{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:24:24Z","timestamp":1778171064621,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"CCF-Baidu Open Fund","award":["CCF-BAIDUOF2020016"],"award-info":[{"award-number":["CCF-BAIDUOF2020016"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U19B2043, 61976185"],"award-info":[{"award-number":["U19B2043, 61976185"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Innovation Foundation","award":["2019R52002"],"award-info":[{"award-number":["2019R52002"]}]},{"name":"Zhejiang Natural Science Foundation","award":["LR19F020002"],"award-info":[{"award-number":["LR19F020002"]}]},{"name":"Fundamental Research Funds for the Central Universities"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475485","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T21:45:34Z","timestamp":1634593534000},"page":"3321-3329","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":22,"title":["Improving Weakly Supervised Object Localization via Causal Intervention"],"prefix":"10.1145","author":[{"given":"Feifei","family":"Shao","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yawei","family":"Luo","sequence":"additional","affiliation":[{"name":"Zhejiang University&Baidu Research, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang Insigma Digital Technology Co., Ltd., Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Ye","sequence":"additional","affiliation":[{"name":"Zhejiang University of Science and Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siliang","family":"Tang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Xiao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_37"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/2900423.2900679"},{"key":"e_1_3_2_1_3_1","volume-title":"Counterfactuals uncover the modular structure of deep generative models. arXiv preprint arXiv:1812.03253","author":"Besserve Michel","year":"2018"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01081"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00232"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001418550017"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.545"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11615-001-0048-3"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Yan Gao Boxiao Liu Nan Guo Xiaochun Ye Fang Wan Haihang You and Dongrui Fan. 2019. C-MIDN: Coupled Multiple Instance Detection Network With Segmentation Guidance for Weakly Supervised Object Detection. In ICCV.  Yan Gao Boxiao Liu Nan Guo Xiaochun Ye Fang Wan Haihang You and Dongrui Fan. 2019. C-MIDN: Coupled Multiple Instance Detection Network With Segmentation Guidance for Weakly Supervised Object Detection. In ICCV.","DOI":"10.1109\/ICCV.2019.00993"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298641"},{"key":"e_1_3_2_1_13_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR.  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR."},{"key":"e_1_3_2_1_14_1","volume-title":"The statistics of causal inference: A view from political methodology. Political Analysis","author":"Keele Luke","year":"2015"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.382"},{"key":"e_1_3_2_1_16_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014"},{"key":"e_1_3_2_1_17_1","unstructured":"Yawei Luo Ping Liu Tao Guan Junqing Yu and Yi Yang. 2020. Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation. In Advances in Neural Information Processing Systems. 20612--20623.  Yawei Luo Ping Liu Tao Guan Junqing Yu and Yi Yang. 2020. Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation. In Advances in Neural Information Processing Systems. 20612--20623."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3064379"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00261"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_26"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.58.110405.085542"},{"key":"e_1_3_2_1_22_1","unstructured":"Jinjie Mai Meng Yang and Wenfeng Luo. 2020. Erasing Integrated Learning: A Simple Yet Effective Approach for Weakly Supervised Object Localization. In CVPR.  Jinjie Mai Meng Yang and Wenfeng Luo. 2020. Erasing Integrated Learning: A Simple Yet Effective Approach for Weakly Supervised Object Localization. In CVPR."},{"key":"e_1_3_2_1_23_1","volume-title":"Causality: Models, Reasoning, and Inference.","author":"Neuberg Leland Gerson","year":"2003"},{"key":"e_1_3_2_1_24_1","volume-title":"Counterfactual vqa: A cause-effect look at language bias. arXiv preprint arXiv:2006.04315","author":"Niu Yulei","year":"2020"},{"key":"e_1_3_2_1_25_1","volume-title":"International Conference on Machine Learning. PMLR, 4036--4044","author":"Parascandolo Giambattista","year":"2018"},{"key":"e_1_3_2_1_26_1","volume-title":"Interpretation and identification of causal mediation. Psychological methods","author":"Pearl Judea","year":"2014"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Judea Pearl et al. 2009. Causal inference in statistics: An overview. Statistics surveys Vol. 3 (2009) 96--146.  