu, Qian Zhang 0009. 534-551 [doi]
• Laplacian Mesh Transformer: Dual Attention and Topology Aware Network for 3D Mesh Classification and SegmentationXiao-juan Li, Jie Yang, Fang-Lue Zhang. 541-560 [doi]
• Self-feature Distillation with Uncertainty Modeling for Degraded Image RecognitionZhou Yang, Weisheng Dong, Xin Li 0005, Jinjian Wu, Leida Li, Guangming Shi. 552-569 [doi]
• Geodesic-Former: A Geodesic-Guided Few-Shot 3D Point Cloud Instance SegmenterTuan Ngo, Khoi Nguyen. 561-578 [doi]
• Novel Class Discovery Without ForgettingK. J. Joseph, Sujoy Paul, Gaurav Aggarwal, Soma Biswas, Piyush Rai, Kai Han 0001, Vineeth N. Balasubramanian. 570-586 [doi]
• Union-Set Multi-source Model Adaptation for Semantic SegmentationZongyao Li, Ren Togo, Takahiro Ogawa 0001, Miki Haseyama. 579-595 [doi]
• SAFA: Sample-Adaptive Feature Augmentation for Long-Tailed Image ClassificationYan Hong, Jianfu Zhang 0003, Zhongyi Sun, Ke Yan. 587-603 [doi]
• Point MixSwap: Attentional Point Cloud Mixing via Swapping Matched Structural DivisionsArdian Umam, Cheng-Kun Yang, Yung-Yu Chuang, Jen-Hui Chuang, Yen-Yu Lin. 596-611 [doi]
• Negative Samples are at Large: Leveraging Hard-Distance Elastic Loss for Re-identificationHyungtae Lee, Sungmin Eum, Heesung Kwon. 604-620 [doi]
• BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object SegmentationYe Yu 0003, Jialing Yuan, Gaurav Mittal, Fuxin Li, Mei Chen. 612-629 [doi]
• Discrete-Constrained Regression for Local Counting ModelsHaipeng Xiong, Angela Yao. 621-636 [doi]
• SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object DetectionMinhyeok Lee, Chaewon Park, Suhwan Cho, Sangyoun Lee. 630-647 [doi]
• Breadcrumbs: Adversarial Class-Balanced Sampling for Long-Tailed RecognitionBo Liu, Haoxiang Li, Hao Kang, Gang Hua 0001, Nuno Vasconcelos. 637-653 [doi]
• Global Spectral Filter Memory Network for Video Object SegmentationYong Liu, Ran Yu, Jiahao Wang, Xinyuan Zhao, Yitong Wang, Yansong Tang, Yujiu Yang. 648-665 [doi]
• Chairs Can Be Stood On: Overcoming Object Bias in Human-Object Interaction DetectionGuangzhi Wang, Yangyang Guo, Yongkang Wong, Mohan S. Kankanhalli. 654-672 [doi]
• Video Instance Segmentation via Multi-Scale Spatio-Temporal Split Attention TransformerOmkar Thawakar, Sanath Narayan, Jiale Cao, Hisham Cholakkal, Rao Muhammad Anwer, Muhammad Haris Khan, Salman Khan 0001, Michael Felsberg, Fahad Shahbaz Khan. 666-681 [doi]
• A Fast Knowledge Distillation Framework for Visual RecognitionZhiqiang Shen, Eric P. Xing. 673-690 [doi]
• RankSeg: Adaptive Pixel Classification with Image Category Ranking for SegmentationHaodi He, Yuhui Yuan, Xiangyu Yue, Han Hu 0004. 682-700 [doi]
• DICE: Leveraging Sparsification for Out-of-Distribution DetectionYiyou Sun, Yixuan Li 0001. 691-708 [doi]
• Learning Topological Interactions for Multi-Class Medical Image SegmentationSaumya Gupta, Xiaoling Hu 0002, James Kaan, Michael Jin, Mutshipay Mpoy, Katherine Chung, Gagandeep Singh, Mary M. Saltz, Tahsin M. Kurç, Joel H. Saltz, Apostolos Tassiopoulos, Prateek Prasanna, Chao Chen 0012. 701-718 [doi]
• Invariant Feature Learning for Generalized Long-Tailed ClassificationKaihua Tang, Mingyuan Tao, Jiaxin Qi, Zhenguang Liu, Hanwang Zhang. 709-726 [doi]
• Unsupervised Segmentation in Real-World Images via Spelke Object InferenceHonglin Chen, Rahul Venkatesh, Yoni Friedman, Jiajun Wu 0001, Joshua B. Tenenbaum, Daniel L. K. Yamins, Daniel M. Bear. 719-735 [doi]
• Sliced Recursive TransformerZhiqiang Shen, Zechun Liu, Eric P. Xing. 727-744 [doi]
• A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-Language ModelMengde Xu, Zheng Zhang 0022, Fangyun Wei, Yutong Lin, Yue Cao 0001, Han Hu 0004, Xiang Bai. 736-753 [doi]