{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T00:07:58Z","timestamp":1768435678077,"version":"3.49.0"},"reference-count":34,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2022,2,16]],"date-time":"2022-02-16T00:00:00Z","timestamp":1644969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key Research and Development Project","award":["2019YFE0109600"],"award-info":[{"award-number":["2019YFE0109600"]}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["61922027, 61971165, and 61932022"],"award-info":[{"award-number":["61922027, 61971165, and 61932022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2022,5,31]]},"abstract":"<jats:p>\n            Person re-identification (ReID) aims at searching the same identity person among images captured by various cameras. Existing fully supervised person ReID methods usually suffer from poor generalization capability caused by domain gaps. Unsupervised person ReID has attracted a lot of attention recently, because it works without intensive manual annotation and thus shows great potential in adapting to new conditions. Representation learning plays a critical role in unsupervised person ReID. In this work, we propose a novel selective contrastive learning framework for fully unsupervised feature learning. Specifically, different from traditional contrastive learning strategies, we propose to use multiple positives and adaptively selected negatives for defining the contrastive loss, enabling to learn a feature embedding model with stronger identity discriminative representation. Moreover, we propose to jointly leverage global and local features to construct three dynamic memory banks, among which the global and local ones are used for pairwise similarity computation and the mixture memory bank are used for contrastive loss definition. Experimental results demonstrate the superiority of our method in unsupervised person ReID compared with the state of the art. Our code is available at\n            <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/pangbo1997\/Unsup_ReID.git\">https:\/\/github.com\/pangbo1997\/Unsup_ReID.git<\/jats:ext-link>\n            .\n          <\/jats:p>","DOI":"10.1145\/3485061","type":"journal-article","created":{"date-parts":[[2022,2,16]],"date-time":"2022-02-16T17:56:32Z","timestamp":1645034192000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["Fully Unsupervised Person Re-Identification via Selective Contrastive Learning"],"prefix":"10.1145","volume":"18","author":[{"given":"Bo","family":"Pang","sequence":"first","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deming","family":"Zhai","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjun","family":"Jiang","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianming","family":"Liu","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,2,16]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054775"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00242"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00110"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00737"},{"key":"e_1_3_1_6_2","volume-title":"Advances in Neural Information Processing Systems","author":"Ge Yixiao","year":"2020","unstructured":"Yixiao Ge, Feng Zhu, Dapeng Chen, Rui Zhao, and Hongsheng Li. 2020. Self-paced contrastive learning with hybrid memory for domain adaptive object re-ID. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018738"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60636-7_27"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00345"},{"key":"e_1_3_1_10_2","article-title":"A simple framework for contrastive learning of visual representations","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. arXiv preprint arXiv:2002.05709.","journal-title":"arXiv preprint arXiv:2002.05709"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_30"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.349"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00321"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6921"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_11"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00543"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2891895"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_11"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298832"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.5555\/2919332.2919877"},{"key":"e_1_3_1_23_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Gidaris Spyros","year":"2018","unstructured":"Spyros Gidaris, Praveer Singh, and Nikos Komodakis. 2018. Unsupervised representation learning by predicting image rotations. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.5555\/2919332.2919877"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00016"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00543"},{"key":"e_1_3_1_29_2","doi-asserted-by":"crossref","first-page":"868","DOI":"10.1007\/978-3-319-46466-4_52","volume-title":"Computer Vision\u2014ECCV 2016","author":"Zheng Liang","year":"2016","unstructured":"Liang Zheng, Zhi Bie, Yifan Sun, Jingdong Wang, Chi Su, Shengjin Wang, and Qi Tian. 2016. MARS: A video benchmark for large-scale person re-identification. In Computer Vision\u2014ECCV 2016, Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling (Eds.). Springer International, Cham, Switzerland, 868\u2013884."},{"key":"e_1_3_1_30_2","first-page":"264","volume-title":"Proceedings of the British Machine Vision Conference (BMVC\u201919)","author":"Ding Guodong","year":"2019","unstructured":"Guodong Ding, Salman H. Khan, and Zhenmin Tang. 2019. Dispersion based clustering for unsupervised person re-identification. In Proceedings of the British Machine Vision Conference (BMVC\u201919). 264."},{"key":"e_1_3_1_31_2","volume-title":"Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR\u201920)","author":"Zhong Zhun","year":"2020","unstructured":"Zhun Zhong, Liang Zheng, Zhiming Luo, Shaozi Li, and Yi Yang. 2020. Invariance matters: Exemplar memory for domain adaptive person re-identification. In Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR\u201920)."},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00621"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01099"},{"key":"e_1_3_1_34_2","article-title":"Deep association learning for unsupervised video person re-identification","author":"Chen Yanbei","year":"2018","unstructured":"Yanbei Chen, Xiatian Zhu, and Shaogang Gong. 2018. Deep association learning for unsupervised video person re-identification. arXiv preprint arXiv:1808.07301.","journal-title":"arXiv preprint arXiv:1808.07301"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00543"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3485061","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3485061","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:17:15Z","timestamp":1750191435000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3485061"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,16]]},"references-count":34,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,5,31]]}},"alternative-id":["10.1145\/3485061"],"URL":"https:\/\/doi.org\/10.1145\/3485061","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,16]]},"assertion":[{"value":"2021-07-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-02-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}