{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T16:59:29Z","timestamp":1770742769512,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Youth Innovation Promotion Association Chinese Academy of Sciences","award":["Y2021122"],"award-info":[{"award-number":["Y2021122"]}]},{"name":"National Nature Science Foundation of China","award":["62121002"],"award-info":[{"award-number":["62121002"]}]},{"name":"Fundamental Research Funds for the Central Universities under Grant","award":["WK3480000011"],"award-info":[{"award-number":["WK3480000011"]}]},{"name":"National Nature Science Foundation of China","award":["62022076"],"award-info":[{"award-number":["62022076"]}]},{"name":"National Nature Science Foundation of China","award":["U1936210"],"award-info":[{"award-number":["U1936210"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3548201","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:42:35Z","timestamp":1665416555000},"page":"5783-5792","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Boat in the Sky: Background Decoupling and Object-aware Pooling for Weakly Supervised Semantic Segmentation"],"prefix":"10.1145","author":[{"given":"Jianjun","family":"Xu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"given":"Hongtao","family":"Xie","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"given":"Hai","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"given":"Yuxin","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"given":"Sun-ao","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00231"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00523"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2463223"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_21"},{"key":"e_1_3_2_2_5_1","volume-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","author":"Chen Liang-Chieh","year":"2017","unstructured":"Liang-Chieh Chen , George Papandreou , Iasonas Kokkinos , Kevin Murphy , and Alan L Yuille . 2017 . Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs . IEEE transactions on pattern analysis and machine intelligence 40, 4 (2017), 834--848. Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L Yuille. 2017. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence 40, 4 (2017), 834--848."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_3_2_2_7_1","volume-title":"Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation. arXiv preprint arXiv:2203.00962","author":"Chen Zhaozheng","year":"2022","unstructured":"Zhaozheng Chen , Tan Wang , Xiongwei Wu , Xian-Sheng Hua , Hanwang Zhang , and Qianru Sun . 2022. Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation. arXiv preprint arXiv:2203.00962 ( 2022 ). Zhaozheng Chen, Tan Wang, Xiongwei Wu, Xian-Sheng Hua, Hanwang Zhang, and Qianru Sun. 2022. Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation. arXiv preprint arXiv:2203.00962 (2022)."},{"key":"e_1_3_2_2_8_1","volume-title":"Attention-based dropout layer for weakly supervised single object localization and semantic segmentation","author":"Choe Junsuk","year":"2020","unstructured":"Junsuk Choe , Seungho Lee , and Hyunjung Shim . 2020. Attention-based dropout layer for weakly supervised single object localization and semantic segmentation . IEEE Transactions on Pattern Analysis and Machine Intelligence ( 2020 ). Junsuk Choe, Seungho Lee, and Hyunjung Shim. 2020. Attention-based dropout layer for weakly supervised single object localization and semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2020)."},{"key":"e_1_3_2_2_9_1","volume-title":"Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552","author":"DeVries Terrance","year":"2017","unstructured":"Terrance DeVries and Graham W Taylor . 2017. Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 ( 2017 ). Terrance DeVries and Graham W Taylor. 2017. Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 (2017)."},{"key":"e_1_3_2_2_10_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. International journal of computer vision 111, 1 (2015), 98--136. 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. International journal of computer vision 111, 1 (2015), 98--136."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00434"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6705"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.239"},{"key":"e_1_3_2_2_16_1","volume-title":"Self-erasing network for integral object attention. Advances in Neural Information Processing Systems 31","author":"Hou Qibin","year":"2018","unstructured":"Qibin Hou , PengTao Jiang , Yunchao Wei , and Ming-Ming Cheng . 2018. Self-erasing network for integral object attention. Advances in Neural Information Processing Systems 31 ( 2018 ). Qibin Hou, PengTao Jiang, Yunchao Wei, and Ming-Ming Cheng. 2018. Self-erasing network for integral object attention. Advances in Neural Information Processing Systems 31 (2018)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01098"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00733"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00216"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16269"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_42"},{"key":"e_1_3_2_2_22_1","volume-title":"Efficient inference in fully connected crfs with gaussian edge potentials. Advances in neural information processing systems 24","author":"Kr\u00e4henb\u00fchl Philipp","year":"2011","unstructured":"Philipp Kr\u00e4henb\u00fchl and Vladlen Koltun . 2011. Efficient inference in fully connected crfs with gaussian edge potentials. Advances in neural information processing systems 24 ( 2011 ). Philipp Kr\u00e4henb\u00fchl and Vladlen Koltun. 2011. Efficient inference in fully connected crfs with gaussian edge potentials. Advances in neural information processing systems 24 (2011)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.381"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11213"},{"key":"e_1_3_2_2_25_1","volume-title":"Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation. Advances in Neural Information Processing Systems 34","author":"Lee Jungbeom","year":"2021","unstructured":"Jungbeom Lee , Jooyoung Choi , Jisoo Mok , and Sungroh Yoon . 2021. Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation. Advances in Neural Information Processing Systems 34 ( 2021 ). Jungbeom Lee, Jooyoung Choi, Jisoo Mok, and Sungroh Yoon. 2021. Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation. Advances in Neural Information Processing Systems 34 (2021)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00541"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00691"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00545"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00960"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20025"},{"key":"e_1_3_2_2_31_1","volume-title":"Group-wise semantic mining for weakly supervised semantic segmentation. arXiv preprint arXiv:2012.05007","author":"Li Xueyi","year":"2020","unstructured":"Xueyi Li , Tianfei Zhou , Jianwu Li , Yi Zhou , and Zhaoxiang Zhang . 2020. Group-wise semantic mining for weakly supervised semantic segmentation. arXiv preprint arXiv:2012.05007 ( 2020 ). Xueyi Li, Tianfei Zhou, Jianwu Li, Yi Zhou, and Zhaoxiang Zhang. 2020. Group-wise semantic mining for weakly supervised semantic segmentation. arXiv preprint arXiv:2012.05007 (2020)."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00688"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_2_34_1","volume-title":"Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction","author":"Liu Zhenguang","year":"2021","unstructured":"Zhenguang Liu , Shuang Wu , Shuyuan Jin , Shouling Ji , Qi Liu , Shijian Lu , and Li Cheng . 2021. Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction . IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) ( 2021 ), 1--16. https:\/\/doi.org\/10.1109\/TPAMI.2021.3139918 Zhenguang Liu, Shuang Wu, Shuyuan Jin, Shouling Ji, Qi Liu, Shijian Lu, and Li Cheng. 2021. Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) (2021), 1--16. https:\/\/doi.org\/10.1109\/TPAMI.2021.3139918"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Lixiang Ru Bo Du and Chen Wu. 2021. Learning visual words for weakly-supervised semantic segmentation.  Lixiang Ru Bo Du and Chen Wu. 2021. Learning visual words for weakly-supervised semantic segmentation.","DOI":"10.1109\/ICCV48922.2021.00688"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00841"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00692"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_21"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00195"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01177"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01229"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.687"},{"key":"e_1_3_2_2_44_1","volume-title":"Stc: A simple to complex framework for weakly-supervised semantic segmentation","author":"Wei Yunchao","year":"2016","unstructured":"Yunchao Wei , Xiaodan Liang , Yunpeng Chen , Xiaohui Shen , Ming-Ming Cheng , Jiashi Feng , Yao Zhao , and Shuicheng Yan . 2016 . Stc: A simple to complex framework for weakly-supervised semantic segmentation . IEEE transactions on pattern analysis and machine intelligence 39, 11 (2016), 2314--2320. Yunchao Wei, Xiaodan Liang, Yunpeng Chen, Xiaohui Shen, Ming-Ming Cheng, Jiashi Feng, Yao Zhao, and Shuicheng Yan. 2016. Stc: A simple to complex framework for weakly-supervised semantic segmentation. IEEE transactions on pattern analysis and machine intelligence 39, 11 (2016), 2314--2320."},{"key":"e_1_3_2_2_45_1","volume-title":"International Conference on Learning Representations.","author":"Xiao Kai Yuanqing","year":"2020","unstructured":"Kai Yuanqing Xiao , Logan Engstrom , Andrew Ilyas , and Aleksander Madry . 2020 . Noise or Signal: The Role of Image Backgrounds in Object Recognition . In International Conference on Learning Representations. Kai Yuanqing Xiao, Logan Engstrom, Andrew Ilyas, and Aleksander Madry. 2020. Noise or Signal: The Role of Image Backgrounds in Object Recognition. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00690"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00265"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"e_1_3_2_2_49_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 7223--7233","author":"Zeng Yu","year":"2019","unstructured":"Yu Zeng , Yunzhi Zhuge , Huchuan Lu , and Lihe Zhang . 2019 . Joint learning of saliency detection and weakly supervised semantic segmentation . In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 7223--7233 . Yu Zeng, Yunzhi Zhuge, Huchuan Lu, and Lihe Zhang. 2019. Joint learning of saliency detection and weakly supervised semantic segmentation. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 7223--7233."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3083269"},{"key":"e_1_3_2_2_51_1","volume-title":"Causal intervention for weakly-supervised semantic segmentation. arXiv preprint arXiv:2009.12547","author":"Zhang Dong","year":"2020","unstructured":"Dong Zhang , Hanwang Zhang , Jinhui Tang , Xiansheng Hua , and Qianru Sun . 2020. Causal intervention for weakly-supervised semantic segmentation. arXiv preprint arXiv:2009.12547 ( 2020 ). Dong Zhang, Hanwang Zhang, Jinhui Tang, Xiansheng Hua, and Qianru Sun. 2020. Causal intervention for weakly-supervised semantic segmentation. arXiv preprint arXiv:2009.12547 (2020)."},{"key":"e_1_3_2_2_52_1","volume-title":"mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412","author":"Zhang Hongyi","year":"2017","unstructured":"Hongyi Zhang , Moustapha Cisse , Yann N Dauphin , and David Lopez-Paz . 2017. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 ( 2017 ). Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. 2017. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17312"},{"key":"e_1_3_2_2_54_1","first-page":"7559","article-title":"Differentiable augmentation for data-efficient gan training","volume":"33","author":"Zhao Shengyu","year":"2020","unstructured":"Shengyu Zhao , Zhijian Liu , Ji Lin , Jun-Yan Zhu , and Song Han . 2020 . Differentiable augmentation for data-efficient gan training . Advances in Neural Information Processing Systems 33 (2020), 7559 -- 7570 . Shengyu Zhao, Zhijian Liu, Ji Lin, Jun-Yan Zhu, and Song Han. 2020. Differentiable augmentation for data-efficient gan training. Advances in Neural Information Processing Systems 33 (2020), 7559--7570.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548201","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3548201","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:20Z","timestamp":1750186820000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548201"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":55,"alternative-id":["10.1145\/3503161.3548201","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3548201","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}