{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T07:11:10Z","timestamp":1778224270088,"version":"3.51.4"},"reference-count":113,"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\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2022ZD0114805"],"award-info":[{"award-number":["2022ZD0114805"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476123"],"award-info":[{"award-number":["62476123"]}],"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":["62376118"],"award-info":[{"award-number":["62376118"]}],"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":["62006112"],"award-info":[{"award-number":["62006112"]}],"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":["62250069"],"award-info":[{"award-number":["62250069"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2024300373"],"award-info":[{"award-number":["2024300373"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["14380021"],"award-info":[{"award-number":["14380021"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CCF-Tencent Rhino-Bird Open Research Fund","award":["RAGR20240101"],"award-info":[{"award-number":["RAGR20240101"]}]},{"name":"Collaborative Innovation Center of Novel Software Technology and Industrialization"},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science Project of Nanjing University"},{"DOI":"10.13039\/100010449","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010449","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Singapore"},{"name":"MOE AcRF Tier 2","award":["MOET2EP20221-0012"],"award-info":[{"award-number":["MOET2EP20221-0012"]}]},{"name":"NTU NAP"},{"name":"Industry Alignment Fund"},{"name":"Collaboration Projects (IAF-ICP) Funding Initiative","award":["RIE2020"],"award-info":[{"award-number":["RIE2020"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tpami.2025.3540889","type":"journal-article","created":{"date-parts":[[2025,2,11]],"date-time":"2025-02-11T18:25:08Z","timestamp":1739298308000},"page":"4489-4504","source":"Crossref","is-referenced-by-count":26,"title":["Learning Without Forgetting for Vision-Language Models"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7226-7773","authenticated-orcid":false,"given":"Da-Wei","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}]},{"given":"Yuanhan","family":"Zhang","sequence":"additional","affiliation":[{"name":"S-Lab, College of Computing and Data Science, Nanyang Technological University, Singapore"}]},{"given":"Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5075-8512","authenticated-orcid":false,"given":"Jingyi","family":"Ning","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1173-1880","authenticated-orcid":false,"given":"Han-Jia","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3533-2078","authenticated-orcid":false,"given":"De-Chuan","family":"Zhan","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4220-5958","authenticated-orcid":false,"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[{"name":"S-Lab, College of Computing and Data Science, Nanyang Technological University, Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3054925"},{"key":"ref2","article-title":"Revisiting meta-learning as supervised learning","author":"Chao","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2981604"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-023-3282-7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2994749"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01294-2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_37"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3057446"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3213473"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.08.002"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-023-2689-5"},{"key":"ref13","first-page":"40924","article-title":"Exploring diverse in-context configurations for image captioning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40231-1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_27"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01322"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_36"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01146"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/924"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref24","first-page":"16664","article-title":"AdaptFormer: Adapting vision transformers for scalable visual recognition","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref25","first-page":"109","article-title":"Scaling & shifting your features: A new baseline for efficient model tuning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lian"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref27","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":"ref28","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref29","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021"},{"key":"ref30","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01059"},{"key":"ref32","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01049"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref40","article-title":"PLOT: Prompt learning with optimal transport for vision-language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref41","first-page":"666","article-title":"M\u00e9moire sur la th\u00e9orie des d\u00e9blais et des remblais","author":"Monge","year":"1781","journal-title":"Histoire de l\u2019Acad\u00e9mie Royale des Sci. de Paris"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01435"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00267"},{"key":"ref44","article-title":"Visual classification via description from large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Menon"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3429383"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3317425"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01094"},{"key":"ref48","first-page":"11816","article-title":"Gradient based sample selection for online continual learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Aljundi"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_33"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01226"},{"key":"ref51","article-title":"Efficient lifelong learning with a-gem","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chaudhry"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_41"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3072041"},{"key":"ref54","first-page":"15920","article-title":"Dark experience for general continual learning: A strong, simple baseline","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Buzzega"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01158"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00672"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109561"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00367"},{"key":"ref59","first-page":"10744","article-title":"DDGR: Continual learning with deep diffusion-based generative replay","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gao"},{"key":"ref60","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_6"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00092"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00718"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01344"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_25"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_16"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16213"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"ref70","first-page":"3987","article-title":"Continual learning through synaptic intelligence","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zenke"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01151"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01622"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00701"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00067"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00303"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_23"},{"key":"ref77","article-title":"A model or 603 exemplars: Towards memory-efficient class-incremental learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou"},{"key":"ref78","article-title":"Lifelong learning with dynamically expandable networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yoon"},{"key":"ref79","first-page":"899","article-title":"Reinforced continual learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref80","article-title":"BEEF: Bi-compatible class-incremental learning via energy-based expansion and fusion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00907"},{"key":"ref82","first-page":"19153","article-title":"Task-aware orthogonal sparse network for exploring shared knowledge in continual learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hu"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00642"},{"key":"ref84","article-title":"Visual prompt tuning in null space for continual learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01088"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00164"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01055"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26216"},{"key":"ref89","first-page":"5682","article-title":"S-prompts learning with pre-trained transformers: An occam\u2019s razor for domain incremental learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"ref91","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liang"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref94","article-title":"A structured self-attentive sentence embedding","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02218-0"},{"key":"ref97","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref98","article-title":"The Caltech-UCSD Birds-200\u20132011 dataset","author":"Wah","year":"2011"},{"key":"ref99","first-page":"9448","article-title":"ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Barbu"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref101","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref105","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref106","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553517"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref110","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref113","article-title":"LAION-400M: Open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10990047\/10882940.pdf?arnumber=10882940","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T17:38:31Z","timestamp":1746725911000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10882940\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":113,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3540889","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}