{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:22:46Z","timestamp":1777890166925,"version":"3.51.4"},"reference-count":89,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["U23A20382,62476123,62376118,62250069"],"award-info":[{"award-number":["U23A20382,62476123,62376118,62250069"]}],"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":["2024300373,14380021"],"award-info":[{"award-number":["2024300373,14380021"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2025M771535"],"award-info":[{"award-number":["2025M771535"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00317","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3314-3325","source":"Crossref","is-referenced-by-count":0,"title":["External Knowledge Injection for CLIP-Based Class-Incremental Learning"],"prefix":"10.1109","author":[{"given":"Da-Wei","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Nanjing University"}]},{"given":"Kai-Wen","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Nanjing University"}]},{"given":"Jingyi","family":"Ning","sequence":"additional","affiliation":[{"name":"Nanjing University,National Key Laboratory for Novel Software Technology"}]},{"given":"Han-Jia","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Nanjing University"}]},{"given":"Lijun","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Nanjing University"}]},{"given":"De-Chuan","family":"Zhan","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Nanjing University"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1201\/9781315373515-10"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01151"},{"key":"ref5","first-page":"11816","article-title":"Gradient based sample selection for online continual learning","author":"Aljundi","year":"2019","journal-title":"NeurIPS"},{"key":"ref6","first-page":"9448","article-title":"Objectnet: A large-scale bias-controlled dataset for pushing the limits of object recognition models","author":"Barbu","year":"2019","journal-title":"NeurIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_33"},{"key":"ref9","article-title":"Efficient lifelong learning with agem","author":"Chaudhry","year":"2018","journal-title":"ICLR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1212"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3057446"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16213"},{"key":"ref15","article-title":"An image is worth 16 x words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"ICLR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_6"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00907"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01294-2"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.4324\/9781410603494-35"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_25"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00092"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72949-2_13"},{"key":"ref26","volume-title":"Openclip","author":"Ilharco","year":"2021"},{"key":"ref27","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021","journal-title":"ICML"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01088"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref32","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009","journal-title":"Technical report"},{"key":"ref33","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02522"},{"key":"ref35","article-title":"Addressing imbalanced domain-incremental learning through dual-balance collaborative experts","author":"Li","year":"2025","journal-title":"ICML"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_37"},{"key":"ref37","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","author":"Liang","year":"2022","journal-title":"NeurIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01226"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00718"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01094"},{"key":"ref41","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv preprint arXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3213473"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9338-y"},{"key":"ref44","article-title":"Ranpac: Random projections and pre-trained models for continual learning","author":"McDonnell","year":"2023","journal-title":"NeurIPS"},{"key":"ref45","article-title":"Visual classification via description from large language models","author":"Menon","year":"2023","journal-title":"ICLR"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01344"},{"key":"ref47","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"NeurIPS"},{"issue":"3","key":"ref48","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10994-024-06662-4","article-title":"Adaptive adapter routing for long-tailed classincremental learning","volume":"114","author":"Qi","year":"2025","journal-title":"Machine Learning"},{"key":"ref49","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref50","first-page":"506","article-title":"Learning multiple visual domains with residual adapters","author":"Rebuffi","year":"2017","journal-title":"NIPS"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01622"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01146"},{"key":"ref54","first-page":"4080","article-title":"Prototypical networks for few-shot learning","author":"Snell","year":"2017","journal-title":"NIPS"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i19.34281"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_16"},{"issue":"11","key":"ref58","article-title":"Visualizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"JMLR"},{"key":"ref59","article-title":"The Caltech-UCSD Birds-200-2011 Dataset","author":"Wah","year":"2011","journal-title":"Technical Report CNS-TR-2011-001, California Institute of Technology"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_23"},{"key":"ref61","article-title":"BEEF: Bicompatible class-incremental learning via energy-based expansion and fusion","author":"Wang","year":"2023","journal-title":"ICLR"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00356"},{"key":"ref63","first-page":"5682","article-title":"S-prompts learning with pre-trained transformers: An occam\u2019s razor for domain incremental learning","author":"Wang","year":"2022","journal-title":"NeurIPS"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_36"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"ref66","article-title":"A hard-to-beat baseline for trainingfree clip-based adaptation","author":"Wang","year":"2024","journal-title":"ICLR"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref69","first-page":"899","article-title":"Reinforced continual learning","author":"Xu","year":"2018","journal-title":"NeurIPS"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00303"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00237"},{"key":"ref72","first-page":"40924","article-title":"Exploring diverse in-context configurations for image captioning","author":"Yang","year":"2023","journal-title":"NeurIPS"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02587"},{"key":"ref74","article-title":"Lifelong learning with dynamically expandable networks","author":"Yoon","year":"2018","journal-title":"ICLR"},{"key":"ref75","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02191"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00701"},{"key":"ref78","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref79","first-page":"3987","article-title":"Continual learning through synaptic intelligence","author":"Zenke","year":"2017","journal-title":"ICML"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01322"},{"key":"ref81","first-page":"61649","article-title":"Multi-layer rehearsal feature augmentation for classincremental learning","author":"Zheng","year":"2024","journal-title":"ICML"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00944"},{"key":"ref83","article-title":"A model or 603 exemplars: Towards memory-efficient class-incremental learning","author":"Zhou","year":"2023","journal-title":"ICLR"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02218-0"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01913"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3540889"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00581"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443325.pdf?arnumber=11443325","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:28:20Z","timestamp":1777613300000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443325\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":89,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00317","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}