{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:06:40Z","timestamp":1765310800308,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62425305, 62221002 and 62203168"],"award-info":[{"award-number":["62425305, 62221002 and 62203168"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Innovation Program of Hunan Province","award":["2024RC3151 and 2023RC1048"],"award-info":[{"award-number":["2024RC3151 and 2023RC1048"]}]},{"name":"the Natural Science Foundation of Hunan Province","award":["2024JJ3013"],"award-info":[{"award-number":["2024JJ3013"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755580","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:30:51Z","timestamp":1761377451000},"page":"6213-6222","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Decoupled Identity and Attribute Tokenization for Person Re-Identification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3325-5415","authenticated-orcid":false,"given":"Rui","family":"Shang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6406-4896","authenticated-orcid":false,"given":"Min","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4862-8975","authenticated-orcid":false,"given":"Xueping","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering at Hunan Normal University, Hunan Normal University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3995-4402","authenticated-orcid":false,"given":"Yuan","family":"Bian","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5365-6254","authenticated-orcid":false,"given":"Yaonan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01766"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612050"},{"key":"e_1_3_2_1_3_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01844"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00113"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613460"},{"key":"e_1_3_2_1_8_1","volume-title":"Transreid: Transformer-based object re-identification.","author":"He Shuting","year":"2021","unstructured":"Shuting He, Hao Luo, Pichao Wang, Fan Wang, Hao Li, and Wei Jiang. 2021. Transreid: Transformer-based object re-identification. (2021), 15013-15022."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00324"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00666"},{"key":"e_1_3_2_1_11_1","volume-title":"International conference on machine learning. PMLR, 12888-12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888-12900."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25225"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.27"},{"key":"e_1_3_2_1_14_1","volume-title":"Dc-former: Diverse and compact transformer for person re-identification.","author":"Li Wen","year":"2023","unstructured":"Wen Li, Cheng Zou, Meng Wang, Furong Xu, Jianan Zhao, Ruobing Zheng, Yuan Cheng, and Wei Chu. 2023b. Dc-former: Diverse and compact transformer for person re-identification. Vol. 37, 2 (2023), 1415-1423."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3346168"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361491"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00167"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00063"},{"key":"e_1_3_2_1_19_1","volume-title":"Clipcap: Clip prefix for image captioning. arXiv preprint arXiv:2111.09734","author":"Mokady Ron","year":"2021","unstructured":"Ron Mokady, Amir Hertz, and Amit H Bermano. 2021. Clipcap: Clip prefix for image captioning. arXiv preprint arXiv:2111.09734 (2021)."},{"key":"e_1_3_2_1_20_1","volume-title":"Soan TM Duong, Nguyen Tran Hoang, Sam Tran, Dao Huu Hung, Chanh D Tr Nguyen, Trung Bui, and Steven QH Truong.","author":"Phan Nguyen","year":"2023","unstructured":"Nguyen Phan, Ta Duc Huy, Soan TM Duong, Nguyen Tran Hoang, Sam Tran, Dao Huu Hung, Chanh D Tr Nguyen, Trung Bui, and Steven QH Truong. 2023. Logovit: Local-global vision transformer for object re-identification. (2023), 1-5."},{"key":"e_1_3_2_1_21_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_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00106"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_1_24_1","volume-title":"Text Self-Supervision Enhances Visual-Language Learning for Person Re-Identification. In 2024 IEEE 17th International Symposium on Embedded Multicore\/Many-core Systems-on-Chip (MCSoC). IEEE, 63-69","author":"Wang Bin","year":"2024","unstructured":"Bin Wang, Huakun Huang, Guowei Liu, Yatie Xiao, Lingjun Zhao, and Zhenbang Liu. 2024. Text Self-Supervision Enhances Visual-Language Learning for Person Re-Identification. In 2024 IEEE 17th International Symposium on Embedded Multicore\/Many-core Systems-on-Chip (MCSoC). IEEE, 63-69."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00648"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3179902"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20155"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206086"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00016"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01642"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2891888"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3535353"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01358"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3128330"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00325"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.349"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.133"},{"key":"e_1_3_2_1_38_1","volume-title":"Person re-identification: Past, present and future. arXiv preprint arXiv:1610.02984","author":"Zheng Liang","year":"2016","unstructured":"Liang Zheng, Yi Yang, and Alexander G Hauptmann. 2016. Person re-identification: Past, present and future. arXiv preprint arXiv:1610.02984 (2016)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.405"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00380"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00465"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_21"},{"key":"e_1_3_2_1_44_1","volume-title":"Aaformer: Auto-aligned transformer for person re-identification","author":"Zhu Kuan","year":"2023","unstructured":"Kuan Zhu, Haiyun Guo, Shiliang Zhang, Yaowei Wang, Jing Liu, Jinqiao Wang, and Ming Tang. 2023. Aaformer: Auto-aligned transformer for person re-identification. IEEE transactions on neural networks and learning systems (2023)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755580","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:03:15Z","timestamp":1765310595000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755580"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":44,"alternative-id":["10.1145\/3746027.3755580","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755580","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}