{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:46:26Z","timestamp":1765309586874,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation (NSF) of China","award":["No.62206156, No.62306074, No.62276155, No.72004127, and No.62206157"],"award-info":[{"award-number":["No.62206156, No.62306074, No.62276155, No.72004127, and No.62206157"]}]},{"name":"NSF of Shandong Province","award":["No.ZR2024QF104, No.ZR2021MF040 and No.ZR2022QF047"],"award-info":[{"award-number":["No.ZR2024QF104, No.ZR2021MF040 and No.ZR2022QF047"]}]},{"name":"Key R&D Program of Shandong Province, China (Major Scientific and Technological Innovation Projects)","award":["No.2022CXGC020107"],"award-info":[{"award-number":["No.2022CXGC020107"]}]},{"name":"Key Research and Development Program of Shaanxi","award":["No.2024GX-YBXM- 556"],"award-info":[{"award-number":["No.2024GX-YBXM- 556"]}]},{"name":"Natural Science Basis Research Plan in Shaanxi Province of China","award":["No.2025JC-JCQN-091"],"award-info":[{"award-number":["No.2025JC-JCQN-091"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755315","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:54:17Z","timestamp":1761375257000},"page":"4107-4116","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FACE: A Dual-Template and Adaptive Curriculum Framework for Unsupervised Text-Based Person Search"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0048-0232","authenticated-orcid":false,"given":"Xiaoxuan","family":"Mu","sequence":"first","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China and School of Software, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1344-2513","authenticated-orcid":false,"given":"Haoyu","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2014-7906","authenticated-orcid":false,"given":"Han","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7576-6356","authenticated-orcid":false,"given":"Tianyuan","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8684-1577","authenticated-orcid":false,"given":"Qinghai","family":"Zheng","sequence":"additional","affiliation":[{"name":"College of Computer and Data Science, Fuzhou University, Fuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3081-8781","authenticated-orcid":false,"given":"Jihua","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_2_1_1_1","DOI":"10.24963\/ijcai.2023\/62"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_2_1","DOI":"10.1145\/3581783.3612285"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_3_1","DOI":"10.1609\/aaai.v38i1.27801"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_4_1","DOI":"10.1016\/j.neucom.2022.04.081"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_5_1","DOI":"10.1145\/3581783.3611987"},{"key":"e_1_3_2_1_6_1","volume-title":"Semantically self-aligned network for text-to-image part-aware person re-identification. arXiv preprint arXiv:2107.12666","author":"Ding Zefeng","year":"2021","unstructured":"Zefeng Ding, Changxing Ding, Zhiyin Shao, and Dacheng Tao. 2021a. Semantically self-aligned network for text-to-image part-aware person re-identification. arXiv preprint arXiv:2107.12666 (2021)."},{"key":"e_1_3_2_1_7_1","volume-title":"Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification. CoRR","author":"Ding Zefeng","year":"2021","unstructured":"Zefeng Ding, Changxing Ding, Zhiyin Shao, and Dacheng Tao. 2021b. Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification. CoRR, Vol. abs\/2107.12666 (2021)."},{"unstructured":"Martin Ester Hans-Peter Kriegel J\u00f6rg Sander Xiaowei Xu et al. 1996. A density-based algorithm for discovering clusters in large spatial databases with noise. In kdd Vol. 96. 226-231.","key":"e_1_3_2_1_8_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_9_1","DOI":"10.1609\/aaai.v36i4.20370"},{"key":"e_1_3_2_1_10_1","volume-title":"Similarity Regulation and Calibration Alignment for Weakly Supervised Text-Based Person Re-Identification. ACM Transactions on Multimedia Computing, Communications and Applications","author":"Fu Ao","year":"2025","unstructured":"Ao Fu, Jiaqi Zhao, Yong Zhou, Wenliang Du, Rui Yao, and Abdulmotaleb El Saddik. 