{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T14:22:29Z","timestamp":1791814949764,"version":"4.3.4"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100017413","name":"Innovation Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017413","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]},{"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10688362","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Joint Visual-Textual Reasoning and Visible-Infrared Modality Alignment for Person Re-Identification"],"prefix":"10.1109","author":[{"given":"Na","family":"Jiang","sequence":"first","affiliation":[{"name":"Capital Normal University,Information Engineering College,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxuan","family":"Qiu","sequence":"additional","affiliation":[{"name":"Capital Normal University,Information Engineering College,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Song","sequence":"additional","affiliation":[{"name":"Capital Normal University,Information Engineering College,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Department of Automation,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiping","family":"Shi","sequence":"additional","affiliation":[{"name":"Capital Normal University,Information Engineering College,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Capital Normal University,Information Engineering College,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25226"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02118"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01786"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00214"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-020-02015-z"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02179"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00720"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327924"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"ref11","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy"},{"key":"ref12","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.575"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054775"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01391"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01876"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_28"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_22"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_27"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612297"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25273"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"issue":"86","key":"ref23","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10688362.pdf?arnumber=10688362","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:43:18Z","timestamp":1727764998000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10688362\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10688362","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}