{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:20:32Z","timestamp":1765308032327,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176188, 62361166629, 62476188"],"award-info":[{"award-number":["62176188, 62361166629, 62476188"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758150","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:44:48Z","timestamp":1761371088000},"page":"12247-12256","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MLLMs Meet Person Re-identification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8068-0838","authenticated-orcid":false,"given":"Mengying","family":"Duan","sequence":"first","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8469-8260","authenticated-orcid":false,"given":"He","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3989-7655","authenticated-orcid":false,"given":"Mang","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et al. 2023. GPT-4 Technical Report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/AIBThings58340.2023.10292475"},{"key":"e_1_3_2_2_3_1","unstructured":"Anthropic. 2023. Claude-intro. https:\/\/www.anthropic.com\/news\/introducing-claude. Accessed: 2024-11-9."},{"key":"e_1_3_2_2_4_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang Binyuan Hui Luo Ji Mei Li Junyang Lin Runji Lin Dayiheng Liu Gao Liu Chengqiang Lu Keming Lu et al. 2023. Qwen Technical Report. arXiv:2309.16609 [cs.CL] https:\/\/arxiv.org\/abs\/2309.16609"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2014.6918664"},{"key":"e_1_3_2_2_6_1","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, J. Vanschoren and S. Yeung (Eds.)","volume":"1","author":"Chen Minghui","year":"2021","unstructured":"Minghui Chen, Zhiqiang Wang, and Feng Zheng. 2021. Benchmarks for Corruption Invariant Person Re-identification. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, J. Vanschoren and S. Yeung (Eds.), Vol. 1."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01445"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2666805"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01711"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i11.33216"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3370437"},{"key":"e_1_3_2_2_12_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_2_13_1","doi-asserted-by":"crossref","unstructured":"Parisa Farmanifard and Arun Ross. 2024. ChatGPT Meets Iris Biometrics. arXiv:2408.04868 [cs.CV] https:\/\/arxiv.org\/abs\/2408.04868","DOI":"10.1109\/IJCB62174.2024.10744525"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/FIE58773.2023.10343006"},{"key":"e_1_3_2_2_15_1","first-page":"1","volume-title":"Proc. IEEE international workshop on performance evaluation for tracking and surveillance (PETS)","volume":"3","author":"Gray Douglas","year":"2007","unstructured":"Douglas Gray, Shane Brennan, and Hai Tao. 2007. Evaluating appearance models for recognition, reacquisition, and tracking. In Proc. IEEE international workshop on performance evaluation for tracking and surveillance (PETS), Vol. 3. 1-7."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647924"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"e_1_3_2_2_18_1","volume-title":"Empowering Visible-Infrared Person Re-Identification with Large Foundation Models. In The Thirty-eighth Annual Conference on Neural Information Processing Systems.","author":"Hu Zhangyi","year":"2024","unstructured":"Zhangyi Hu, Bin Yang, and Mang Ye. 2024. Empowering Visible-Infrared Person Re-Identification with Large Foundation Models. In The Thirty-eighth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350994"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350994"},{"key":"e_1_3_2_2_21_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. GPT-4o System Card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00436"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00321"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.513"},{"key":"e_1_3_2_2_25_1","volume-title":"Stephan G\u00fcnnemann, Eyke H\u00fcllermeier, Stephan Krusche, Gitta Kutyniok, Tilman Michaeli, Claudia Nerdel, J\u00fcrgen Pfeffer, Oleksandra Poquet, Michael Sailer, Albrecht Schmidt, Tina Seidel, et al.","author":"Kasneci Enkelejda","year":"2023","unstructured":"Enkelejda Kasneci, Kathrin Se\u00dfler, Stefan K\u00fcchemann, Maria Bannert, Daryna Dementieva, Frank Fischer, Urs Gasser, George Louis Groh, Stephan G\u00fcnnemann, Eyke H\u00fcllermeier, Stephan Krusche, Gitta Kutyniok, Tilman Michaeli, Claudia Nerdel, J\u00fcrgen Pfeffer, Oleksandra