{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:03:58Z","timestamp":1784138638003,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":72,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"the Key Research and Development Project in Shaanxi Province","award":["2023GXLH-024"],"award-info":[{"award-number":["2023GXLH-024"]}]},{"name":"National Natural Science Foundation of China","award":["62302380"],"award-info":[{"award-number":["62302380"]}]},{"name":"National Natural Science Foundation of China","award":["62476215"],"award-info":[{"award-number":["62476215"]}]},{"name":"National Natural Science Foundation of China","award":["62037001"],"award-info":[{"award-number":["62037001"]}]},{"name":"National Natural Science Foundation of China","award":["62137002"],"award-info":[{"award-number":["62137002"]}]},{"name":"National Natural Science Foundation of China","award":["62192781"],"award-info":[{"award-number":["62192781"]}]},{"name":"the China Postdoctoral Science Foundation","award":["2023M742789"],"award-info":[{"award-number":["2023M742789"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809718","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"494-504","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Unifying Granularity and Reliability: A Robust and Efficient Framework for Text-based Person Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0936-6551","authenticated-orcid":false,"given":"Jingchen","family":"Hao","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9961-9507","authenticated-orcid":false,"given":"Jiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an, China and China Telecom Artificial Intelligence Technology (Beijing) Co., Ltd, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9791-6637","authenticated-orcid":false,"given":"Zhen","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1727-2737","authenticated-orcid":false,"given":"Yuting","family":"Zhang","sequence":"additional","affiliation":[{"name":"China Telecom Artificial Intelligence Technology (Beijing) Co., Ltd, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1835-9271","authenticated-orcid":false,"given":"Zhongjiang","family":"He","sequence":"additional","affiliation":[{"name":"China Telecom Artificial Intelligence Technology (Beijing) Co., Ltd, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0330-5435","authenticated-orcid":false,"given":"Weizhan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7917-1628","authenticated-orcid":false,"given":"Hao","family":"Sun","sequence":"additional","affiliation":[{"name":"China Telecom Artificial Intelligence Technology (Beijing) Co., Ltd, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"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","volume-title":"International conference on machine learning. PMLR, 233-242","author":"Arpit Devansh","year":"2017","unstructured":"Devansh Arpit, Stanis\u0142aw Jastrz\u0119bski, Nicolas Ballas, David Krueger, Emmanuel Bengio, Maxinder S Kanwal, Tegan Maharaj, Asja Fischer, Aaron Courville, Yoshua Bengio, et al., 2017. A closer look at memorization in deep networks. In International conference on machine learning. PMLR, 233-242."},{"key":"e_1_3_2_1_3_1","volume-title":"International conference on machine learning. PMLR, 864-873","author":"Bhojanapalli Srinadh","year":"2020","unstructured":"Srinadh Bhojanapalli, Chulhee Yun, Ankit Singh Rawat, Sashank Reddi, and Sanjiv Kumar. 2020. Low-rank bottleneck in multi-head attention models. In International conference on machine learning. PMLR, 864-873."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27801"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1212"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00208"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3068825"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.081"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-025-00078-x"},{"key":"e_1_3_2_1_10_1","first-page":"4171","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 4171-4186."},{"key":"e_1_3_2_1_11_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_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20370"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01451"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3273719"},{"key":"e_1_3_2_1_15_1","volume-title":"Visual-textual association with hardest and semi-hard negative pairs mining for person search. arXiv preprint arXiv:1912.03083","author":"Ge Jing","year":"2019","unstructured":"Jing Ge, Guangyu Gao, and Zhen Liu. 2019. Visual-textual association with hardest and semi-hard negative pairs mining for person search. arXiv preprint arXiv:1912.03083 (2019)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1514"},{"key":"e_1_3_2_1_17_1","volume-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels. Advances in neural information processing systems","author":"Han Bo","year":"2018","unstructured":"Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor Tsang, and Masashi Sugiyama. 2018. Co-teaching: Robust training of deep neural networks with extremely noisy labels. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_18_1","volume-title":"Text-based person search with limited data. arXiv preprint arXiv:2110.10807","author":"Han Xiao","year":"2021","unstructured":"Xiao Han, Sen He, Li Zhang, and Tao Xiang. 2021. Text-based person search with limited data. arXiv preprint arXiv:2110.10807 (2021)."},{"key":"e_1_3_2_1_19_1","volume-title":"Towards a unified view of parameter-efficient transfer learning. arXiv preprint arXiv:2110.04366","author":"He Junxian","year":"2021","unstructured":"Junxian He, Chunting Zhou, Xuezhe Ma, Taylor Berg-Kirkpatrick, and Graham Neubig. 2021. Towards a unified view of parameter-efficient transfer learning. arXiv preprint arXiv:2110.04366 (2021)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_21_1","volume-title":"Long short-term memory. Neural computation","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation, Vol. 9, 8 (1997), 1735-1780."