{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:16:51Z","timestamp":1775578611287,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":99,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276108"],"award-info":[{"award-number":["62276108"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680960","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"7947-7956","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4899-9320","authenticated-orcid":false,"given":"Lianghui","family":"Zhu","sequence":"first","affiliation":[{"name":"School of EIC, Huazhong University of Science & Technology, Wuhan, Hubei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7093-2280","authenticated-orcid":false,"given":"Junwei","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of EIC, Huazhong University of Science & Technology, Wuhan, Hubei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6021-1358","authenticated-orcid":false,"given":"Yan","family":"Liu","sequence":"additional","affiliation":[{"name":"Alipay Tian Qian Security Lab, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6102-7350","authenticated-orcid":false,"given":"Xin","family":"Hao","sequence":"additional","affiliation":[{"name":"Alipay Tian Qian Security Lab, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4582-7488","authenticated-orcid":false,"given":"Wenyu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of EIC, Huazhong University of Science & Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6732-7823","authenticated-orcid":false,"given":"Xinggang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of EIC, Huazhong University of Science & Technology, Wuhan, Hubei, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00231"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_16"},{"key":"e_1_3_2_1_3_1","volume-title":"Proc. of CVPR.","author":"Arun Aditya","unstructured":"Aditya Arun, C. V. Jawahar, and M. Pawan Kumar. 2019. Dissimilarity Coefficient Based Weakly Supervised Object Detection. In Proc. of CVPR."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.311"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Jianjun Chen Shancheng Fang Hongtao Xie Zheng-Jun Zha Yue Hu and Jianlong Tan. 2021. End-to-end Boundary Exploration for Weakly-supervised Semantic Segmentation. In ACM MM. 10 pages.","DOI":"10.1145\/3474085.3475402"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_4"},{"key":"e_1_3_2_1_7_1","volume-title":"Segment anything model (sam) enhanced pseudo labels for weakly supervised semantic segmentation. ArXiv preprint","author":"Chen Tianle","year":"2023","unstructured":"Tianle Chen, Zheda Mai, Ruiwen Li, and Wei-lun Chao. 2023. Segment anything model (sam) enhanced pseudo labels for weakly supervised semantic segmentation. ArXiv preprint (2023)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Zhiwei Chen Liujuan Cao Yunhang Shen Feihong Lian Yongjian Wu and Rongrong Ji. 2021. E2Net: Excitative-Expansile Learning for Weakly Supervised Object Localization. In ACM MM. 9 pages.","DOI":"10.1145\/3474085.3475211"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01301"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00307"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.545"},{"key":"e_1_3_2_1_13_1","volume-title":"Proc. of ICLR.","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In Proc. of ICLR."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_31"},{"key":"e_1_3_2_1_15_1","volume-title":"MutexMatch: Semi-Supervised Learning With Mutex-Based Consistency Regularization. TNNLS","author":"Duan Yue","year":"2024","unstructured":"Yue Duan, Zhen Zhao, Lei Qi, Lei Wang, Luping Zhou, Yinghuan Shi, and Yang Gao. 2024. MutexMatch: Semi-Supervised Learning With Mutex-Based Consistency Regularization. TNNLS (2024)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01477"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.29068"},{"key":"e_1_3_2_1_18_1","volume-title":"Luc Van Gool, Christopher KI Williams, John Winn, and Andrew Zisserman.","author":"Everingham Mark","year":"2015","unstructured":"Mark Everingham, SM Ali Eslami, Luc Van Gool, Christopher KI Williams, John Winn, and Andrew Zisserman. 