{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T23:57:46Z","timestamp":1768262266482,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":47,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612133","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"2744-2755","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Co-Salient Object Detection with Semantic-Level Consensus Extraction and Dispersion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6902-5089","authenticated-orcid":false,"given":"Peiran","family":"Xu","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7815-3750","authenticated-orcid":false,"given":"Yadong","family":"Mu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, 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","volume-title":"BEiT: BERT Pre-Training of Image Transformers. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=p-BhZSz59o4","author":"Bao Hangbo","year":"2022","unstructured":"Hangbo Bao, Li Dong, Songhao Piao, and Furu Wei. 2022. BEiT: BERT Pre-Training of Image Transformers. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=p-BhZSz59o4"},{"key":"e_1_3_2_1_3_1","volume-title":"Vision Transformer Adapter for Dense Predictions. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=plKu2GByCNW","author":"Chen Zhe","year":"2023","unstructured":"Zhe Chen, Yuchen Duan, Wenhai Wang, Junjun He, Tong Lu, Jifeng Dai, and Yu Qiao. 2023. Vision Transformer Adapter for Dense Predictions. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=plKu2GByCNW"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.193"},{"key":"e_1_3_2_1_5_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=YicbFdNTTy","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 International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.487"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/97"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3060412"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01211"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_3_2_1_12_1","volume-title":"TCNet: Co-Salient Object Detection via Parallel Interaction of Transformers and CNNs","author":"Ge Yanliang","year":"2022","unstructured":"Yanliang Ge, Qiao Zhang, Tian-Zhu Xiang, Cong Zhang, and Hongbo Bi. 2022. TCNet: Co-Salient Object Detection via Parallel Interaction of Transformers and CNNs. IEEE Transactions on Circuits and Systems for Video Technology (2022)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_14_1","first-page":"18749","article-title":"Icnet: Intra-saliency correlation network for co-saliency detection","volume":"33","author":"Jin Wen-Da","year":"2020","unstructured":"Wen-Da Jin, Jun Xu, Ming-Ming Cheng, Yi Zhang, and Wei Guo. 2020. Icnet: Intra-saliency correlation network for co-saliency detection. Advances in Neural Information Processing Systems, Vol. 33 (2020), 18749--18759.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.743"},{"key":"e_1_3_2_1_16_1","first-page":"6","article-title":"Detecting Robust Co-Saliency with Recurrent Co-Attention Neural Network","volume":"2","author":"Li Bo","year":"2019","unstructured":"Bo Li, Zhengxing Sun, Lv Tang, Yunhan Sun, and Jinlong Shi. 2019. Detecting Robust Co-Saliency with Recurrent Co-Attention Neural Network.. In IJCAI, Vol. 2. 6.","journal-title":"IJCAI"},{"key":"e_1_3_2_1_17_1","volume-title":"Rao Muhammad Anwer, and Fahad Shahbaz Khan","author":"Li Long","year":"2023","unstructured":"Long Li, Junwei Han, Ni Zhang, Nian Liu, Salman Khan, Hisham Cholakkal, Rao Muhammad Anwer, and Fahad Shahbaz Khan. 2023. Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection. arxiv: 2305.00514 [cs.CV]"},{"key":"e_1_3_2_1_18_1","volume-title":"Tel Aviv","author":"Li Yanghao","year":"2022","unstructured":"Yanghao Li, Hanzi Mao, Ross Girshick, and Kaiming He. 2022a. Exploring plain vision transformer backbones for object detection. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part IX. Springer, 280--296."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00468"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475601"},{"key":"e_1_3_2_1_24_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_25_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925903"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3264883"},{"key":"e_1_3_2_1_28_1","volume-title":"CoSformer: Detecting co-salient object with transformers. arXiv preprint arXiv:2104.14729","author":"Tang Lv","year":"2021","unstructured":"Lv Tang and Bo Li. 2021. CoSformer: Detecting co-salient object with transformers. arXiv preprint arXiv:2104.14729 (2021)."},{"key":"e_1_3_2_1_29_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, ?ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018917"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/424"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00105"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298918"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0907-4"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01349"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00321"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00907"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3185550"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00413"},{"key":"e_1_3_2_1_43_1","volume-title":"CoADNet: Collaborative aggregation-and-distribution networks for co-salient object detection. Advances in neural information processing systems","author":"Zhang Qijian","year":"2020","unstructured":"Qijian Zhang, Runmin Cong, Junhui Hou, Chongyi Li, and Yao Zhao. 2020a. CoADNet: Collaborative aggregation-and-distribution networks for co-salient object detection. Advances in neural information processing systems, Vol. 33 (2020), 6959--6970."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_27"},{"key":"e_1_3_2_1_45_1","volume-title":"GCoNet: A Stronger Group Collaborative Co-Salient Object Detector. arXiv preprint arXiv:2205.15469","author":"Zheng Peng","year":"2022","unstructured":"Peng Zheng, Huazhu Fu, Deng-Ping Fan, Qi Fan, Jie Qin, and Luc Van Gool. 2022. GCoNet: A Stronger Group Collaborative Co-Salient Object Detector. arXiv preprint arXiv:2205.15469 (2022)."},{"key":"e_1_3_2_1_46_1","volume-title":"Memory-aided Contrastive Consensus Learning for Co-salient Object Detection. arXiv preprint arXiv:2302.14485","author":"Zheng Peng","year":"2023","unstructured":"Peng Zheng, Jie Qin, Shuo Wang, Tian-Zhu Xiang, and Huan Xiong. 2023. Memory-aided Contrastive Consensus Learning for Co-salient Object Detection. arXiv preprint arXiv:2302.14485 (2023)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234586"}],"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\/3581783.3612133","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612133","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:54:44Z","timestamp":1755820484000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612133"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":47,"alternative-id":["10.1145\/3581783.3612133","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612133","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"}}]}}