{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T05:29:43Z","timestamp":1785389383170,"version":"3.55.0"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62101453"],"award-info":[{"award-number":["62101453"]}],"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":["62201467"],"award-info":[{"award-number":["62201467"]}],"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":["62176198"],"award-info":[{"award-number":["62176198"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2021A1515110544"],"award-info":[{"award-number":["2021A1515110544"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Basic Research Program of Shaanxi","award":["2022JQ-686"],"award-info":[{"award-number":["2022JQ-686"]}]},{"name":"Natural Science Basic Research Program of Shaanxi","award":["2019JQ-158"],"award-info":[{"award-number":["2019JQ-158"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2022TQ0260"],"award-info":[{"award-number":["2022TQ0260"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young Talent Fund of Xi'an Association for Science and Technology","award":["959202313088"],"award-info":[{"award-number":["959202313088"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3291588","type":"journal-article","created":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T18:17:51Z","timestamp":1688408271000},"page":"2056-2068","source":"Crossref","is-referenced-by-count":80,"title":["Dual Modality Prompt Tuning for Vision-Language Pre-Trained Model"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6021-8261","authenticated-orcid":false,"given":"Yinghui","family":"Xing","sequence":"first","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qirui","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4603-847X","authenticated-orcid":false,"given":"De","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Telecommunications Engineering, Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3429-576X","authenticated-orcid":false,"given":"Shizhou","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8710-5520","authenticated-orcid":false,"given":"Guoqiang","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9218-9132","authenticated-orcid":false,"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2977-8057","authenticated-orcid":false,"given":"Yanning","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, 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.","author":"Radford","year":"2021"},{"key":"ref2","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01101"},{"key":"ref4","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"Proc. Mach. Learn. Healthcare Conf.","author":"Zhang","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00324"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref12","first-page":"1","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3227416"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547851"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3549201"},{"key":"ref20","article-title":"Clipcap: Clip prefix for image captioning","author":"Mokady","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"ref25","article-title":"Exploring visual prompts for adapting large-scale models","author":"Bahng","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"ref28","article-title":"Neural prompt search","author":"Zhang","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"ref31","article-title":"Prompt tuning for generative multimodal pretrained models","author":"Yang","year":"2022"},{"key":"ref32","article-title":"CPT: Colorful prompt tuning for pre-trained vision-language models","author":"Yao","year":"2021"},{"key":"ref33","first-page":"1","article-title":"Frustratingly simple contrastive prompt tuning for vision-language models","author":"Sahoo","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3007340"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2644866"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_41"},{"key":"ref37","first-page":"11285","article-title":"TinyTL: Reduce memory, not parameters for efficient on-device learning","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Cai","year":"2020"},{"key":"ref38","first-page":"506","article-title":"Learning multiple visual domains with residual adapters","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Rebuffi","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2993952"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3142955"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3233442"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3168146"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3001510"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3215310"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141886"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3158072"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref48","first-page":"21271","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Grill","year":"2020"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref50","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref51","first-page":"1","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":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref56","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref62","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref63","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht","year":"2019"},{"key":"ref64","first-page":"10506","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2019"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10171397.pdf?arnumber=10171397","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:08:41Z","timestamp":1706756921000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10171397\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3291588","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}