{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T03:49:34Z","timestamp":1785296974714,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100017052","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. U21B2037, No. U22B2051, No. 62176222, No. 62176223, No. 62176226, No. 62072386, No. 62072387, No. 62072389, No. 62002305,No. 62272401"],"award-info":[{"award-number":["No. U21B2037, No. U22B2051, No. 62176222, No. 62176223, No. 62176226, No. 62072386, No. 62072387, No. 62072389, No. 62002305,No. 62272401"]}],"id":[{"id":"10.13039\/100017052","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science Fund for Distinguished Young Scholars","award":["No.62025603"],"award-info":[{"award-number":["No.62025603"]}]},{"name":"Natural Science Foundation of Fujian Province of China","award":["No.2021J01002, No.2022J06001"],"award-info":[{"award-number":["No.2021J01002, No.2022J06001"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["No.2023M732948"],"award-info":[{"award-number":["No.2023M732948"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["No.2022ZD0118201"],"award-info":[{"award-number":["No.2022ZD0118201"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611768","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"4157-4168","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":32,"title":["Beat: Bi-directional One-to-Many Embedding Alignment for Text-based Person Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8744-3423","authenticated-orcid":false,"given":"Yiwei","family":"Ma","sequence":"first","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3912-9306","authenticated-orcid":false,"given":"Xiaoshuai","family":"Sun","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9956-6308","authenticated-orcid":false,"given":"Jiayi","family":"Ji","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4355-5711","authenticated-orcid":false,"given":"Guannan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Contemporary Amperex Technology Co., Limited, Ningde, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6940-8384","authenticated-orcid":false,"given":"Weilin","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Contemporary Amperex Technology Co., Limited, Ningde, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9163-2932","authenticated-orcid":false,"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"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":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5056--5066","author":"Cascante-Bonilla Paola","year":"2022","unstructured":"Paola Cascante-Bonilla, Hui Wu, Letao Wang, Rogerio S Feris, and Vicente Ordonez. 2022. Simvqa: Exploring simulated environments for visual question answering. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5056--5066."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01452"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_4"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6631"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_10_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_11_1","doi-asserted-by":"publisher","DOI":"10.11834\/jig.220620"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00503"},{"key":"e_1_3_2_1_13_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_14_1","volume-title":"Jamie Ryan Kiros, and Sanja Fidler","author":"Faghri Fartash","year":"2017","unstructured":"Fartash Faghri, David J Fleet, Jamie Ryan Kiros, and Sanja Fidler. 2017. Vse: Improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612 (2017)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01748"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.329"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the International Conference on Machine Learning, ICML. 6373--6391","author":"Fei Hao","year":"2022","unstructured":"Hao Fei, Shengqiong Wu, Yafeng Ren, and Meishan Zhang. 2022. Matching Structure for Dual Learning. In Proceedings of the International Conference on Machine Learning, ICML. 6373--6391."},{"key":"e_1_3_2_1_18_1","volume-title":"Devise: A deep visual-semantic embedding model. Advances in neural information processing systems 26","author":"Frome Andrea","year":"2013","unstructured":"Andrea Frome, Greg S Corrado, Jon Shlens, Samy Bengio, Jeff Dean, Marc'Aurelio Ranzato, and Tomas Mikolov. 2013. Devise: A deep visual-semantic embedding model. Advances in neural information processing systems 26 (2013)."},{"key":"e_1_3_2_1_19_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_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475634"},{"key":"e_1_3_2_1_21_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_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 17980--17989","author":"Hu Xiaowei","year":"2022","unstructured":"Xiaowei Hu, Zhe Gan, Jianfeng Wang, Zhengyuan Yang, Zicheng Liu, Yumao Lu, and Lijuan Wang. 2022. Scaling Up Vision-Language Pre-Training for Image Captioning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 17980--17989."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3183434"},{"key":"e_1_3_2_1_26_1","volume-title":"Step-wise hierarchical alignment network for image-text matching. IJCAI","author":"Ji Zhong","year":"2021","unstructured":"Zhong Ji, Kexin Chen, and Haoran Wang. 2021. Step-wise hierarchical alignment network for image-text matching. IJCAI (2021)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00504"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6777"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01069"},{"key":"e_1_3_2_1_32_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_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"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","doi-asserted-by":"publisher","DOI":"10.1007\/s11192-020-03430-8"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350869"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350991"},{"key":"e_1_3_2_1_40_1","volume-title":"Knowing what it is: Semantic-enhanced Dual Attention Transformer","author":"Ma Yiwei","year":"2022","unstructured":"Yiwei Ma, Jiayi Ji, Xiaoshuai Sun, Yiyi Zhou, Yongjian Wu, Feiyue Huang, and Rongrong Ji. 2022. Knowing what it is: Semantic-enhanced Dual Attention Transformer. IEEE Transactions on Multimedia (2022), 1--1. https:\/\/doi.org\/10. 1109\/TMM.2022.3164787"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.13"},{"key":"e_1_3_2_1_43_1","volume-title":"Learning Granularity-Unified Representations for Text-to-Image Person Re-identification. arXiv preprint arXiv:2207.07802","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. arXiv preprint arXiv:2207.07802 (2022)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"e_1_3_2_1_45_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Chengji Wang Zhiming Luo Yaojin Lin and Shaozi Li. 2021. Text-based Person Search via Multi-Granularity Embedding Learning.. In IJCAI. 1068--1074.","DOI":"10.24963\/ijcai.2021\/148"},{"key":"e_1_3_2_1_47_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_48_1","volume-title":"Towards real-time panoptic narrative grounding by an end-to-end grounding network. arXiv preprint arXiv:2301.03160","author":"Wang Haowei","year":"2023","unstructured":"Haowei Wang, Jiayi Ji, Yiyi Zhou, Yongjian Wu, and Xiaoshuai Sun. 2023. Towards real-time panoptic narrative grounding by an end-to-end grounding network. arXiv preprint arXiv:2301.03160 (2023)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_2"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093614"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105419"},{"key":"e_1_3_2_1_53_1","volume-title":"AMEN: Adversarial Multi-space Embedding Network for Text-Based Person Re-identification. In Chinese Conference on Pattern Recognition and Computer Vision (PRCV). Springer, 462--473","author":"Wang Zijie","year":"2021","unstructured":"Zijie Wang, Jingyi Xue, Aichun Zhu, Yifeng Li, Mingyi Zhang, and Chongliang Zhong. 2021. AMEN: Adversarial Multi-space Embedding Network for Text-Based Person Re-identification. In Chinese Conference on Pattern Recognition and Computer Vision (PRCV). Springer, 462--473."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108891"},{"key":"e_1_3_2_1_55_1","volume-title":"CAIBC: Capturing All-round Information Beyond Color for Text-based Person Retrieval. arXiv preprint arXiv:2209.05773","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. arXiv preprint arXiv:2209.05773 (2022)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548166"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JEI.29.4.043028"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00016"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00165"},{"key":"e_1_3_2_1_60_1","volume-title":"Mining False Positive Examples for Text-Based Person Re-identification. arXiv preprint arXiv:2303.08466","author":"Xu Wenhao","year":"2023","unstructured":"Wenhao Xu, Zhiyin Shao, and Changxing Ding. 2023. Mining False Positive Examples for Text-Based Person Re-identification. arXiv preprint arXiv:2303.08466 (2023)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413864"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611768","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611768","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:12:41Z","timestamp":1755821561000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611768"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":65,"alternative-id":["10.1145\/3581783.3611768","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611768","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}