{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:26:37Z","timestamp":1775665597245,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Scientific and Technological Innovation Action Plan of Shanghai Science and Technology Committee","award":["22511102202"],"award-info":[{"award-number":["22511102202"]}]},{"name":"National Natural Science Foundation of China","award":["62072112"],"award-info":[{"award-number":["62072112"]}]},{"name":"National Key R&D Program of China","award":["2020AAA0108301"],"award-info":[{"award-number":["2020AAA0108301"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612212","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"5532-5541","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Towards End-to-End Unsupervised Saliency Detection with Self-Supervised Top-Down Context"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7104-8630","authenticated-orcid":false,"given":"Yicheng","family":"Song","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8992-0756","authenticated-orcid":false,"given":"Shuyong","family":"Gao","sequence":"additional","affiliation":[{"name":"Fudan University & Keenon Robotics Co., Ltd., Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5798-5152","authenticated-orcid":false,"given":"Haozhe","family":"Xing","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8331-9740","authenticated-orcid":false,"given":"Yiting","family":"Cheng","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4953-2660","authenticated-orcid":false,"given":"Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3339-8751","authenticated-orcid":false,"given":"Wenqiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206596"},{"key":"e_1_3_2_1_2_1","unstructured":"Adam Bielski and Paolo Favaro. [n. d.]. MOVE: Unsupervised Movable Object Segmentation and Detection. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_3_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2015.2498644"},{"key":"e_1_3_2_1_6_1","volume-title":"Enhanced-alignment measure for binary foreground map evaluation. arXiv preprint arXiv:1805.10421","author":"Fan Deng-Ping","year":"2018","unstructured":"Deng-Ping Fan, Cheng Gong, Yang Cao, Bo Ren, Ming-Ming Cheng, and Ali Borji. 2018. Enhanced-alignment measure for binary foreground map evaluation. arXiv preprint arXiv:1805.10421 (2018)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.05.002"},{"key":"e_1_3_2_1_8_1","unstructured":"Shuyong Gao Wei Zhang Yan Wang Qianyu Guo Chenglong Zhang Yangji He and Wenqiang Zhang. 2022. Weakly-Supervised Salient Object Detection Using Point Supervision. In AAAI."},{"key":"e_1_3_2_1_9_1","first-page":"11309","article-title":"Self-paced contrastive learning with hybrid memory for domain adaptive object re-id","volume":"33","author":"Ge Yixiao","year":"2020","unstructured":"Yixiao Ge, Feng Zhu, Dapeng Chen, Rui Zhao, et al. 2020. Self-paced contrastive learning with hybrid memory for domain adaptive object re-id. Advances in Neural Information Processing Systems, Vol. 33 (2020), 11309--11321.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.209"},{"key":"e_1_3_2_1_14_1","volume-title":"Supervised contrastive learning. Advances in neural information processing systems","author":"Khosla Prannay","year":"2020","unstructured":"Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised contrastive learning. Advances in neural information processing systems, Vol. 33 (2020), 18661--18673."},{"key":"e_1_3_2_1_15_1","volume-title":"Efficient inference in fully connected crfs with gaussian edge potentials. in neural information processing systems","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. in neural information processing systems, Vol. 24 (2011)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.78"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 5455--5463","author":"Li Guanbin","year":"2015","unstructured":"Guanbin Li and Yizhou Yu. 2015. Visual saliency based on multiscale deep features. In Proceedings of the IEEE conference on computer vision and pattern recognition. 5455--5463."},{"key":"e_1_3_2_1_18_1","volume-title":"Prototypical Contrastive Learning of Unsupervised Representations. In International Conference on Learning Representations.","author":"Li Junnan","unstructured":"Junnan Li, Pan Zhou, Caiming Xiong, and Steven Hoi. [n.,d.]. Prototypical Contrastive Learning of Unsupervised Representations. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.370"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.43"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20052"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00404"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1109\/TPAMI.2010.70","article-title":"Learning to detect a salient object","volume":"33","author":"Liu Tie","year":"2010","unstructured":"Tie Liu, Zejian Yuan, Jian Sun, Jingdong Wang, Nanning Zheng, Xiaoou Tang, and Heung-Yeung Shum. 2010. Learning to detect a salient object. IEEE Transactions on Pattern analysis and machine intelligence, Vol. 33, 2 (2010), 353--367.","journal-title":"IEEE Transactions on Pattern analysis and machine intelligence"},{"key":"e_1_3_2_1_24_1","volume-title":"Nhung Ngo, Thi Hoai Phuong Nguyen, Zhongyu Lou, and Thomas Brox.","author":"Nguyen Tam","year":"2019","unstructured":"Tam Nguyen, Maximilian Dax, Chaithanya Kumar Mummadi, Nhung Ngo, Thi Hoai Phuong Nguyen, Zhongyu Lou, and Thomas Brox. 2019. Deepusps: Deep robust unsupervised saliency prediction via self-supervision. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_25_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00943"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2018.00289"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00410"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00766"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01634"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein et al. 2015. Imagenet large scale visual recognition challenge. International journal of computer vision Vol. 115 (2015) 211--252.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_1_33_1","volume-title":"Hierarchical image saliency detection on extended CSSD","author":"Shi Jianping","year":"2015","unstructured":"Jianping Shi, Qiong Yan, Li Xu, and Jiaya Jia. 2015. Hierarchical image saliency detection on extended CSSD. IEEE transactions on pattern analysis and machine intelligence, Vol. 38, 4 (2015), 717--729."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00442"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00195"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00579"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298938"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.404"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00721"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01143"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00403"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"e_1_3_2_1_43_1","volume-title":"International conference on machine learning. PMLR, 478--487","author":"Xie Junyuan","year":"2016","unstructured":"Junyuan Xie, Ross Girshick, and Ali Farhadi. 2016. Unsupervised deep embedding for clustering analysis. In International conference on machine learning. PMLR, 478--487."},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 989--998","author":"Xie Jinheng","year":"2022","unstructured":"Jinheng Xie, Jianfeng Xiang, Junliang Chen, Xianxu Hou, Xiaodong Zhao, and Linlin Shen. 2022. C2AM: Contrastive Learning of Class-Agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 989--998."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.153"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.407"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.556"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00637"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16434"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00623"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.436"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_21"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01256"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00941"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"e_1_3_2_1_56_1","volume-title":"Activation to Saliency: Forming High-Quality Labels for Unsupervised Salient Object Detection","author":"Zhou Huajun","year":"2022","unstructured":"Huajun Zhou, Peijia Chen, Lingxiao Yang, Xiaohua Xie, and Jianhuang Lai. 2022. Activation to Saliency: Forming High-Quality Labels for Unsupervised Salient Object Detection. IEEE Transactions on Circuits and Systems for Video Technology (2022)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00701"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00916"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.360"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612212","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612212","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:08:59Z","timestamp":1755821339000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612212"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":59,"alternative-id":["10.1145\/3581783.3612212","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612212","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}