{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T19:44:14Z","timestamp":1792611854462,"version":"4.5.0"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62376004"],"award-info":[{"award-number":["62376004"]}],"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":["62102205"],"award-info":[{"award-number":["62102205"]}],"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","award":["2208085J18"],"award-info":[{"award-number":["2208085J18"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tcsvt.2024.3454366","type":"journal-article","created":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T18:32:43Z","timestamp":1725474763000},"page":"148-161","source":"Crossref","is-referenced-by-count":29,"title":["Pedestrian Attribute Recognition via CLIP-Based Prompt Vision-Language Fusion"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6117-6745","authenticated-orcid":false,"given":"Xiao","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiandong","family":"Jin","sequence":"additional","affiliation":[{"name":"Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, and the School of Artificial Intelligence, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7233-2739","authenticated-orcid":false,"given":"Chenglong","family":"Li","sequence":"additional","affiliation":[{"name":"Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, and the School of Artificial Intelligence, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8375-3590","authenticated-orcid":false,"given":"Jin","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6144-8931","authenticated-orcid":false,"given":"Cheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Video Investigation Detachment of Hefei Public Security Bureau, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108220"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3189027"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3204444"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299143"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.fcij.2018.10.003"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.212"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477680"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.65"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/441"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178144"},{"key":"ref15","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref16","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Kenton"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref19","article-title":"A richly annotated dataset for pedestrian attribute recognition","author":"Li","year":"2016","journal-title":"arXiv:1603.07054"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2878349"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654966"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.46"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_41"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19991"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.64"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01591-y"},{"key":"ref27","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3331841"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25152"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1410-8"},{"key":"ref35","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Harold Li","year":"2019","journal-title":"arXiv:1908.03557"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00249"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02558"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/88"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref43","article-title":"Point-bind & point-LLM: Aligning point cloud with multi-modality for 3D understanding, generation, and instruction following","author":"Guo","year":"2023","journal-title":"arXiv:2309.00615"},{"key":"ref44","first-page":"684","article-title":"LanguageBind: Extending video-language pretraining to n-modality by language-based semantic alignment","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Zhu"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00130"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ACPR.2015.7486476"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_42"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00082"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00510"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6883"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2982962"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00100"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108865"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07300-7"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.05.028"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3045286"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01499-z"},{"key":"ref60","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sutskever"},{"key":"ref61","article-title":"Rethinking of pedestrian attribute recognition: A reliable evaluation under zero-shot pedestrian identity setting","author":"Jia","year":"2021","journal-title":"arXiv:2107.03576"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3285411"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.129"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.219"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6925"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.450"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11229"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/102"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2839521"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240588"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2969189"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01174"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3253799"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105708"},{"key":"ref75","article-title":"LLaMA-adapter: Efficient fine-tuning of large language models with zero-initialized attention","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Zhang"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10857816\/10664464.pdf?arnumber=10664464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T05:46:16Z","timestamp":1738215976000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10664464\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":75,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3454366","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}