2015. The pascal visual object classes challenge: A retrospective. IJCV (2015)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_23"},{"key":"e_1_3_2_1_20_1","volume-title":"Proc. of ICML.","author":"Fu Daniel Y.","year":"2020","unstructured":"Daniel Y. Fu, Mayee F. Chen, Frederic Sala, Sarah M. Hooper, Kayvon Fatahalian, and Christopher R\u00e9. 2020. Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods. In Proc. of ICML."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_10"},{"key":"e_1_3_2_1_22_1","volume-title":"Scott","author":"Ge Weifeng","year":"2019","unstructured":"Weifeng Ge, Weilin Huang, Sheng Guo, and Matthew R. Scott. 2019. Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance Segmentation. In Proc. of ICCV."},{"key":"e_1_3_2_1_23_1","volume-title":"Proc. of NeurIPS.","author":"Han Kai","year":"2021","unstructured":"Kai Han, An Xiao, Enhua Wu, Jianyuan Guo, Chunjing Xu, and Yunhe Wang. 2021. Transformer in Transformer. In Proc. of NeurIPS."},{"key":"e_1_3_2_1_24_1","volume-title":"Girshick","author":"He Kaiming","year":"2017","unstructured":"Kaiming He, Georgia Gkioxari, Piotr Doll\u00e1r, and Ross B. Girshick. 2017. Mask R-CNN. In Proc. of ICCV."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Yu-Hsing Hsieh Guan-Sheng Chen Shun-Xian Cai Ting-Yun Wei Huei-Fang Yang and Chu-Song Chen. 2023. Class-incremental Continual Learning for Instance Segmentation with Image-level Weak Supervision. In ICCV.","DOI":"10.1109\/ICCV51070.2023.00121"},{"key":"e_1_3_2_1_27_1","volume-title":"Proc. of NeurIPS.","author":"Hsu Cheng-Chun","year":"2019","unstructured":"Cheng-Chun Hsu, Kuang-Jui Hsu, Chung-Chi Tsai, Yen-Yu Lin, and Yung-Yu Chuang. 2019. Weakly Supervised Instance Segmentation using the Bounding Box Tightness Prior. In Proc. of NeurIPS."},{"key":"e_1_3_2_1_28_1","volume-title":"Weakly supervised instance segmentation using multi-stage erasing refinement and saliency-guided proposals ordering. JVCI","author":"Hu Zheng","year":"2020","unstructured":"Zheng Hu, Zhi Liu, Gongyang Li, Linwei Ye, Lei Zhou, and Yang Wang. 2020. Weakly supervised instance segmentation using multi-stage erasing refinement and saliency-guided proposals ordering. JVCI (2020)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Zitong Huang Yiping Bao Bowen Dong Erjin Zhou and Wangmeng Zuo. 2022. W2N:Switching From Weak Supervision to Noisy Supervision for Object Detection. arxiv: 2207.12104 [cs.CV]","DOI":"10.1007\/978-3-031-20056-4_41"},{"key":"e_1_3_2_1_30_1","volume-title":"Proc. of NeurIPS.","author":"Huang Zeyi","year":"2020","unstructured":"Zeyi Huang, Yang Zou, B. V. K. Vijaya Kumar, and Dong Huang. 2020. Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection. In Proc. of NeurIPS."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00106"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16261"},{"key":"e_1_3_2_1_33_1","volume-title":"Segment Anything is A Good Pseudo-label Generator for Weakly Supervised Semantic Segmentation. ArXiv preprint","author":"Jiang Peng-Tao","year":"2023","unstructured":"Peng-Tao Jiang and Yuqi Yang. 2023. Segment Anything is A Good Pseudo-label Generator for Weakly Supervised Semantic Segmentation. ArXiv preprint (2023)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.457"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.181"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00424"},{"key":"e_1_3_2_1_37_1","volume-title":"ArXiv preprint","author":"Kirillov Alexander","year":"2023","unstructured":"Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Doll\u00e1r, and Ross Girshick. 2023. Segment Anything. ArXiv preprint (2023)."},{"key":"e_1_3_2_1_38_1","unstructured":"Ivan Laptev Vadim Kantorov Maxime Oquab and Minsu Cho. [n. d.]. ContextLocNet: Context-aware deep network models for weakly supervised localization. ( [n. d.])."},{"key":"e_1_3_2_1_39_1","volume-title":"Proc. of BMVC.","author":"Laradji Issam H.","year":"2019","unstructured":"Issam H. Laradji, David V\u00e1zquez, and Mark Schmidt. 2019. Where are the Masks: Instance Segmentation with Image-level Supervision. In Proc. of BMVC."