Judea Pearl et al. 2009. Causal inference in statistics: An overview. Statistics surveys Vol. 3 (2009) 96--146.","DOI":"10.1214\/09-SS057"},{"key":"e_1_3_2_1_28_1","volume-title":"Causal inference in statistics: A primer","author":"Pearl Judea"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01087"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1093\/ije\/dyt127"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_32_1","volume-title":"Grad-cam: Visual explanations from deep networks via gradient-based localization. In ICCV.","author":"Selvaraju Ramprasaath R","year":"2017"},{"key":"e_1_3_2_1_33_1","volume-title":"Deep Learning for Weakly-Supervised Object Detection and Object Localization: A Survey. arXiv preprint arXiv:2105.12694","author":"Shao Feifei","year":"2021"},{"key":"e_1_3_2_1_34_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. In arXiv.  Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. In arXiv."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1177\/0049124196024003004"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Christian Szegedy Wei Liu Yangqing Jia Pierre Sermanet Scott Reed Dragomir Anguelov Dumitru Erhan Vincent Vanhoucke and Andrew Rabinovich. 2015. Going deeper with convolutions. In CVPR.  Christian Szegedy Wei Liu Yangqing Jia Pierre Sermanet Scott Reed Dragomir Anguelov Dumitru Erhan Vincent Vanhoucke and Andrew Rabinovich. 2015. Going deeper with convolutions. In CVPR.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_37_1","volume-title":"2020 a. Long-tailed classification by keeping the good and removing the bad momentum causal effect. arXiv preprint arXiv:2009.12991","author":"Tang Kaihua","year":"2020"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298664"},{"key":"e_1_3_2_1_40_1","unstructured":"Catherine Wah Steve Branson Peter Welinder Pietro Perona and Serge Belongie. 2011. The caltech-ucsd birds-200--2011 dataset. (2011).  Catherine Wah Steve Branson Peter Welinder Pietro Perona and Serge Belongie. 2011. The caltech-ucsd birds-200--2011 dataset. (2011)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01077"},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV). 434--450","author":"Wei Yunchao","year":"2018"},{"key":"e_1_3_2_1_43_1","unstructured":"Peter Welinder Steve Branson Takeshi Mita Catherine Wah Florian Schroff Serge Belongie and Pietro Perona. 2010. Caltech-UCSD birds 200. (2010).  Peter Welinder Steve Branson Takeshi Mita Catherine Wah Florian Schroff Serge Belongie and Pietro Perona. 2010. Caltech-UCSD birds 200. (2010)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Haolan Xue Chang Liu Fang Wan Jianbin Jiao Xiangyang Ji and Qixiang Ye. 2019. DANet: Divergent Activation for Weakly Supervised Object Localization. In ICCV.  Haolan Xue Chang Liu Fang Wan Jianbin Jiao Xiangyang Ji and Qixiang Ye. 2019. DANet: Divergent Activation for Weakly Supervised Object Localization. In ICCV.","DOI":"10.1109\/ICCV.2019.00669"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Seunghan Yang Yoonhyung Kim Youngeun Kim and Changick Kim. 2020 a. Combinational Class Activation Maps for Weakly Supervised Object Localization. In WACV.  Seunghan Yang Yoonhyung Kim Youngeun Kim and Changick Kim. 2020 a. Combinational Class Activation Maps for Weakly Supervised Object Localization. In WACV.","DOI":"10.1109\/WACV45572.2020.9093566"},{"key":"e_1_3_2_1_47_1","volume-title":"2020 b. Deconfounded image captioning: A causal retrospect. arXiv preprint arXiv:2003.03923","author":"Yang Xu","year":"2020"},{"key":"e_1_3_2_1_48_1","volume-title":"A survey on causal inference. arXiv preprint arXiv:2002.02770","author":"Yao Liuyi","year":"2020"},{"key":"e_1_3_2_1_49_1","volume-title":"Interventional few-shot learning. arXiv preprint arXiv:2009.13000","author":"Yue Zhongqi","year":"2020"},{"key":"e_1_3_2_1_50_1","volume-title":"Causal intervention for weakly-supervised semantic segmentation. arXiv preprint arXiv:2009.12547","author":"Zhang Dong","year":"2020"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00144"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Bolei Zhou Aditya Khosla Agata Lapedriza Aude Oliva and Antonio Torralba. 2016. Learning deep features for discriminative localization. In CVPR.  Bolei Zhou Aditya Khosla Agata Lapedriza Aude Oliva and Antonio Torralba. 2016. Learning deep features for discriminative localization. In CVPR.","DOI":"10.1109\/CVPR.2016.319"}],"event":{"name":"MM '21: ACM Multimedia Conference","location":"Virtual Event China","acronym":"MM '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475485","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475485","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:34Z","timestamp":1750193314000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475485"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":52,"alternative-id":["10.1145\/3474085.3475485","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475485","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}