{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:18:22Z","timestamp":1774419502386,"version":"3.50.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889907","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Relation-aware Semantic Alignment Network for Text-to-Image Person Retrieval"],"prefix":"10.1109","author":[{"given":"Yong","family":"Wu","sequence":"first","affiliation":[{"name":"Anhui Normal University,School of Computer and Information,Wuhu,China"}]},{"given":"Rongxi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Anhui Normal University,School of Computer and Information,Wuhu,China"}]},{"given":"Hongchao","family":"Li","sequence":"additional","affiliation":[{"name":"Anhui Normal University,School of Computer and Information,Wuhu,China"}]},{"given":"Ze","family":"Zhou","sequence":"additional","affiliation":[{"name":"Anhui Normal University,School of Computer and Information,Wuhu,China"}]},{"given":"Feifei","family":"Wei","sequence":"additional","affiliation":[{"name":"Anhui Normal University,School of Computer and Information,Wuhu,China"}]},{"given":"Min","family":"Li","sequence":"additional","affiliation":[{"name":"Guangxi Academy of Agricultural Sciences,Nanning,China"}]},{"given":"Guodui","family":"He","sequence":"additional","affiliation":[{"name":"China Communications Service Guangxi Technical Service Branch,Nanning,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327924"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3337653"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27801"},{"key":"ref6","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref7","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations (ICLR)","author":"Dosovitskiy"},{"key":"ref8","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3410129"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25072-9_42"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01026"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02226"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-53305-1_16"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445963"},{"key":"ref16","article-title":"Prompt decoupling for text-to-image person re-identification","author":"Li","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02078"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3355644"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02094-8"},{"key":"ref20","article-title":"Semantically self-aligned network for text-to-image part-aware person re-identification","author":"Ding","year":"2021"},{"key":"ref21","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02568"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889907.pdf?arnumber=10889907","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:11Z","timestamp":1774416191000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889907\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889907","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}