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00267"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.382"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_1"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00983"},{"key":"e_1_3_2_1_44_1","unstructured":"Zecheng Li Zening Zeng Yuqi Liang and Jin-Gang Yu. 2023. Complete Instances Mining for Weakly Supervised Instance Segmentation. In IJCAI."},{"key":"e_1_3_2_1_45_1","volume-title":"Weakly Supervised Instance Segmentation Using Hybrid Networks. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2019","author":"Liao Shisha","year":"2019","unstructured":"Shisha Liao, Yongqing Sun, Chenqiang Gao, Pranav Shenoy K. P, Song Mu, Jun Shimamura, and Atsushi Sagata. 2019. Weakly Supervised Instance Segmentation Using Hybrid Networks. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2019, Brighton, United Kingdom, May 12--17, 2019."},{"key":"e_1_3_2_1_46_1","unstructured":"Jianghang Lin Yunhang Shen Bingquan Wang Shaohui Lin Ke Li and Liujuan Cao. 2024. Weakly Supervised Open-Vocabulary Object Detection. In AAAI."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_48_1","volume-title":"Proc. of CVPR.","author":"Liu Boxiao","year":"2019","unstructured":"Boxiao Liu, Yan Gao, Nan Guo, Xiaochun Ye, Fang Wan, Haihang You, and Dongrui Fan. 2019. Utilizing the Instability in Weakly Supervised Object Detection.. In Proc. of CVPR."},{"key":"e_1_3_2_1_49_1","volume-title":"Leveraging instance-, image-and dataset-level information for weakly supervised instance segmentation","author":"Liu Yun","year":"2020","unstructured":"Yun Liu, Yu-Huan Wu, Peisong Wen, Yujun Shi, Yu Qiu, and Ming-Ming Cheng. 2020. Leveraging instance-, image-and dataset-level information for weakly supervised instance segmentation. IEEE TPAMI (2020)."},{"key":"e_1_3_2_1_50_1","volume-title":"Proc. of ICML.","author":"Locatello Francesco","year":"2020","unstructured":"Francesco Locatello, Ben Poole, Gunnar R\u00e4tsch, Bernhard Sch\u00f6lkopf, Olivier Bachem, and Michael Tschannen. 2020. Weakly-Supervised Disentanglement Without Compromises. In Proc. of ICML."},{"key":"e_1_3_2_1_51_1","volume-title":"Segment anything in medical images. ArXiv preprint","author":"Ma Jun","year":"2023","unstructured":"Jun Ma and Bo Wang. 2023. Segment anything in medical images. ArXiv preprint (2023)."},{"key":"e_1_3_2_1_52_1","volume-title":"WS-RCNN: Learning to Score Proposals for Weakly Supervised Instance Segmentation. Sensors","author":"Ou Jia-Rong","year":"2021","unstructured":"Jia-Rong Ou, Shu-Le Deng, and Jin-Gang Yu. 2021. WS-RCNN: Learning to Score Proposals for Weakly Supervised Instance Segmentation. Sensors (2021)."},{"key":"e_1_3_2_1_53_1","volume-title":"Multiscale combinatorial grouping for image segmentation and object proposal generation","author":"Pont-Tuset Jordi","year":"2016","unstructured":"Jordi Pont-Tuset, Pablo Arbelaez, Jonathan T Barron, Ferran Marques, and Jitendra Malik. 2016. Multiscale combinatorial grouping for image segmentation and object proposal generation. IEEE TPAMI (2016)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"crossref","unstructured":"Chen Qian and Hui Zhang. 2022. Region-based Pixels Integration Mechanism for Weakly Supervised Semantic Segmentation. In ACM MM. 9 pages.","DOI":"10.1145\/3503161.3548141"},{"key":"e_1_3_2_1_55_1","volume-title":"Proc. of NeurIPS.","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross B. Girshick, and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Proc. of NeurIPS."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01061"},{"key":"e_1_3_2_1_57_1","volume-title":"Proc. of ICML.","author":"Schroeter Julien","unstructured":"Julien Schroeter, Kirill A. Sidorov, and A. David Marshall. 2019. Weakly-Supervised Temporal Localization via Occurrence Count Learning. In Proc. of ICML."