Poquet, Michael Sailer, Albrecht Schmidt, Tina Seidel, et al., 2023. ChatGPT for good? On opportunities and challenges of large language models for education. Learning and Individual Differences (2023). https:\/\/api.semanticscholar.org\/CorpusID:257445349"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548770"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.429"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2024.3475375"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01305"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01797"},{"key":"e_1_3_2_2_31_1","unstructured":"Yiding Lu Mouxing Yang Dezhong Peng Peng Hu Yijie Lin and Xi Peng. 2025. LLaVA-ReID: Selective Multi-image Questioner for Interactive Person Re-Identification. arXiv:2504.10174 [cs.CV] https:\/\/arxiv.org\/abs\/2504.10174"},{"key":"e_1_3_2_2_32_1","volume-title":"Mehrsan Javan, Parthipan Siva, Ismail Ben Ayed, and Eric Granger.","author":"Masson Hugo","year":"2021","unstructured":"Hugo Masson, Amran Bhuiyan, Le Thanh Nguyen-Meidine, Mehrsan Javan, Parthipan Siva, Ismail Ben Ayed, and Eric Granger. 2021. Exploiting Prunability for Person Re-Identification. arXiv:1907.02547 [cs.CV] https:\/\/arxiv.org\/abs\/1907.02547"},{"key":"e_1_3_2_2_33_1","unstructured":"OpenAI. 2023. Hello GPT-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/. Accessed: 2024-10-31."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.70091\/atras\/ai.18"},{"key":"e_1_3_2_2_35_1","volume-title":"Gemini: A Family of Highly Capable Multimodal Models. arXiv:2312.11805 [cs.CL] https:\/\/arxiv.org\/abs\/2312.11805","author":"Team Gemini","year":"2024","unstructured":"Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M. Dai, Anja Hauth, Katie Millican, David Silver, et al., 2024. Gemini: A Family of Highly Capable Multimodal Models. arXiv:2312.11805 [cs.CL] https:\/\/arxiv.org\/abs\/2312.11805"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/BOTSE59190.2023.00008"},{"key":"e_1_3_2_2_37_1","volume-title":"\u0141 ukasz Kaiser, and Illia Polosukhin","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_2_2_38_1","volume-title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. arXiv preprint arXiv:2409.12191","author":"Wang Peng","year":"2024","unstructured":"Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, and Junyang Lin. 2024. Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00839"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00016"},{"key":"e_1_3_2_2_41_1","unstructured":"Zhiyu Wu Xiaokang Chen Zizheng Pan Xingchao Liu Wen Liu Damai Dai Huazuo Gao Yiyang Ma Chengyue Wu Bingxuan Wang Zhenda Xie Yu Wu Kai Hu Jiawei Wang Yaofeng Sun Yukun Li Yishi Piao Kang Guan Aixin Liu Xin Xie Yuxiang You Kai Dong Xingkai Yu Haowei Zhang Liang Zhao Yisong Wang and Chong Ruan. 2024. DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding. arXiv:2412.10302 [cs.CV] https:\/\/arxiv.org\/abs\/2412.10302"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2360373"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2960509"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3439680"},{"key":"e_1_3_2_2_45_1","unstructured":"Mang Ye Shuoyi Chen Chenyue Li Wei-Shi Zheng David Crandall and Bo Du. 2024. Transformer for Object Re-Identification: A Survey. arXiv:2401.06960 [cs.CV] https:\/\/arxiv.org\/abs\/2401.06960"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3054775"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3541053"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25436"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3472122"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.133"},{"key":"e_1_3_2_2_51_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_2_52_1","volume-title":"Chen Change Loy, and Xiaoou Tang","author":"Zhu Shizhan","year":"2016","unstructured":"Shizhan Zhu, Sifei Liu, Chen Change Loy, and Xiaoou Tang. 2016. Deep Cascaded Bi-Network for Face Hallucination. In Computer Vision - ECCV 2016, Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling (Eds.). Springer International Publishing, Cham, 614-630."}],"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\/3746027.3758150","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:16:32Z","timestamp":1765307792000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758150"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":52,"alternative-id":["10.1145\/3746027.3758150","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758150","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"}}]}}