{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:29:52Z","timestamp":1775190592504,"version":"3.50.1"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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","award":["61972188"],"award-info":[{"award-number":["61972188"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62122035"],"award-info":[{"award-number":["62122035"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tip.2022.3205216","type":"journal-article","created":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T19:35:05Z","timestamp":1663184105000},"page":"6097-6108","source":"Crossref","is-referenced-by-count":40,"title":["Conditional Feature Learning Based Transformer for Text-Based Person Search"],"prefix":"10.1109","volume":"31","author":[{"given":"Chenyang","family":"Gao","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5210-7585","authenticated-orcid":false,"given":"Guanyu","family":"Cai","sequence":"additional","affiliation":[{"name":"Tencent Youtu Laboratory, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4991-0596","authenticated-orcid":false,"given":"Xinyang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Tencent Youtu Laboratory, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1701-9141","authenticated-orcid":false,"given":"Feng","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering and the Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology, Shenzhen, China"}]},{"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent Youtu Laboratory, Shanghai, China"}]},{"given":"Yifei","family":"Gong","sequence":"additional","affiliation":[{"name":"Tencent Youtu Laboratory, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1749-3599","authenticated-orcid":false,"given":"Fangzhou","family":"Lin","sequence":"additional","affiliation":[{"name":"Graduate School of Information Sciences, Tohoku University, Sendai, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8132-9083","authenticated-orcid":false,"given":"Xing","family":"Sun","sequence":"additional","affiliation":[{"name":"Tencent Youtu Laboratory, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3449-5940","authenticated-orcid":false,"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093640"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1219"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00208"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3020383"},{"key":"ref6","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"arXiv:1810.04805","author":"Devlin","year":"2018"},{"key":"ref7","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","volume-title":"arXiv:1707.05612","author":"Faghri","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","article-title":"In defense of the triplet loss for person re-identification","volume-title":"arXiv:1703.07737","author":"Hermans","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6777"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00117"},{"key":"ref13","article-title":"Adam: A method for stochastic optimization","volume-title":"arXiv:1412.6980","author":"Kingma","year":"2014"},{"key":"ref14","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","volume-title":"arXiv:1411.2539","author":"Kiros","year":"2014"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3073718"},{"key":"ref18","article-title":"VisualBERT: A simple and performant baseline for vision and language","volume-title":"arXiv:1908.03557","author":"Harold Li","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.209"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350869"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00431"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.442"},{"key":"ref25","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"arXiv:1908.02265","author":"Lu","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00190"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2984883"},{"key":"ref28","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"arXiv:1409.1556","author":"Simonyan","year":"2014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.427"},{"key":"ref30","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"arXiv:1908.08530","author":"Su","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_30"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref33","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240552"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3123315"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2963957"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045079"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3026079"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.103"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00871"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413864"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2910414"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9626658\/09893017.pdf?arnumber=9893017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:12:36Z","timestamp":1705957956000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9893017\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/tip.2022.3205216","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}