{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T16:42:52Z","timestamp":1776789772511,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0117103"],"award-info":[{"award-number":["2022ZD0117103"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,30]]},"DOI":"10.1145\/3652583.3658054","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T06:30:40Z","timestamp":1717741840000},"page":"92-100","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Fine-grained Semantics-aware Representation Learning for Text-based Person Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8027-4287","authenticated-orcid":false,"given":"Di","family":"Wang","sequence":"first","affiliation":[{"name":"Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3035-835X","authenticated-orcid":false,"given":"Feng","family":"Yan","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8425-2963","authenticated-orcid":false,"given":"Yifeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8756-2027","authenticated-orcid":false,"given":"Lin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0382-2715","authenticated-orcid":false,"given":"Xiao","family":"Liang","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6033-4959","authenticated-orcid":false,"given":"Haodi","family":"Zhong","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6004-6471","authenticated-orcid":false,"given":"Ronghua","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shihezi University, Shihezi, China"}]}],"member":"320","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_2_1","volume-title":"RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search. arXiv preprint arXiv:2305.13653","author":"Bai Yang","year":"2023","unstructured":"Yang Bai, Min Cao, Daming Gao, Ziqiang Cao, Chen Chen, Zhenfeng Fan, Liqiang Nie, and Min Zhang. 2023. RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search. arXiv preprint arXiv:2305.13653 (2023)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_9"},{"key":"e_1_3_2_1_4_1","volume-title":"Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325","author":"Chen Xinlei","year":"2015","unstructured":"Xinlei Chen, Hao Fang, Tsung-Yi Lin, Ramakrishna Vedantam, Saurabh Gupta, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2015. Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)."},{"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":"10.1007\/978-3-030-58577-8_7"},{"key":"e_1_3_2_1_7_1","volume-title":"Dzmitry Bahdanau, and Yoshua Bengio.","author":"Cho Kyunghyun","year":"2014","unstructured":"Kyunghyun Cho, Bart Van Merri\u00ebnboer, Dzmitry Bahdanau, and Yoshua Bengio. 2014. On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014)."},{"key":"e_1_3_2_1_8_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_9_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_10_1","volume-title":"International conference on machine learning. PMLR, 1180--1189","author":"Ganin Yaroslav","year":"2015","unstructured":"Yaroslav Ganin and Victor Lempitsky. 2015. Unsupervised domain adaptation by backpropagation. In International conference on machine learning. PMLR, 1180--1189."},{"key":"e_1_3_2_1_11_1","volume-title":"Contextual non-local alignment over full-scale representation for text-based person search. arXiv preprint arXiv: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. arXiv preprint arXiv:2101.03036 (2021)."},{"key":"e_1_3_2_1_12_1","volume-title":"Generative adversarial nets. Advances in neural information processing systems","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. Advances in neural information processing systems, Vol. 27 (2014)."},{"key":"e_1_3_2_1_13_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_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_15_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_16_1","volume-title":"International conference on machine learning. PMLR, 4904--4916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision-language representation learning with noisy text supervision. In International conference on machine learning. PMLR, 4904--4916."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"e_1_3_2_1_18_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)."},{"key":"e_1_3_2_1_19_1","volume-title":"Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539","author":"Kiros Ryan","year":"2014","unstructured":"Ryan Kiros, Ruslan Salakhutdinov, and Richard S Zemel. 2014. Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 (2014)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"e_1_3_2_1_22_1","unstructured":"Yaowei Li Zimo Liu Wenming Yang Yaowei Wang Qingmin Liao et al. 2023. CLIP-based Synergistic Knowledge Transfer for Text-based Person Retrieval. arXiv preprint arXiv:2309.09496 (2023)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01524"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00190"},{"key":"e_1_3_2_1_25_1","volume-title":"Long short-term memory. Neural computation","author":"Short-Term Memory Long","year":"2010","unstructured":"Long Short-Term Memory. 2010. Long short-term memory. Neural computation, Vol. 9, 8 (2010), 1735--1780."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00970"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"e_1_3_2_1_28_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_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."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00591"},{"key":"e_1_3_2_1_31_1","volume-title":"Neural machine translation of rare words with subword units. arXiv preprint arXiv:1508.07909","author":"Sennrich Rico","year":"2015","unstructured":"Rico Sennrich, Barry Haddow, and Alexandra Birch. 2015. Neural machine translation of rare words with subword units. arXiv preprint arXiv:1508.07909 (2015)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01026"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","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":"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_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.77"},{"key":"e_1_3_2_1_37_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)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00715"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475434"},{"key":"e_1_3_2_1_40_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_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548166"},{"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\/ICCV.2019.00381"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"}],"event":{"name":"ICMR '24: International Conference on Multimedia Retrieval","location":"Phuket Thailand","acronym":"ICMR '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 2024 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658054","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652583.3658054","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T08:49:44Z","timestamp":1755766184000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658054"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":47,"alternative-id":["10.1145\/3652583.3658054","10.1145\/3652583"],"URL":"https:\/\/doi.org\/10.1145\/3652583.3658054","relation":{},"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"2024-06-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}