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_18"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"crossref","unstructured":"Feifei Shao Yawei Luo Li Zhang Lu Ye Siliang Tang Yi Yang and Jun Xiao. 2021. Improving Weakly Supervised Object Localization via Causal Intervention. In ACM MM. 9 pages.","DOI":"10.1145\/3474085.3475485"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00809"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_8"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00079"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01383"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_21"},{"key":"e_1_3_2_1_65_1","volume-title":"An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems. ArXiv preprint","author":"Sun Weixuan","year":"2023","unstructured":"Weixuan Sun, Zheyuan Liu, Yanhao Zhang, Yiran Zhong, and Nick Barnes. 2023. An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems. ArXiv preprint (2023)."},{"key":"e_1_3_2_1_66_1","volume-title":"Dual-Gradients Localization Framework for Weakly Supervised Object Localization. In MM '20: The 28th ACM International Conference on Multimedia, Virtual Event \/ Seattle, WA, USA, October 12--16","author":"Tan Chuangchuang","year":"2020","unstructured":"Chuangchuang Tan, Guanghua Gu, Tao Ruan, Shikui Wei, and Yao Zhao. 2020. Dual-Gradients Localization Framework for Weakly Supervised Object Localization. In MM '20: The 28th ACM International Conference on Multimedia, Virtual Event \/ Seattle, WA, USA, October 12--16, 2020."},{"key":"e_1_3_2_1_67_1","volume-title":"Pcl: Proposal cluster learning for weakly supervised object detection","author":"Tang Peng","year":"2018","unstructured":"Peng Tang, Xinggang Wang, Song Bai, Wei Shen, Xiang Bai, Wenyu Liu, and Alan Yuille. 2018. Pcl: Proposal cluster learning for weakly supervised object detection. IEEE TPAMI (2018)."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.326"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_22"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00540"},{"key":"e_1_3_2_1_71_1","volume-title":"Proc. of ICML.","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9gou. 2021. Training data-efficient image transformers & distillation through attention. In Proc. of ICML."},{"key":"e_1_3_2_1_72_1","volume-title":"Smeulders","author":"Uijlings Jasper R. R.","year":"2013","unstructured":"Jasper R. R. Uijlings, Koen E. A. van de Sande, Theo Gevers, and Arnold W. M. Smeulders. 2013. Selective Search for Object Recognition. IJCV (2013)."},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00230"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00141"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01009"},{"key":"e_1_3_2_1_76_1","volume-title":"Proc. of ICML.","author":"Wang Xinggang","year":"2013","unstructured":"Xinggang Wang, Baoyuan Wang, Xiang Bai, Wenyu Liu, and Zhuowen Tu. 2013. Max-Margin Multiple-Instance Dictionary Learning. In Proc. of ICML."},{"key":"e_1_3_2_1_77_1","volume-title":"Proc. of ICML.","author":"Xu Chang","year":"2014","unstructured":"Chang Xu, Dacheng Tao, Chao Xu, and Yong Rui. 2014. Large-margin Weakly Supervised Dimensionality Reduction. In Proc. of ICML."},{"key":"e_1_3_2_1_78_1","unstructured":"Jingyuan Xu Hongtao Xie Chuanbin Liu and Yongdong Zhang. 2022. Proxy Probing Decoder for Weakly Supervised Object Localization: A Baseline Investigation. In ACM MM."},{"key":"e_1_3_2_1_79_1","unstructured":"Jianjun Xu Hongtao Xie Hai Xu Yuxin Wang Sun-ao Liu and Yongdong Zhang. 2022. Boat in the Sky: Background Decoupling and Object-aware Pooling for Weakly Supervised Semantic Segmentation. In ACM MM."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00993"},{"key":"e_1_3_2_1_81_1","volume-title":"Objectness Consistent Representation for Weakly Supervised Object Detection. In MM '20: The 28th ACM International Conference on Multimedia, Virtual Event \/ Seattle, WA, USA, October 12--16","author":"Yang Ke","year":"2020","unstructured":"Ke Yang, Peng Zhang, Peng Qiao, Zhiyuan Wang, Dongsheng Li, and Yong Dou. 2020. Objectness Consistent Representation for Weakly Supervised Object Detection. In MM '20: The 28th ACM International Conference on Multimedia, Virtual Event \/ Seattle, WA, USA, October 12--16, 2020."},{"key":"e_1_3_2_1_82_1","volume-title":"Fine-Grained Visual Prompting. ArXiv preprint","author":"Yang Lingfeng","year":"2023","unstructured":"Lingfeng Yang, Yueze Wang, Xiang Li, Xinlong Wang, and Jian Yang. 2023. Fine-Grained Visual Prompting. ArXiv preprint (2023)."