{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:02:26Z","timestamp":1783530146102,"version":"3.55.0"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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":["62071502"],"award-info":[{"award-number":["62071502"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Key Project of Peng Cheng Laboratory","award":["PCL2023A09"],"award-info":[{"award-number":["PCL2023A09"]}]},{"name":"Guangdong Excellent Youth Team Program","award":["2023B1515040025"],"award-info":[{"award-number":["2023B1515040025"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tcsvt.2024.3449109","type":"journal-article","created":{"date-parts":[[2024,8,23]],"date-time":"2024-08-23T18:04:17Z","timestamp":1724436257000},"page":"13152-13163","source":"Crossref","is-referenced-by-count":14,"title":["Continual Learning of Image Classes With Language Guidance From a Vision-Language Model"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7866-6377","authenticated-orcid":false,"given":"Wentao","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujun","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weizhuo","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6032-8548","authenticated-orcid":false,"given":"Qicheng","family":"Lao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9865-2212","authenticated-orcid":false,"given":"Yue","family":"Yu","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8327-0003","authenticated-orcid":false,"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8714-0369","authenticated-orcid":false,"given":"Ruixuan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","article-title":"Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection","author":"Liu","year":"2023","journal-title":"arXiv:2303.05499"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3154443"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3248089"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3263870"},{"key":"ref6","first-page":"1","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ouyang"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02448-8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IS48319.2020.9200182"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/s0079-7421(08)60536-8"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref11","first-page":"1","article-title":"Parameter-level soft-masking for continual learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Konishi"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3304567"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00088"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01718"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01927"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00092"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00303"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_36"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01146"},{"key":"ref22","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":"ref23","first-page":"1","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref24","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01322"},{"key":"ref26","first-page":"1","article-title":"Unifying importance based regularisation methods for continual learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Benzing"},{"key":"ref27","article-title":"Preserving earlier knowledge in continual learning with the help of all previous feature extractors","author":"Li","year":"2021","journal-title":"arXiv:2104.13614"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3417431"},{"key":"ref29","first-page":"1","article-title":"A model or 603 exemplars: Towards memory-efficient class-incremental learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhou"},{"key":"ref30","first-page":"1","article-title":"Dark experience for general continual learning: A strong, simple baseline","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Buzzega"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59710-8_17"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01560"},{"key":"ref33","article-title":"Class incremental learning with pre-trained vision-language models","author":"Liu","year":"2023","journal-title":"arXiv:2310.20348"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00356"},{"key":"ref35","article-title":"Learning without forgetting for vision-language models","author":"Zhou","year":"2023","journal-title":"arXiv:2305.19270"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00938"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01754"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3039522"},{"key":"ref41","first-page":"1","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref42","volume-title":"Introducing Chatgpt","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"ref44","first-page":"7480","article-title":"Scaling vision transformers to 22 billion parameters","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dehghani"},{"key":"ref45","article-title":"LCM-LoRA: A universal stable-diffusion acceleration module","author":"Luo","year":"2023","journal-title":"arXiv:2311.05556"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref47","volume-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM55620.2022.9995352"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-023-00005-y"},{"key":"ref52","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref53","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":"ref54","article-title":"CLIP model is an efficient continual learner","author":"Thengane","year":"2022","journal-title":"arXiv:2210.03114"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10811783\/10644076.pdf?arnumber=10644076","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,21]],"date-time":"2024-12-21T05:56:23Z","timestamp":1734760583000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10644076\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":56,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3449109","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}