{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:14:03Z","timestamp":1783692843157,"version":"3.55.0"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"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":["2018AAA0100400"],"award-info":[{"award-number":["2018AAA0100400"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071466"],"award-info":[{"award-number":["62071466"]}],"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":["62076242"],"award-info":[{"award-number":["62076242"]}],"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":["62376267"],"award-info":[{"award-number":["62376267"]}],"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":["61976208"],"award-info":[{"award-number":["61976208"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"InnoHK Project"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tcsvt.2023.3327605","type":"journal-article","created":{"date-parts":[[2023,10,25]],"date-time":"2023-10-25T18:07:59Z","timestamp":1698257279000},"page":"4653-4667","source":"Crossref","is-referenced-by-count":58,"title":["Pro-Tuning: Unified Prompt Tuning for Vision Tasks"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4370-1021","authenticated-orcid":false,"given":"Xing","family":"Nie","sequence":"first","affiliation":[{"name":"Department of State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bolin","family":"Ni","sequence":"additional","affiliation":[{"name":"Department of State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0610-907X","authenticated-orcid":false,"given":"Jianlong","family":"Chang","sequence":"additional","affiliation":[{"name":"Huawei Cloud and AI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7103-6321","authenticated-orcid":false,"given":"Gaofeng","family":"Meng","sequence":"additional","affiliation":[{"name":"Department of State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6748-6709","authenticated-orcid":false,"given":"Chunlei","family":"Huo","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2089-9733","authenticated-orcid":false,"given":"Shiming","family":"Xiang","sequence":"additional","affiliation":[{"name":"Department of State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7252-5047","authenticated-orcid":false,"given":"Qi","family":"Tian","sequence":"additional","affiliation":[{"name":"Huawei Cloud and AI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3201822"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956516"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298885"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3088545"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref7","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref8","first-page":"1565","article-title":"Learning imbalanced datasets with label-distribution-aware margin loss","volume-title":"Proc. NIPS","author":"Cao"},{"key":"ref9","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.295"},{"key":"ref11","first-page":"1","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018","journal-title":"OpenAI Blog"},{"issue":"8","key":"ref12","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"ref14","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. ICML","author":"Jia"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref17","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. ICML","author":"Li"},{"key":"ref18","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. ICML","author":"Touvron"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","first-page":"3320","article-title":"How transferable are features in deep neural networks?","volume-title":"Proc. NIPS","author":"Yosinski"},{"key":"ref21","first-page":"11285","article-title":"TinyTL: Reduce memory, not parameters for efficient on-device learning","volume-title":"Proc. NIPS","author":"Cai"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_41"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2900467"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3047140"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3059872"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2989308"},{"key":"ref27","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. ICML","author":"Houlsby"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.41"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00277"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2991171"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3001583"},{"key":"ref32","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume-title":"Proc. NIPS","author":"Tsimpoukelli"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3181604"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref37","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3245584"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01047"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref41","first-page":"16664","article-title":"AdaptFormer: Adapting vision transformers for scalable visual recognition","volume-title":"Proc. NIPS","author":"Chen"},{"key":"ref42","first-page":"1","article-title":"Learning multiple visual domains with residual adapters","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Rebuffi"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00847"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00872"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.549"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2004.383"},{"key":"ref50","first-page":"1","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume-title":"Proc. CVPR Workshop","author":"Khosla"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref53","first-page":"1","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"Proc. ICLR","author":"Hendrycks"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref62","first-page":"1","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref63","first-page":"1","article-title":"What makes instance discrimination good for transfer learning?","volume-title":"Proc. ICLR","author":"Zhao"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01173"},{"key":"ref65","article-title":"CLIP-adapter: Better vision-language models with feature adapters","author":"Gao","year":"2021","journal-title":"arXiv:2110.04544"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00511"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.385"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10550083\/10295530.pdf?arnumber=10295530","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T21:17:51Z","timestamp":1719350271000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10295530\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":71,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3327605","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}