{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:16:29Z","timestamp":1783527389812,"version":"3.55.0"},"reference-count":83,"publisher":"Association for Computing Machinery (ACM)","issue":"2s","license":[{"start":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T00:00:00Z","timestamp":1656547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["U1803262, 62171325, 62176191"],"award-info":[{"award-number":["U1803262, 62171325, 62176191"]}],"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":[[2022,6,30]]},"abstract":"<jats:p>Person re-identification (re-ID) is commonly investigated as a ranking problem. However, the performance of existing re-ID models drops dramatically, when they encounter extreme positive-negative class imbalance (e.g., very small ratio of positive and negative samples) during training. To alleviate this problem, this article designs a rank-in-rank loss to optimize the distribution of feature embeddings. Specifically, we propose a Differentiable Retrieval-Sort Loss (DRSL) to optimize the re-ID model by ranking each positive sample ahead of the negative samples according to the distance and sorting the positive samples according to the angle (e.g., similarity score). The key idea of the proposed DRSL lies in minimizing the distance between samples of the same category along with the angle between them. Considering that the ranking and sorting operations are non-differentiable and non-convex, the DRSL also performs the optimization of automatic derivation and backpropagation. In addition, the analysis of the proposed DRSL is provided to illustrate that the DRSL not only maintains the inter-class distance distribution but also preserves the intra-class similarity structure in terms of angle constraints. Extensive experimental results indicate that the proposed DRSL can improve the performance of the state-of-the-art re-ID models, thus demonstrating its effectiveness and superiority in the re-ID task.<\/jats:p>","DOI":"10.1145\/3532866","type":"journal-article","created":{"date-parts":[[2022,4,30]],"date-time":"2022-04-30T11:11:52Z","timestamp":1651317112000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":25,"title":["Rank-in-Rank Loss for Person Re-identification"],"prefix":"10.1145","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0748-3669","authenticated-orcid":false,"given":"Xin","family":"Xu","sequence":"first","affiliation":[{"name":"Wuhan University of Science and Technology, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3140-3243","authenticated-orcid":false,"given":"Xin","family":"Yuan","sequence":"additional","affiliation":[{"name":"Wuhan University of Science and Technology, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3846-9157","authenticated-orcid":false,"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Wuhan University, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0318-3255","authenticated-orcid":false,"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Wuhan University of Science and Technology, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5872-3872","authenticated-orcid":false,"given":"Ruimin","family":"Hu","sequence":"additional","affiliation":[{"name":"Wuhan University, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,10,6]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR.2015.7299016"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1016\/j.patcog.2019.107036"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1145\/3345001"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1007\/978-3-030-58545-7_39"},{"key":"e_1_3_1_6_2","first-page":"193","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Burges Christopher","year":"2006","unstructured":"Christopher Burges, Robert Ragno, and Quoc Le. 2006. Learning to rank with nonsmooth cost functions. In Proceedings of the Advances in Neural Information Processing Systems. 193\u2013200."},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR.2019.00196"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR.2018.00225"},{"key":"e_1_3_1_9_2","volume-title":"Proceedings of the NIPS Workshop: Machine Learning for Web Search","author":"Chapelle Olivier","year":"2007","unstructured":"Olivier Chapelle, Quoc Le, and Alex Smola. 2007. Large margin optimization of ranking measures. In Proceedings of the NIPS Workshop: Machine Learning for Web Search."},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/TIP.2021.3107211"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1007\/978-3-030-58598-3_38"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigMM.2018.8499067"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR.2019.00526"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/TPAMI.2020.2991457"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR.2017.145"},{"key":"e_1_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Yinpeng Chen Xiyang Dai Dongdong Chen Mengchen Liu Xiaoyi Dong Lu Yuan and Zicheng Liu. 2021. Mobile-former: Bridging mobilenet and transformer. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . 5270\u20135279.","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR.2018.00110"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1609\/aaai.v33i01.33018295"},{"key":"e_1_3_1_20_2","first-page":"1","volume-title":"Proceedings of the IEEE International Workshop on Performance Evaluation for Tracking and Surveillance","author":"Gray Douglas","year":"2007","unstructured":"Douglas Gray, Shane Brennan, and Hai Tao. 2007. Evaluating appearance models for recognition, reacquisition, and tracking. In Proceedings of the IEEE International Workshop on Performance Evaluation for Tracking and Surveillance. Citeseer, 1\u20137."},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/ICCV.2019.00374"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR.2018.00248"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR.2018.00423"},{"key":"e_1_3_1_24_2","unstructured":"Alexander Hermans Lucas Beyer and Bastian Leibe. 2017. In defense of the triplet loss for person re-identification. arXiv:1703.07737. Retrieved from https:\/\/arxiv.org\/abs\/1703.07737."