{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T19:54:27Z","timestamp":1790711667488,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":45,"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":"NSFC","award":["No.U20A20387"],"award-info":[{"award-number":["No.U20A20387"]}]},{"name":"Key R&D Program of Zhejiang Province","award":["No.2021C01121, 2023C01043"],"award-info":[{"award-number":["No.2021C01121, 2023C01043"]}]},{"name":"National Key R&D Program of China","award":["No.2023YFE0204200"],"award-info":[{"award-number":["No.2023YFE0204200"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612547","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"125-134","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Multi-Scale Similarity Aggregation for Dynamic Metric Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2026-9771","authenticated-orcid":false,"given":"Dingyi","family":"Zhang","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6859-9038","authenticated-orcid":false,"given":"Yingming","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5098-2506","authenticated-orcid":false,"given":"Zhongfei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Binghamton University, Binghamton, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Bachman Philip","year":"2019","unstructured":"Philip Bachman, R Devon Hjelm, and William Buchwalter. 2019. Learning representations by maximizing mutual information across views. In Advances in Neural Information Processing Systems, Vol. 32."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)","author":"Bi Wei","year":"2011","unstructured":"Wei Bi and James T Kwok. 2011. Multi-label classification on tree-and dag-structured hierarchies. In Proceedings of the 28th International Conference on Machine Learning (ICML-11). 17--24."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00196"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"e_1_3_2_1_5_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_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.145"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"e_1_3_2_1_9_1","volume-title":"Martin Riedmiller, and Thomas Brox.","author":"Dosovitskiy Alexey","year":"2014","unstructured":"Alexey Dosovitskiy, Jost Tobias Springenberg, Martin Riedmiller, and Thomas Brox. 2014. Discriminative unsupervised feature learning with convolutional neural networks. In Advances in Neural Information Processing Systems, Vol. 27."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_17"},{"key":"e_1_3_2_1_11_1","unstructured":"Jean-Bastien Grill Florian Strub Florent Altch\u00e9 Corentin Tallec Pierre Richemond Elena Buchatskaya Carl Doersch Bernardo Pires Zhaohan Guo Mohammad Azar et al. 2020. Bootstrap Your Own Latent: A new approach to self-supervised learning. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.307"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24261-3_7"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00330"},{"key":"e_1_3_2_1_17_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00131"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.47"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.434"},{"key":"e_1_3_2_1_22_1","unstructured":"Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury Gregory Chanan Trevor Killeen Zeming Lin Natalia Gimelshein Luca Antiga et al. 2019. PyTorch: An imperative style high-performance deep learning library. In Advances in Neural Information Processing Systems. 8024--8035."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00655"},{"key":"e_1_3_2_1_24_1","volume-title":"Tel Aviv","author":"Ramzi Elias","year":"2022","unstructured":"Elias Ramzi, Nicolas Audebert, Nicolas Thome, Cl\u00e9ment Rambour, and Xavier Bitot. 2022. Hierarchical Average Precision Training for Pertinent Image Retrieval. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XIV. Springer, 250--266."},{"key":"e_1_3_2_1_25_1","volume-title":"L2-constrained softmax loss for discriminative face verification. arXiv preprint arXiv:1703.09507","author":"Ranjan Rajeev","year":"2017","unstructured":"Rajeev Ranjan, Carlos D Castillo, and Rama Chellappa. 2017. L2-constrained softmax loss for discriminative face verification. arXiv preprint arXiv:1703.09507 (2017)."},{"key":"e_1_3_2_1_26_1","volume-title":"International Conference on Machine Learning. PMLR, 8242--8252","author":"Roth Karsten","year":"2020","unstructured":"Karsten Roth, Timo Milbich, Samarth Sinha, Prateek Gupta, Bjorn Ommer, and Joseph Paul Cohen. 2020. Revisiting training strategies and generalization performance in deep metric learning. In International Conference on Machine Learning. PMLR, 8242--8252."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_1_28_1","unstructured":"Kihyuk Sohn. 2016. Improved deep metric learning with multi-class n-pair loss objective. In Advances in neural information processing systems. 1857--1865."},{"key":"e_1_3_2_1_29_1","unstructured":"Yi Sun Yuheng Chen Xiaogang Wang and Xiaoou Tang. 2014. Deep learning face representation by joint identification-verification. In Advances in neural information processing systems. 1988--1996."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00643"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00535"},{"key":"e_1_3_2_1_32_1","volume-title":"Proxynca: Revisiting and revitalizing proxy neighborhood component analysis. In Computer Vision-ECCV 2020: 16th European Conference","author":"Teh Eu Wern","year":"2020","unstructured":"Eu Wern Teh, Terrance DeVries, and Graham W Taylor. 2020. Proxynca: Revisiting and revitalizing proxy neighborhood component analysis. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXIV 16. Springer, 448--464."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123359"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00516"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00535"},{"key":"e_1_3_2_1_37_1","volume-title":"International conference on machine learning. PMLR, 5075--5084","author":"Wehrmann Jonatas","year":"2018","unstructured":"Jonatas Wehrmann, Ricardo Cerri, and Rodrigo Barros. 2018. Hierarchical multi-label classification networks. In International conference on machine learning. PMLR, 5075--5084."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.309"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"e_1_3_2_1_40_1","volume-title":"Li","author":"Yi Dong","year":"2014","unstructured":"Dong Yi, Zhen Lei, and Stan Z. Li. 2014. Deep metric learning for practical person re-identification. arXiv preprint arXiv:1407.4979 (2014)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/222"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.94"},{"key":"e_1_3_2_1_43_1","volume-title":"Classification is a strong baseline for deep metric learning. arXiv preprint arXiv:1811.12649","author":"Zhai Andrew","year":"2018","unstructured":"Andrew Zhai and Hao-Yu Wu. 2018. Classification is a strong baseline for deep metric learning. arXiv preprint arXiv:1811.12649 (2018)."},{"key":"e_1_3_2_1_44_1","volume-title":"Tel Aviv","author":"Zheng Wenzhao","year":"2022","unstructured":"Wenzhao Zheng, Yuanhui Huang, Borui Zhang, Jie Zhou, and Jiwen Lu. 2022. Dynamic Metric Learning with Cross-Level Concept Distillation. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXIV. Springer, 197--213."},{"key":"e_1_3_2_1_45_1","unstructured":"Yuehua Zhu Muli Yang Cheng Deng and Wei Liu. 2020. Fewer is more: A deep graph metric learning perspective using fewer proxies. In Advances in Neural Information Processing Systems. 17792--17803."}],"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\/3581783.3612547","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612547","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:58:06Z","timestamp":1755820686000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612547"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":45,"alternative-id":["10.1145\/3581783.3612547","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612547","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"}}]}}