{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T07:41:27Z","timestamp":1765438887733,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T00:00:00Z","timestamp":1686528000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222203, 61976049, U20B2063"],"award-info":[{"award-number":["62222203, 61976049, U20B2063"]}],"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":[[2023,6,12]]},"DOI":"10.1145\/3591106.3592253","type":"proceedings-article","created":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T22:33:38Z","timestamp":1686263618000},"page":"307-315","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Multi-granularity Separation Network for Text-Based Person Retrieval with Bidirectional Refinement Regularization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6340-012X","authenticated-orcid":false,"given":"Shenshen","family":"Li","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5685-3123","authenticated-orcid":false,"given":"Xing","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7303-3231","authenticated-orcid":false,"given":"Fumin","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5070-4511","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, China"}]}],"member":"320","published-online":{"date-parts":[[2023,6,12]]},"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":"Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification. CoRR abs\/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. CoRR abs\/2107.12666 (2021)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Ammarah Farooq Muhammad Awais Josef Kittler and Syed\u00a0Safwan Khalid. 2022. AXM-Net: Implicit Cross-Modal Feature Alignment for Person Re-identification. In AAAI. 4477\u20134485.","DOI":"10.1609\/aaai.v36i4.20370"},{"key":"e_1_3_2_1_4_1","volume-title":"Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search. CoRR abs\/2101.03036","author":"Gao Chenyang","year":"2021","unstructured":"Chenyang Gao, Guanyu Cai, Xinyang Jiang, Feng Zheng, Jun Zhang, Yifei Gong, Pai Peng, Xiaowei Guo, and Xing Sun. 2021. Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search. CoRR abs\/2101.03036 (2021)."},{"key":"e_1_3_2_1_5_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. 770\u2013778."},{"key":"e_1_3_2_1_6_1","volume-title":"BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification. In IEEE Conference on Computer Vision and Pattern Recognition. 2014\u20132023","author":"Hou Ruibing","year":"2021","unstructured":"Ruibing Hou, Hong Chang, Bingpeng Ma, Rui Huang, and Shiguang Shan. 2021. BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification. In IEEE Conference on Computer Vision and Pattern Recognition. 2014\u20132023."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Xin Jin Cuiling Lan Wenjun Zeng and Zhibo Chen. 2020. Global Distance-Distributions Separation for Unsupervised Person Re-identification. In ECCV. 735\u2013751.","DOI":"10.1007\/978-3-030-58571-6_43"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Ya Jing Chenyang Si Junbo Wang Wei Wang Liang Wang and Tieniu Tan. 2020. Pose-Guided Multi-Granularity Attention Network for Text-Based Person Search. In AAAI. 11189\u201311196.","DOI":"10.1609\/aaai.v34i07.6777"},{"key":"e_1_3_2_1_9_1","volume-title":"Person Search with Natural Language Description. In IEEE Conference on Computer Vision and Pattern Recognition. 5187\u20135196","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 IEEE Conference on Computer Vision and Pattern Recognition. 5187\u20135196."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413895"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_13_1","volume-title":"Adversarial Representation Learning for Text-to-Image Matching. In IEEE\/CVF International Conference on Computer Vision. 5813\u20135823","author":"Sarafianos Nikolaos","year":"2019","unstructured":"Nikolaos Sarafianos, Xiang Xu, and Ioannis\u00a0A. Kakadiaris. 2019. Adversarial Representation Learning for Text-to-Image Matching. In IEEE\/CVF International Conference on Computer Vision. 5813\u20135823."},{"key":"e_1_3_2_1_14_1","volume-title":"Learning Granularity-Unified Representations for Text-to-Image Person Re-identification. In The ACM International Conference on Multimedia. 5566\u20135574","author":"Shao Zhiyin","year":"2022","unstructured":"Zhiyin Shao, Xinyu Zhang, Meng Fang, Zhifeng Lin, Jian Wang, and Changxing Ding. 2022. Learning Granularity-Unified Representations for Text-to-Image Person Re-identification. In The ACM International Conference on Multimedia. 5566\u20135574."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Wei Suo Mengyang Sun Kai Niu Yiqi Gao Peng Wang Yanning Zhang and Qi Wu. 2022. A Simple and Robust Correlation Filtering Method for Text-Based Person Search. In ECCV. 726\u2013742.","DOI":"10.1007\/978-3-031-19833-5_42"},{"key":"e_1_3_2_1_16_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems. 5998\u20136008."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/148"},{"key":"e_1_3_2_1_18_1","volume-title":"UK","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, Vol.\u00a012357. 402\u2013420."},{"key":"e_1_3_2_1_19_1","volume-title":"CAIBC: Capturing All-round Information Beyond Color for Text-based Person Retrieval. In ACM International Conference on Multimedia. 5314\u20135322","author":"Wang Zijie","year":"2022","unstructured":"Zijie Wang, Aichun Zhu, Jingyi Xue, Xili Wan, Chao Liu, Tian Wang, and Yifeng Li. 2022. CAIBC: Capturing All-round Information Beyond Color for Text-based Person Retrieval. In ACM International Conference on Multimedia. 5314\u20135322."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548166"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00016"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00165"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-018-0541-x"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2676345"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2967597"},{"key":"e_1_3_2_1_26_1","volume-title":"Image-Specific Information Suppression and Implicit Local Alignment for Text-based Person Search. CoRR abs\/2208.14365","author":"Yan Shuanglin","year":"2022","unstructured":"Shuanglin Yan, Hao Tang, Liyan Zhang, and Jinhui Tang. 2022. Image-Specific Information Suppression and Implicit Local Alignment for Text-based Person Search. CoRR abs\/2208.14365 (2022)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Dong Yi Zhen Lei Shengcai Liao and Stan\u00a0Z. Li. 2014. Deep Metric Learning for Person Re-identification. In ICPR. 34\u201339.","DOI":"10.1109\/ICPR.2014.16"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.10.083"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Ying Zhang and Huchuan Lu. 2018. Deep Cross-Modal Projection Learning for Image-Text Matching. In ECCV. 707\u2013723.","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"e_1_3_2_1_30_1","volume-title":"Hierarchical Gumbel Attention Network for Text-based Person Search. In ACM International Conference on Multimedia. 3441\u20133449","author":"Zheng Kecheng","year":"2020","unstructured":"Kecheng Zheng, Wu Liu, Jiawei Liu, Zheng-Jun Zha, and Tao Mei. 2020. Hierarchical Gumbel Attention Network for Text-based Person Search. In ACM International Conference on Multimedia. 3441\u20133449."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"}],"event":{"name":"ICMR '23: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Thessaloniki Greece","acronym":"ICMR '23"},"container-title":["Proceedings of the 2023 ACM International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3591106.3592253","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3591106.3592253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:30Z","timestamp":1750178250000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3591106.3592253"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,12]]},"references-count":32,"alternative-id":["10.1145\/3591106.3592253","10.1145\/3591106"],"URL":"https:\/\/doi.org\/10.1145\/3591106.3592253","relation":{},"subject":[],"published":{"date-parts":[[2023,6,12]]},"assertion":[{"value":"2023-06-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}