},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16429"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"crossref","unstructured":"Yufei Yin Jiajun Deng Wengang Zhou Li Li and Houqiang Li. 2023. Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection. In ICCV.","DOI":"10.1109\/ICCV51070.2023.00645"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00838"},{"key":"e_1_3_2_1_86_1","volume-title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection. arxiv: 2203.03605 [cs.CV]","author":"Zhang Hao","year":"2022","unstructured":"Hao Zhang, Feng Li, Shilong Liu, Lei Zhang, Hang Su, Jun Zhu, Lionel M. Ni, and Heung-Yeung Shum. 2022. DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection. arxiv: 2203.03605 [cs.CV]"},{"key":"e_1_3_2_1_87_1","volume-title":"Weakly Supervised Instance Segmentation via Category-aware Centerness Learning with Localization Supervision. PR","author":"Zhang Jiabin","year":"2023","unstructured":"Jiabin Zhang, Hu Su, Yonghao He, and Wei Zou. 2023. Weakly Supervised Instance Segmentation via Category-aware Centerness Learning with Localization Supervision. PR (2023)."},{"key":"e_1_3_2_1_88_1","volume-title":"Weakly supervised instance segmentation by exploring entire object regions","author":"Zhang Ke","year":"2021","unstructured":"Ke Zhang, Chun Yuan, Yiming Zhu, Yong Jiang, and Lishu Luo. 2021. Weakly supervised instance segmentation by exploring entire object regions. IEEE TMM (2021)."},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"crossref","unstructured":"Meijie Zhang Jianwu Li and Tianfei Zhou. 2022. Multi-Granular Semantic Mining for Weakly Supervised Semantic Segmentation. In ACM MM.","DOI":"10.1145\/3503161.3547919"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00448"},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"crossref","unstructured":"Xiangrong Zhang Zelin Peng Peng Zhu Tianyang Zhang Chen Li Huiyu Zhou and Licheng Jiao. 2021. Adaptive Affinity Loss and Erroneous Pseudo-Label Refinement for Weakly Supervised Semantic Segmentation. In ACM MM.","DOI":"10.1145\/3474085.3475675"},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00103"},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00399"},{"key":"e_1_3_2_1_95_1","volume-title":"A brief introduction to weakly supervised learning. National science review","author":"Zhou Zhi-Hua","year":"2018","unstructured":"Zhi-Hua Zhou. 2018. A brief introduction to weakly supervised learning. National science review (2018)."},{"key":"e_1_3_2_1_96_1","volume-title":"WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation. ArXiv preprint","author":"Zhu Lianghui","year":"2023","unstructured":"Lianghui Zhu, Yingyue Li, Jieming Fang, Yan Liu, Hao Xin, Wenyu Liu, and Xinggang Wang. 2023. WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation. ArXiv preprint (2023)."},{"key":"e_1_3_2_1_97_1","volume-title":"An encoder-decoder framework with dynamic convolution for weakly supervised instance segmentation. IET Computer Vision","author":"Zhu Liangjun","year":"2023","unstructured":"Liangjun Zhu, Li Peng, Shuchen Ding, and Zhongren Liu. 2023. An encoder-decoder framework with dynamic convolution for weakly supervised instance segmentation. IET Computer Vision (2023)."},{"key":"e_1_3_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00323"},{"key":"e_1_3_2_1_99_1","volume-title":"Proc. of ECCV.","author":"Lawrence Zitnick C","year":"2014","unstructured":"C Lawrence Zitnick and Piotr Doll\u00e1r. 2014. Edge boxes: Locating object proposals from edges. In Proc. of ECCV."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680960","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680960","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:34Z","timestamp":1750295854000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680960"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":99,"alternative-id":["10.1145\/3664647.3680960","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680960","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}