{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T17:27:15Z","timestamp":1783099635190,"version":"3.54.6"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["U20B2070"],"award-info":[{"award-number":["U20B2070"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["61832016"],"award-info":[{"award-number":["61832016"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L221013"],"award-info":[{"award-number":["L221013"]}],"id":[{"id":"10.13039\/501100004826","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":[[2023,9]]},"DOI":"10.1109\/tcsvt.2023.3245584","type":"journal-article","created":{"date-parts":[[2023,2,16]],"date-time":"2023-02-16T23:10:30Z","timestamp":1676589030000},"page":"4616-4629","source":"Crossref","is-referenced-by-count":66,"title":["Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0502-3960","authenticated-orcid":false,"given":"Chengcheng","family":"Ma","sequence":"first","affiliation":[{"name":"National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Alibaba DAMO Academy, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3709-6216","authenticated-orcid":false,"given":"Jiankang","family":"Deng","sequence":"additional","affiliation":[{"name":"Huawei Inc., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4831-9451","authenticated-orcid":false,"given":"Lingxi","family":"Xie","sequence":"additional","affiliation":[{"name":"Huawei Inc., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6502-145X","authenticated-orcid":false,"given":"Weiming","family":"Dong","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, 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"},{"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"},{"key":"ref3","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv:2108.07258"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3137430"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3039522"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref10","article-title":"Prompt-aligned gradient for prompt tuning","author":"Zhu","year":"2022","journal-title":"arXiv:2205.14865"},{"key":"ref11","article-title":"Variational prompt tuning improves generalization of vision-language models","author":"Derakhshani","year":"2022","journal-title":"arXiv:2210.02390"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1996.8.7.1341"},{"key":"ref13","first-page":"1256","article-title":"Gradient starvation: A learning proclivity in neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Pezeshki"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3038720"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3169693"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01512"},{"key":"ref19","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Tsimpoukelli"},{"key":"ref20","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref21","article-title":"Local-global context aware transformer for language-guided video segmentation","author":"Liang","year":"2022","journal-title":"arXiv:2203.09773"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01503"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"ref24","article-title":"Class-aware visual prompt tuning for vision-language pre-trained model","author":"Xing","year":"2022","journal-title":"arXiv:2208.08340"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.763"},{"key":"ref26","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yu"},{"key":"ref27","article-title":"Tip-adapter: Training-free CLIP-adapter for better vision-language modeling","author":"Zhang","year":"2021","journal-title":"arXiv:2111.03930"},{"key":"ref28","article-title":"CPT: Colorful prompt tuning for pre-trained vision-language models","author":"Yao","year":"2021","journal-title":"arXiv:2109.11797"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref30","article-title":"Neural prompt search","author":"Zhang","year":"2022","journal-title":"arXiv:2206.04673"},{"key":"ref31","first-page":"5637","article-title":"WILDS: A benchmark of in-the-wild distribution shifts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koh"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2981604"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2022.3178128"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3195549"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3152615"},{"key":"ref36","first-page":"1","article-title":"Free lunch for few-shot learning: Distribution calibration","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yang"},{"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\/CVPR.2016.90"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s13373-017-0101-1"},{"key":"ref42","first-page":"1","article-title":"Stein variational gradient descent as gradient flow","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Liu"},{"key":"ref43","first-page":"1","article-title":"Maximum mean discrepancy gradient flow","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Arbel"},{"key":"ref44","first-page":"4104","article-title":"Sliced-Wasserstein flows: Nonparametric generative modeling via optimal transport and diffusions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liutkus"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3178101"},{"key":"ref46","first-page":"8572","article-title":"Wide neural networks of any depth evolve as linear models under gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lee"},{"key":"ref47","first-page":"1","article-title":"How many degrees of freedom do we need to train deep networks: A loss landscape perspective","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Larsen"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref53","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv:1306.5151"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref58","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht"},{"key":"ref59","first-page":"1","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Wang"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref62","article-title":"PromptDet: Expand your detector vocabulary with uncurated images","author":"Feng","year":"2022","journal-title":"arXiv:2203.16513"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref65","article-title":"A simple baseline for open-vocabulary semantic segmentation with pre-trained vision-language model","author":"Xu","year":"2021","journal-title":"arXiv:2112.14757"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref67","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Cheng"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10241245\/10045664.pdf?arnumber=10045664","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T03:09:09Z","timestamp":1710385749000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10045664\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":67,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3245584","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}