{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:56:37Z","timestamp":1780764997547,"version":"3.54.1"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012335","name":"National Defense Basic Scientific Research Program of China","doi-asserted-by":"publisher","award":["JCKY2020903B002"],"award-info":[{"award-number":["JCKY2020903B002"]}],"id":[{"id":"10.13039\/501100012335","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306294"],"award-info":[{"award-number":["62306294"]}],"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":["2308085QF222"],"award-info":[{"award-number":["2308085QF222"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M743385"],"award-info":[{"award-number":["2023M743385"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004739","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":[[2024,11]]},"DOI":"10.1109\/tcsvt.2024.3424566","type":"journal-article","created":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T17:52:50Z","timestamp":1720461170000},"page":"11579-11591","source":"Crossref","is-referenced-by-count":25,"title":["Multi-Modal Attribute Prompting for Vision-Language Models"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3791-3984","authenticated-orcid":false,"given":"Xin","family":"Liu","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4380-5573","authenticated-orcid":false,"given":"Jiamin","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenfei","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Sangfor Technologies Inc., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1856-9564","authenticated-orcid":false,"given":"Tianzhu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Jia"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3137430"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3039522"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3392831"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3253548"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3391304"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3397997"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3315133"},{"key":"ref10","article-title":"Three ways to improve feature alignment for open vocabulary detection","author":"Arandjelovi\u0107","year":"2023","journal-title":"arXiv:2303.13518"},{"key":"ref11","first-page":"15946","article-title":"Multi-modal classifiers for open-vocabulary object detection","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kaul"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref13","article-title":"Object2Scene: Putting objects in context for open-vocabulary 3D detection","author":"Zhu","year":"2023","journal-title":"arXiv:2309.09456"},{"key":"ref14","first-page":"68367","article-title":"OpenMask3D: Open-vocabulary 3D instance segmentation","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Takmaz"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3245584"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02011"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00135"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref24","article-title":"Text descriptions are compressive and invariant representations for visual learning","author":"Feng","year":"2023","journal-title":"arXiv:2307.04317"},{"key":"ref25","article-title":"Visual classification via description from large language models","volume-title":"Proc. 11th Int. Conf. Learn. Represent. (ICLR)","author":"Menon"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00034"},{"key":"ref27","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref28","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2303"},{"key":"ref29","article-title":"A survey of large language models","author":"Xin Zhao","year":"2023","journal-title":"arXiv:2303.18223"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-71050-9","volume-title":"Optimal Transport: Old and New","volume":"338","author":"Villani","year":"2009"},{"key":"ref31","first-page":"2292","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"26","author":"Cuturi"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3038720"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref36","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021","journal-title":"arXiv:2111.11432"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995754"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3088545"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3282777"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3196550"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3193612"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2920783"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3241651"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00324"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.576"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2023.08.012"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref50","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":"ref51","article-title":"Learning visual attributes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"20","author":"Ferrari"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.48"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01873-z"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0695-z"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.127"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12295"},{"key":"ref57","first-page":"5720","article-title":"Learning attribute-aware hash codes for large-scale fine-grained image retrieval","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Wei"},{"key":"ref58","first-page":"64681","article-title":"Learning to parameterize visual attributes for open-set fine-grained retrieval","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref59","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. NIPS","author":"Khosla"},{"key":"ref60","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref61","first-page":"12116","article-title":"Do vision transformers see like convolutional neural networks?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Raghu"},{"key":"ref62","article-title":"From CLIP to DINO: Visual encoders shout in multi-modal large language models","author":"Jiang","year":"2023","journal-title":"arXiv:2310.08825"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.328"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref70","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv:1306.5151"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref76","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht"},{"key":"ref77","first-page":"10506","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Wang"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref79","article-title":"Qwen technical report","volume-title":"arXiv:2309.16609","author":"Bai","year":"2023"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10768851\/10587284.pdf?arnumber=10587284","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T19:49:38Z","timestamp":1732736978000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10587284\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":79,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3424566","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}