{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:43:39Z","timestamp":1783737819691,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206006; 62302140"],"award-info":[{"award-number":["62206006; 62302140"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["JZ2024HGTB0261"],"award-info":[{"award-number":["JZ2024HGTB0261"]}],"id":[{"id":"10.13039\/501100012226","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\/3746027.3755171","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:39:06Z","timestamp":1761377946000},"page":"6047-6056","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Unsupervised Cross-Modal Person Search via Progressive Diverse Text Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8946-0083","authenticated-orcid":false,"given":"Feng","family":"Chen","sequence":"first","affiliation":[{"name":"Anhui University of Technology, Ma'anshan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6676-1902","authenticated-orcid":false,"given":"Jielong","family":"He","sequence":"additional","affiliation":[{"name":"Anhui University of Technology, Ma'anshan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5905-0974","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Anhui university of technology, Ma'anshan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7563-2676","authenticated-orcid":false,"given":"Heng","family":"Liu","sequence":"additional","affiliation":[{"name":"AnHui University of Technology, Ma'anshan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7877-8775","authenticated-orcid":false,"given":"Zhe","family":"Chen","sequence":"additional","affiliation":[{"name":"Anhui University of Technology, Ma'anshan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6596-8117","authenticated-orcid":false,"given":"Yaxiong","family":"Wang","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/62"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612285"},{"key":"e_1_3_2_1_3_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877-1901."},{"key":"e_1_3_2_1_4_1","volume-title":"Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification. arXiv e-prints","author":"Ding Zefeng","year":"2021","unstructured":"Zefeng Ding, Changxing Ding, Zhiyin Shao, and Dacheng Tao. 2021. Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification. arXiv e-prints (2021), arXiv-2107."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 32nd ACM International Conference on Multimedia. 9397-9406","author":"Duan Yue","year":"2024","unstructured":"Yue Duan, Zhangxuan Gu, Zhenzhe Ying, Lei Qi, Changhua Meng, and Yinghuan Shi. 2024. PC2: Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrieval. In Proceedings of the 32nd ACM International Conference on Multimedia. 9397-9406."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20370"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence. 794-802","author":"Gong Tiantian","year":"2024","unstructured":"Tiantian Gong, Junsheng Wang, and Liyan Zhang. 2024. Enhancing cross-modal completion and alignment for unsupervised incomplete text-to-image person retrieval. In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence. 794-802."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3717656"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3337653"},{"key":"e_1_3_2_1_10_1","first-page":"29406","article-title":"Learning with noisy correspondence for cross-modal matching","volume":"34","author":"Huang Zhenyu","year":"2021","unstructured":"Zhenyu Huang, Guocheng Niu, Xiao Liu, Wenbiao Ding, Xinyan Xiao, Hua Wu, and Xi Peng. 2021. Learning with noisy correspondence for cross-modal matching. Advances in Neural Information Processing Systems, Vol. 34 (2021), 29406-29419.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"e_1_3_2_1_12_1","volume-title":"CaLa: Complementary Association Learning for Augmenting Composed Image Retrieval. SIGIR","author":"Jiang Xintong","year":"2024","unstructured":"Xintong Jiang, Yaxiong Wang, Yujiao Wu, Bingwen Hu, and Xueming Qian. 2024. CaLa: Complementary Association Learning for Augmenting Composed Image Retrieval. SIGIR (2024)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3285601"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3285601"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In Proceedings of the International conference on machine learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 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 Proceedings of the International conference on machine learning. PMLR, 12888-12900."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28101"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.209"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the International Joint Conference on Artificial Intelligence. 1047-1055","author":"Li Zongyi","year":"2024","unstructured":"Zongyi Li, Jianbo Li, Yuxuan Shi, Hefei Ling, Jiazhong Chen, Runsheng Wang, and Shijuan Huang. 2024b. Cross-modal generation and alignment via attribute-guided prompt for unsupervised text-based person retrieval. In Proceedings of the International Joint Conference on Artificial Intelligence. 1047-1055."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3355644"},{"key":"e_1_3_2_1_22_1","volume-title":"Improving person re-identification by attribute and identity learning. Pattern recognition","author":"Lin Yutian","year":"2019","unstructured":"Yutian Lin, Liang Zheng, Zhedong Zheng, Yu Wu, Zhilan Hu, Chenggang Yan, and Yi Yang. 2019. Improving person re-identification by attribute and identity learning. Pattern recognition, Vol. 95 (2019), 151-161."},{"key":"e_1_3_2_1_23_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2023), 34892-34916."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29314"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447260"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3385500"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2699623"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612009"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01621"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01553"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/148"},{"key":"e_1_3_2_1_32_1","volume-title":"Beyond General Alignment: Fine-Grained Entity-Centric Image-Text Matching with Multimodal Attentive Experts. SIGIR","author":"Wang Yaxiong","year":"2025","unstructured":"Yaxiong Wang, Lianwei Wu, Lechao Cheng, Zhun Zhong, Yujiao Wu, and Meng Wang. 2025. Beyond General Alignment: Fine-Grained Entity-Centric Image-Text Matching with Multimodal Attentive Experts. SIGIR (2025)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3024822"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.24963\/IJCAI.2019\/526"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3340102"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548057"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548166"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00363"},{"key":"e_1_3_2_1_40_1","volume-title":"Cap4Video: Enhancing Video Understanding with Auxiliary Captions","author":"Wu Wenhao","year":"2024","unstructured":"Wenhao Wu, Xiaohan Wang, Haipeng Luo, Jingdong Wang, Yi Yang, and Wanli Ouyang. 2024b. Cap4Video: Enhancing Video Understanding with Auxiliary Captions. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024), 1-15."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124071"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327924"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611709"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3390984"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01337"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02247"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28524"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.KNOSYS.2023.110280"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01120"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01120"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3368217"},{"key":"e_1_3_2_1_54_1","first-page":"45666","article-title":"Plip: Language-image pre-training for person representation learning","volume":"37","author":"Zuo Jialong","year":"2024","unstructured":"Jialong Zuo, Jiahao Hong, Feng Zhang, Changqian Yu, Hanyu Zhou, Changxin Gao, Nong Sang, and Jingdong Wang. 2024. Plip: Language-image pre-training for person representation learning. Advances in Neural Information Processing Systems, Vol. 37 (2024), 45666-45702.","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755171","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:57:56Z","timestamp":1765310276000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755171"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":54,"alternative-id":["10.1145\/3746027.3755171","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755171","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"}}]}}