},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR46437.2021.00666"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/ICASSP.2014.6854454"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR.2014.27"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR.2018.00243"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1007\/s11263-019-01274-1"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1016\/j.patcog.2019.06.006"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1145\/3522714"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR.2017.713"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/TMM.2019.2958756"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/ICCV.2017.47"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR.2016.434"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1007\/978-3-030-01234-2_31"},{"key":"e_1_3_1_37_2","first-page":"15534","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Oksuz Kemal","year":"2020","unstructured":"Kemal Oksuz, Baris Can Cam, Emre Akbas, and Sinan Kalkan. 2020. A ranking-based, balanced loss function unifying classification and localisation in object detection. In Proceedings of the Advances in Neural Information Processing Systems. 15534\u201315545."},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/ICCV48922.2021.00300"},{"key":"e_1_3_1_39_2","first-page":"8024","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. Pytorch: An imperative style, high-performance deep learning library. In Proceedings of the Advances in Neural Information Processing Systems. 8024\u20138035."},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1007\/s10791-009-9124-x"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/ICCV.2019.00385"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/TCNS.2021.3059794"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/ICCV.2019.00521"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR.2018.00632"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR42600.2020.00764"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR.2018.00051"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_1_48_2","first-page":"1857","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Sohn Kihyuk","year":"2016","unstructured":"Kihyuk Sohn. 2016. Improved deep metric learning with multi-class n-pair loss objective. In Proceedings of the Advances in Neural Information Processing Systems. 1857\u20131865. Retrieved from https:\/\/proceedings.neurips.cc\/paper\/2016\/hash\/6b180037abbebea991d8b1232f8a8ca9-Abstract.html."},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1007\/978-3-030-01264-9_25"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1007\/978-3-030-01225-0_30"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/TCSVT.2021.3061412"},{"key":"e_1_3_1_52_2","first-page":"4170","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"29","author":"Ustinova Evgeniya","year":"2016","unstructured":"Evgeniya Ustinova and Victor S. Lempitsky. 2016. Learning deep embeddings with histogram loss. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 29. 4170\u20134178. http:\/\/papers.nips.cc\/paper\/6464-learning-deep-embeddings-with-histogram-loss."},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR.2016.144"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1145\/3240508.3240552"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/TMM.2012.2187181"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/TIP.2012.2207397"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR.2019.00535"},{"key":"e_1_3_1_58_2","unstructured":"Zheng Wang Xin Yuan Toshihiko Yamasaki Yutian Lin Xin Xu and Wenjun Zeng. 2020. Re-identification= retrieval+ verification: Back to essence and forward with a new metric. arXiv:2011.11506. Retrieved from https:\/\/arxiv.org\/abs\/2011.11506."},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR.2018.00016"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1007\/978-3-319-46478-7_31"},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/TCSVT.2019.2909549"},{"key":"e_1_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/TNNLS.2020.2979190"},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/TIP.2019.2940684"},{"key":"e_1_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/ICME51207.2021.9428200"},{"key":"e_1_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1016\/j.patcog.2021.107827"},{"key":"e_1_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1016\/j.patcog.2018.08.015"},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1609\/aaai.v34i01.5362"},{"key":"e_1_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1145\/3089249"},{"key":"e_1_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/TIP.2017.2765836"},{"key":"e_1_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1016\/j.neucom.2021.04.070"},{"key":"e_1_3_1_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/TPAMI.2021.3054775"},{"key":"e_1_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/TSP.2020.2976587"},{"key":"e_1_3_1_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1007\/978-3-030-01270-0_12"},{"key":"e_1_3_1_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPRW50498.2020.00185"},{"key":"e_1_3_1_75_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPRW.2019.00194"},{"key":"e_1_3_1_76_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR.2019.00076"},{"key":"e_1_3_1_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/TMM.2020.2972125"},{"key":"e_1_3_1_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR.2017.103"},{"key":"e_1_3_1_79_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/ICCV.2015.133"},{"key":"e_1_3_1_80_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.357"},{"key":"e_1_3_1_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1145\/3159171"},{"key":"e_1_3_1_82_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/ICCV.2017.405"},{"key":"e_1_3_1_83_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/CVPR.2017.389"},{"key":"e_1_3_1_84_2","doi-asserted-by":"publisher","DOI":"10.1145\/10.1109\/TPAMI.2021.3069237"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3532866","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3532866","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:37Z","timestamp":1750186837000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3532866"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,30]]},"references-count":83,"journal-issue":{"issue":"2s","published-print":{"date-parts":[[2022,6,30]]}},"alternative-id":["10.1145\/3532866"],"URL":"https:\/\/doi.org\/10.1145\/3532866","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,30]]},"assertion":[{"value":"2021-10-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-04-19","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-10-06","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}