{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:26:01Z","timestamp":1765308361095,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476260, 62225207, 62436008"],"award-info":[{"award-number":["62476260, 62225207, 62436008"]}],"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":["WK2100000057"],"award-info":[{"award-number":["WK2100000057"]}],"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\/3746027.3755063","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:50:47Z","timestamp":1761371447000},"page":"6037-6046","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual Uncertainty-Guided Feature Alignment Learning for Text-Based Person Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0774-2027","authenticated-orcid":false,"given":"Yufei","family":"Zheng","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9940-6366","authenticated-orcid":false,"given":"Jiawei","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6482-2803","authenticated-orcid":false,"given":"Bingyu","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7231-3696","authenticated-orcid":false,"given":"Zikun","family":"Wei","sequence":"additional","affiliation":[{"name":"Independent, Independent Researcher, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5558-4631","authenticated-orcid":false,"given":"Yong","family":"Wu","sequence":"additional","affiliation":[{"name":"AI Lab, China Merchants Bank, Chengdu, Sichuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2510-8993","authenticated-orcid":false,"given":"Zheng-Jun","family":"Zha","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, 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\/WACV45572.2020.9093640"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/62"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27801"},{"key":"e_1_3_2_1_4_1","volume-title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions. arXiv preprint arXiv:2311.12793","author":"Chen Lin","year":"2023","unstructured":"Lin Chen, Jisong Li, Xiaoyi Dong, Pan Zhang, Conghui He, Jiaqi Wang, Feng Zhao, and Dahua Lin. 2023. ShareGPT4V: Improving Large Multi-Modal Models with Better Captions. arXiv preprint arXiv:2311.12793 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.081"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"e_1_3_2_1_7_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. 2021. 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_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20370"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205216"},{"key":"e_1_3_2_1_10_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_1_11_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_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02228"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6777"},{"key":"e_1_3_2_1_15_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28101"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612244"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350991"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29314"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611768"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"e_1_3_2_1_23_1","volume-title":"Modeling uncertainty with hedged instance embedding. arXiv preprint arXiv:1810.00319","author":"Oh Seong Joon","year":"2018","unstructured":"Seong Joon Oh, Kevin Murphy, Jiyan Pan, Joseph Roth, Florian Schroff, and Andrew Gallagher. 2018. Modeling uncertainty with hedged instance embedding. arXiv preprint arXiv:1810.00319 (2018)."},{"key":"e_1_3_2_1_24_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)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6857"},{"key":"e_1_3_2_1_26_1","volume-title":"A study of Gaussian mixture models of color and texture features for image classification and segmentation. Pattern recognition","author":"Permuter Haim","year":"2006","unstructured":"Haim Permuter, Joseph Francos, and Ian Jermyn. 2006. A study of Gaussian mixture models of color and texture features for image classification and segmentation. Pattern recognition, Vol. 39, 4 (2006), 695-706."},{"key":"e_1_3_2_1_27_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_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548028"},{"key":"e_1_3_2_1_29_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_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28298"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01621"},{"key":"e_1_3_2_1_32_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_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681553"},{"key":"e_1_3_2_1_34_1","volume-title":"Vitaa: Visual-textual attributes alignment in person search by natural language. In Computer Vision-ECCV 2020: 16th European Conference","author":"Wang Zhe","year":"2020","unstructured":"Zhe Wang, Zhiyuan Fang, Jun Wang, and Yezhou Yang. 2020. 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."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548166"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00016"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00165"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327924"},{"key":"e_1_3_2_1_39_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)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611709"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972168"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28585"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413864"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_21"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02078"}],"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\/3746027.3755063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:21:36Z","timestamp":1765308096000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755063"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":48,"alternative-id":["10.1145\/3746027.3755063","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755063","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"}}]}}