{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:56:39Z","timestamp":1777888599731,"version":"3.51.4"},"reference-count":49,"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":["62206135,62225604"],"award-info":[{"award-number":["62206135,62225604"]}],"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":["JCYJ20240813114237048"],"award-info":[{"award-number":["JCYJ20240813114237048"]}],"id":[{"id":"10.13039\/501100012226","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\/iccv51701.2025.00360","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3777-3786","source":"Crossref","is-referenced-by-count":1,"title":["Mind the Gap: Preserving and Compensating for the Modality Gap in CLIP-Based Continual Learning"],"prefix":"10.1109","author":[{"given":"Linlan","family":"Huang","sequence":"first","affiliation":[{"name":"CS Nankai University,VCIP"}]},{"given":"Xusheng","family":"Cao","sequence":"additional","affiliation":[{"name":"CS Nankai University,VCIP"}]},{"given":"Haori","family":"Lu","sequence":"additional","affiliation":[{"name":"CS Nankai University,VCIP"}]},{"given":"Yifan","family":"Meng","sequence":"additional","affiliation":[{"name":"CS Nankai University,VCIP"}]},{"given":"Fei","family":"Yang","sequence":"additional","affiliation":[{"name":"NKIARI,Shenzhen,Futian"}]},{"given":"Xialei","family":"Liu","sequence":"additional","affiliation":[{"name":"NKIARI,Shenzhen,Futian"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw53098.2021.00393"},{"issue":"7","key":"ref3","first-page":"33663385","article-title":"A continual learning survey: Defying forgetting in classification tasks","volume":"44","author":"De Lange","year":"2021","journal-title":"IEEE TPAMI"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00907"},{"key":"ref6","article-title":"Mitigate the gap: Investigating approaches for improving cross-modal alignment in clip","author":"Eslami","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"It\u2019s not a modality gap: Characterizing and addressing the contrastive gap","author":"Fahim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"issue":"2","key":"ref9","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00297"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72949-2_13"},{"key":"ref12","article-title":"Clap4clip: Continual learning with probabilistic finetuning for vision-language models","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Jha","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref14","volume-title":"Learning multiple layers of features from tiny images.","author":"Krizhevsky","year":"2009"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00642"},{"key":"ref16","article-title":"Unbiased regionlanguage alignment for open-vocabulary dense prediction","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"28243","article-title":"Cascade-CLIP: Cascaded visionlanguage embeddings alignment for zero-shot semantic segmentation","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Li","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1280"},{"key":"ref20","article-title":"Gradient episodic memory for continual learning","volume":"30","author":"Lopez-Paz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_22"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3213473"},{"key":"ref23","article-title":"An empirical investigation of the role of pre-training in lifelong learning","author":"Mehta","year":"2021","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Cross the gap: Exposing the intra-modal misalignment in clip via modality inversion","author":"Mistretta","year":"2025","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01146"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01931"},{"key":"ref30","article-title":"Clip model is an efficient continual learner","author":"Thengane","year":"2022","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00568-3"},{"key":"ref32","first-page":"398","article-title":"Foster: Feature boosting and compression for classincremental learning","volume-title":"ECCV","author":"Wang","year":"2022"},{"key":"ref33","article-title":"Memory replay with data compression for continual learning","volume-title":"International Conference on Learning Representations","author":"Wang","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_36"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00938"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00938"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00303"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02587"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02191"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01750"},{"key":"ref42","article-title":"A large-scale study of representation learning with the visual task adaptation benchmark","author":"Zhai","year":"2019","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01754"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093365"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3449109"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01752"},{"key":"ref47","first-page":"1645","article-title":"Cotransport for class-incremental learning","author":"Zhou","year":"2021","journal-title":"ACM MM"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02218-0"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3540889"}],"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\/11444362.pdf?arnumber=11444362","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:51:35Z","timestamp":1777611095000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444362\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00360","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}