},{"key":"e_1_3_2_1_22_1","volume-title":"International conference on machine learning. PMLR, 2790-2799","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In International conference on machine learning. PMLR, 2790-2799."},{"key":"e_1_3_2_1_23_1","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2022. Lora: Low-rank adaptation of large language models. ICLR, Vol. 1, 2 (2022), 3.","journal-title":"ICLR"},{"key":"e_1_3_2_1_24_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_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.322"},{"key":"e_1_3_2_1_28_1","volume-title":"The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691","author":"Lester Brian","year":"2021","unstructured":"Brian Lester, Rami Al-Rfou, and Noah Constant. 2021. The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691 (2021)."},{"key":"e_1_3_2_1_29_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. 2022b. 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_30_1","volume-title":"Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath Selvaraju, Akhilesh Gotmare, Shafiq Joty, Caiming Xiong, and Steven Chu Hong Hoi. 2021. Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems, Vol. 34 (2021), 9694-9705."},{"key":"e_1_3_2_1_31_1","volume-title":"Dividemix: Learning with noisy labels as semi-supervised learning. arXiv preprint arXiv:2002.07394","author":"Li Junnan","year":"2020","unstructured":"Junnan Li, Richard Socher, and Steven CH Hoi. 2020. Dividemix: Learning with noisy labels as semi-supervised learning. arXiv preprint arXiv:2002.07394 (2020)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746846"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28101"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.209"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"e_1_3_2_1_36_1","volume-title":"Data augmentation for text-based person retrieval using large language models. arXiv preprint arXiv:2405.11971","author":"Li Zheng","year":"2024","unstructured":"Zheng Li, Lijia Si, Caili Guo, Yang Yang, and Qiushi Cao. 2024b. Data augmentation for text-based person retrieval using large language models. arXiv preprint arXiv:2405.11971 (2024)."},{"key":"e_1_3_2_1_37_1","volume-title":"UP-Person: Unified Parameter-Efficient Transfer Learning for Text-based Person Retrieval. arXiv preprint arXiv:2504.10084","author":"Liu Yating","year":"2025","unstructured":"Yating Liu, Yaowei Li, Xiangyuan Lan, Wenming Yang, Zimo Liu, and Qingmin Liao. 2025a. UP-Person: Unified Parameter-Efficient Transfer Learning for Text-based Person Retrieval. arXiv preprint arXiv:2504.10084 (2025)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445963"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32608"},{"key":"e_1_3_2_1_40_1","volume-title":"LLaVA-ReID: Selective multi-image questioner for interactive person re-identification. arXiv preprint arXiv:2504.10174","author":"Lu Yiding","year":"2025","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 preprint arXiv:2504.10174 (2025)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3594880"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3574970"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01342"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02568"},{"key":"e_1_3_2_1_45_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_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00591"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548028"},{"key":"e_1_3_2_1_48_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_49_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714788"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.06.017"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01621"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0693"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548057"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3290477"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00165"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.266"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222570"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611832"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327924"},{"key":"e_1_3_2_1_62_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. 2023c. 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_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611709"},{"key":"e_1_3_2_1_64_1","volume-title":"Deep learning for person re-identification: A survey and outlook","author":"Ye Mang","year":"2021","unstructured":"Mang Ye, Jianbing Shen, Gaojie Lin, Tao Xiang, Ling Shao, and Steven CH Hoi. 2021. Deep learning for person re-identification: A survey and outlook. IEEE transactions on pattern analysis and machine intelligence, Vol. 44, 6 (2021), 2872-2893."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3573185"},{"key":"e_1_3_2_1_66_1","volume-title":"Divide and fuse: A re-ranking approach for person re-identification. arXiv preprint arXiv:1708.04169","author":"Yu Rui","year":"2017","unstructured":"Rui Yu, Zhichao Zhou, Song Bai, and Xiang Bai. 2017. Divide and fuse: A re-ranking approach for person re-identification. arXiv preprint arXiv:1708.04169 (2017)."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.14"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.389"},{"key":"e_1_3_2_1_70_1","volume-title":"International conference on learning representations.","author":"Zhou Tianyi","year":"2020","unstructured":"Tianyi Zhou, Shengjie Wang, and Jeff Bilmes. 2020. Robust curriculum learning: from clean label detection to noisy label self-correction. In International conference on learning representations."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02078"}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:07:28Z","timestamp":1784135248000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809718"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":72,"alternative-id":["10.1145\/3805712.3809718","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809718","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}