{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T14:40:34Z","timestamp":1773931234105,"version":"3.50.1"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","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":[{"name":"National Key Research and Development Program of China","award":["2021YFE0205700"],"award-info":[{"award-number":["2021YFE0205700"]}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["JQ23016"],"award-info":[{"award-number":["JQ23016"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Development Fund of Macau","award":["0123\/2022\/A3"],"award-info":[{"award-number":["0123\/2022\/A3"]}]},{"name":"Science and Technology Development Fund of Macau","award":["0070\/2020\/AMJ"],"award-info":[{"award-number":["0070\/2020\/AMJ"]}]},{"name":"Science and Technology Development Fund of Macau","award":["0096\/2023\/RIA2"],"award-info":[{"award-number":["0096\/2023\/RIA2"]}]},{"name":"CCF-Zhipu AI Large Model Project","award":["202219"],"award-info":[{"award-number":["202219"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2054"],"award-info":[{"award-number":["U23B2054"]}],"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":["62276254"],"award-info":[{"award-number":["62276254"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"InnoHK program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2024.3521677","type":"journal-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:23:06Z","timestamp":1734981786000},"page":"198-208","source":"Crossref","is-referenced-by-count":2,"title":["Vision Transformer With Relation Exploration for Pedestrian Attribute Recognition"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1421-779X","authenticated-orcid":false,"given":"Hao","family":"Tan","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation Chinese Academy of Sciences (CASIA), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8501-4123","authenticated-orcid":false,"given":"Zichang","family":"Tan","sequence":"additional","affiliation":[{"name":"Sangfor Technologies Inc., Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6784-0934","authenticated-orcid":false,"given":"Dunfang","family":"Weng","sequence":"additional","affiliation":[{"name":"AI-PRIME, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7788-9368","authenticated-orcid":false,"given":"Ajian","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation Chinese Academy of Sciences (CASIA), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4735-2885","authenticated-orcid":false,"given":"Jun","family":"Wan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation Chinese Academy of Sciences (CASIA), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0791-189X","authenticated-orcid":false,"given":"Zhen","family":"Lei","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation Chinese Academy of Sciences (CASIA), Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2961-8096","authenticated-orcid":false,"given":"Stan Z.","family":"Li","sequence":"additional","affiliation":[{"name":"Westlake University, Zhejiang, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.51"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2919199"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6883"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01499-z"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.46"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.02.019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.51"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACPR.2015.7486476"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477680"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICB.2015.7139070"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.284"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.387"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.81"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486604"},{"key":"ref15","first-page":"1","article-title":"Localization guided learning for pedestrian attribute recognition","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Liu","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_42"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref18","first-page":"4997","article-title":"Weakly-supervised learning of mid-level features for pedestrian attribute recognition and localization","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Yu","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018634"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref21","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.65"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/441"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019275"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-022-00893-y"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3045286"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.05.028"},{"key":"ref28","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654966"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2878349"},{"key":"ref32","first-page":"166","volume-title":"Proc. IEEE\/CVF Winter Conf. Appl. Comput. Vis.","author":"Cormier","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.24"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000029664.99615.94"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref38","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00510"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2022.10.003"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3178144"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_33"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00580"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3055780"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00449"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00045"},{"key":"ref50","first-page":"1","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018","journal-title":"OpenAI Tech Rep."},{"issue":"8","key":"ref51","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref52","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/iros55552.2023.10342025"},{"key":"ref55","first-page":"1","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao","year":"2022"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475202"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00292"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3214768"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3226473"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3233774"},{"key":"ref62","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.06.006"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.133"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/341"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00100"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref70","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00104"},{"key":"ref73","article-title":"Rethinking of pedestrian attribute recognition: A reliable evaluation under zero-shot pedestrian identity setting","author":"Jia","year":"2021"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01591-y"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10812850.pdf?arnumber=10812850","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:56:30Z","timestamp":1737399390000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10812850\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3521677","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}