{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T15:48:24Z","timestamp":1783007304970,"version":"3.54.5"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"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":["NSFC 62222607"],"award-info":[{"award-number":["NSFC 62222607"]}],"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":["NSFC 62476188"],"award-info":[{"award-number":["NSFC 62476188"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Shanghai Municipal Science and Technology Major Project","doi-asserted-by":"publisher","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}],"id":[{"id":"10.13039\/501100001809","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":[[2025,6]]},"DOI":"10.1109\/tcsvt.2024.3524181","type":"journal-article","created":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T19:43:08Z","timestamp":1735587788000},"page":"5885-5899","source":"Crossref","is-referenced-by-count":6,"title":["M-Tuning: Prompt Tuning With Mitigated Label Bias in Open-Set Scenarios"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3764-2555","authenticated-orcid":false,"given":"Ning","family":"Liao","sequence":"first","affiliation":[{"name":"MoE Key Laboratory of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6337-5748","authenticated-orcid":false,"given":"Xiaopeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei Inc., Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6628-0370","authenticated-orcid":false,"given":"Min","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9639-7679","authenticated-orcid":false,"given":"Junchi","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref2","first-page":"1","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.256"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.173"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01349"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00241"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00361"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_29"},{"key":"ref9","article-title":"M2IOSR: Maximal mutual information open set recognition","author":"Sun","year":"2021","journal-title":"arXiv:2108.02373"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_38"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/469"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00438"},{"key":"ref13","first-page":"32","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045079"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_25"},{"key":"ref17","article-title":"Rethinking visual prompt learning as masked visual token modeling","author":"Liao","year":"2023","journal-title":"arXiv:2303.04998"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00414"},{"key":"ref21","article-title":"Unified vision and language prompt learning","author":"Zang","year":"2022","journal-title":"arXiv:2210.07225"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298799"},{"key":"ref23","article-title":"MaPLe: Multi-modal prompt learning","author":"Uzair Khattak","year":"2022","journal-title":"arXiv:2210.03117"},{"key":"ref24","article-title":"MAPL: Parameter-efficient adaptation of unimodal pre-trained models for vision-language few-shot prompting","author":"Ma\u00f1as","year":"2022","journal-title":"arXiv:2210.07179"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3339387"},{"key":"ref26","article-title":"ProTeCt: Prompt tuning for taxonomic open set classification","author":"Wu","year":"2023","journal-title":"arXiv:2306.02240"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02225"},{"key":"ref28","article-title":"Prompt tuning with soft context sharing for vision-language models","author":"Ding","year":"2022","journal-title":"arXiv:2208.13474"},{"key":"ref29","first-page":"15558","article-title":"K-LITE: Learning transferable visual models with external knowledge","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shen"},{"key":"ref30","first-page":"38","article-title":"Large-scale zero-shot image classification from rich and diverse textual descriptions","volume-title":"Proc. 3rd Workshop Beyond Vis. Lang., Integrating Real-World Knowl. (LANTERN)","author":"Bujwid"},{"key":"ref31","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3297086"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3327605"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-016-5610-8"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2707495"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_21"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_30"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3106743"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00860"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3343520"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01436"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02007"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3245584"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3268680"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref50","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":"ref51","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"issue":"7","key":"ref52","first-page":"3","article-title":"Tiny imagenet visual recognition challenge","volume":"7","author":"Le","year":"2015","journal-title":"CS 231N"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref54","article-title":"LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop","author":"Yu","year":"2015","journal-title":"arXiv:1506.03365"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00085"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00324"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.71"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref61","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht"},{"key":"ref62","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":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref64","first-page":"1","article-title":"Open-set recognition: A good closed-set classifier is all you need","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Vaze"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref67","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.","author":"Jia"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00017"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01515"},{"key":"ref70","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20081"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00264"},{"key":"ref73","first-page":"7068","article-title":"Exploring the limits of out-of-distribution detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Fort"},{"key":"ref74","first-page":"1","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hendrycks"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511998"},{"key":"ref76","article-title":"A unified survey on anomaly, novelty, open-set, and out of-distribution detection: Solutions and future challenges","volume":"2022","author":"Salehi","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291588"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3265842"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3310282"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548021"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11027896\/10818508.pdf?arnumber=10818508","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T17:55:11Z","timestamp":1749578111000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10818508\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":80,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3524181","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}