2025. Similarity Regulation and Calibration Alignment for Weakly Supervised Text-Based Person Re-Identification. ACM Transactions on Multimedia Computing, Communications and Applications (2025)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_11_1","DOI":"10.1109\/ICCVW60793.2023.00295"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_12_1","DOI":"10.1007\/s11042-021-10983-0"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_13_1","DOI":"10.1109\/TIP.2023.3337653"},{"unstructured":"Wenyi Hong Weihan Wang Ming Ding Wenmeng Yu Qingsong Lv Yan Wang Yean Cheng Shiyu Huang Junhui Ji Zhao Xue et al. 2024. Cogvlm2: Visual language models for image and video understanding. arXiv preprint arXiv:2408.16500 (2024).","key":"e_1_3_2_1_14_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_15_1","DOI":"10.1109\/CVPR52729.2023.00273"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_16_1","DOI":"10.1609\/aaai.v34i07.6777"},{"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)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_18_1","DOI":"10.1109\/TMM.2024.3410129"},{"key":"e_1_3_2_1_19_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."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_20_1","DOI":"10.1609\/aaai.v38i4.28101"},{"key":"e_1_3_2_1_21_1","first-page":"5187","volume-title":"Person Search with Natural Language Description. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017","author":"Li Shuang","year":"2017","unstructured":"Shuang Li, Tong Xiao, Hongsheng Li, Bolei Zhou, Dayu Yue, and Xiaogang Wang. 2017. Person Search with Natural Language Description. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017. IEEE Computer Society, 5187-5196."},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the International Joint Conference on Artificial Intelligence. International Joint Conferences on Artificial Intelligence Organization. 1047-1055","author":"Li Zongyi","year":"2024","unstructured":"Zongyi Li, Jianbo Li, Yuxuan Shi, Hefei Ling, Jiazhong Chen, Runsheng Wang, and Shijuan Huang. 2024c. 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. International Joint Conferences on Artificial Intelligence Organization. 1047-1055."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_23_1","DOI":"10.1109\/TMM.2024.3355644"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_24_1","DOI":"10.1145\/3343031.3350991"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_25_1","DOI":"10.1109\/CVPR46437.2021.00970"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_26_1","DOI":"10.1109\/TIP.2020.2984883"},{"key":"e_1_3_2_1_27_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_28_1","DOI":"10.1109\/CVPR52733.2024.02568"},{"key":"e_1_3_2_1_29_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."},{"unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever et al. 2018. Improving language understanding by generative pre-training. (2018).","key":"e_1_3_2_1_30_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_31_1","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_32_1","first-page":"5813","volume-title":"Adversarial Representation Learning for Text-to-Image Matching. In 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019","author":"Sarafianos Nikolaos","year":"2019","unstructured":"Nikolaos Sarafianos, Xiang Xu, and Ioannis A. Kakadiaris. 2019. Adversarial Representation Learning for Text-to-Image Matching. In 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019. IEEE, 5813-5823."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_33_1","DOI":"10.1145\/3503161.3548028"},{"key":"e_1_3_2_1_34_1","volume-title":"European Conference on Computer Vision. Springer, 624-641","author":"Shu Xiujun","year":"2022","unstructured":"Xiujun Shu, Wei Wen, Haoqian Wu, Keyu Chen, Yiran Song, Ruizhi Qiao, Bo Ren, and Xiao Wang. 2022. See finer, see more: Implicit modality alignment for text-based person retrieval. In European Conference on Computer Vision. Springer, 624-641."},{"key":"e_1_3_2_1_35_1","volume-title":"Guiding vision-language model selection for visual question-answering across tasks, domains, and knowledge types. arXiv preprint arXiv:2409.09269","author":"Sinha Neelabh","year":"2024","unstructured":"Neelabh Sinha, Vinija Jain, and Aman Chadha. 2024. Guiding vision-language model selection for visual question-answering across tasks, domains, and knowledge types. arXiv preprint arXiv:2409.09269 (2024)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_36_1","DOI":"10.1145\/3627631.3627648"},{"unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth Katie Millican et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023).","key":"e_1_3_2_1_37_1"},{"key":"e_1_3_2_1_38_1","first-page":"1068","article-title":"Text-based person search via multi-granularity embedding learning","author":"Wang Chengji","year":"2021","unstructured":"Chengji Wang, Zhiming Luo, Yaojin Lin, and Shaozi Li. 2021. Text-based person search via multi-granularity embedding learning.. In IJCAI. 1068-1074.","journal-title":"IJCAI."},{"key":"e_1_3_2_1_39_1","volume-title":"Exploiting the textual potential from vision-language pre-training for text-based person search. arXiv preprint arXiv:2303.04497","author":"Wang Guanshuo","year":"2023","unstructured":"Guanshuo Wang, Fufu Yu, Junjie Li, Qiong Jia, and Shouhong Ding. 2023. Exploiting the textual potential from vision-language pre-training for text-based person search. arXiv preprint arXiv:2303.04497 (2023)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_40_1","DOI":"10.1109\/CVPR52688.2022.00715"},{"key":"e_1_3_2_1_41_1","volume-title":"UK","volume":"420","author":"Wang Zhe","year":"2020","unstructured":"Zhe Wang, Zhiyuan Fang, Jun Wang, and Yezhou Yang. 2020a. ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language. In Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XII (Lecture Notes in Computer Science, Vol. 12357), Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan-Michael Frahm (Eds.). Springer, 402-420."},{"key":"e_1_3_2_1_42_1","first-page":"402","volume-title":"UK","author":"Wang Zhe","year":"2020","unstructured":"Zhe Wang, Zhiyuan Fang, Jun Wang, and Yezhou Yang. 2020b. Vitaa: Visual-textual attributes alignment in person search by natural language. In Computer vision-ECCV 2020: 16th European conference, glasgow, UK, August 23-28, 2020, proceedings, part XII 16. Springer, 402-420."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_43_1","DOI":"10.1145\/3503161.3548057"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_44_1","DOI":"10.1145\/3503161.3548166"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_45_1","DOI":"10.1109\/TCSVT.2024.3392831"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_46_1","DOI":"10.1609\/aaai.v38i6.28433"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_47_1","DOI":"10.1109\/ICCV48922.2021.00165"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_48_1","DOI":"10.1109\/TIP.2023.3327924"},{"key":"e_1_3_2_1_49_1","volume-title":"Image-specific information suppression and implicit local alignment for text-based person search","author":"Yan Shuanglin","year":"2023","unstructured":"Shuanglin Yan, Hao Tang, Liyan Zhang, and Jinhui Tang. 2023b. Image-specific information suppression and implicit local alignment for text-based person search. IEEE transactions on neural networks and learning systems (2023)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_50_1","DOI":"10.1145\/3581783.3611709"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_51_1","DOI":"10.1109\/TMM.2020.2972168"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_52_1","DOI":"10.1145\/3664647.3680591"},{"key":"e_1_3_2_1_53_1","volume-title":"Munich","volume":"723","author":"Zhang Ying","year":"2018","unstructured":"Ying Zhang and Huchuan Lu. 2018. Deep Cross-Modal Projection Learning for Image-Text Matching. In Computer Vision - ECCV 2018 - 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part I (Lecture Notes in Computer Science, Vol. 11205). Springer, 707-723."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_54_1","DOI":"10.1109\/ICCV48922.2021.01120"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_55_1","DOI":"10.1145\/3394171.3413864"},{"key":"e_1_3_2_1_56_1","volume-title":"CPCL: Cross-Modal Prototypical Contrastive Learning for Weakly Supervised Text-based Person Re-Identification. arXiv preprint arXiv:2401.10011","author":"Zheng Yanwei","year":"2024","unstructured":"Yanwei Zheng, Xinpeng Zhao, Chuanlin Lan, Xiaowei Zhang, Bowen Huang, Jibin Yang, and Dongxiao Yu. 2024. CPCL: Cross-Modal Prototypical Contrastive Learning for Weakly Supervised Text-based Person Re-Identification. arXiv preprint arXiv:2401.10011 (2024)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_57_1","DOI":"10.1145\/3383184"},{"key":"e_1_3_2_1_58_1","first-page":"209","volume-title":"DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval. In MM '21: ACM Multimedia Conference","author":"Zhu Aichun","year":"2021","unstructured":"Aichun Zhu, Zijie Wang, Yifeng Li, Xili Wan, Jing Jin, Tian Wang, Fangqiang Hu, and Gang Hua. 2021. DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval. In MM '21: ACM Multimedia Conference, Virtual Event, China, October 20 - 24, 2021. ACM, 209-217."}],"event":{"sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"acronym":"MM '25","name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755315","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:43:01Z","timestamp":1765309381000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755315"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":58,"alternative-id":["10.1145\/3746027.3755315","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755315","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"}}]}}