{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:59:46Z","timestamp":1777888786311,"version":"3.51.4"},"reference-count":66,"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\/501100002597","name":"Kyung Hee University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002597","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008122","name":"ITRC","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008122","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","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\/iccv51701.2025.01630","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17546-17556","source":"Crossref","is-referenced-by-count":0,"title":["ESSENTIAL: Episodic and Semantic Memory Integration for Video Class-Incremental Learning"],"prefix":"10.1109","author":[{"given":"Jongseo","family":"Lee","sequence":"first","affiliation":[{"name":"Kyung Hee University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyungho","family":"Bae","sequence":"additional","affiliation":[{"name":"Danggeun Market Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyle","family":"Min","sequence":"additional","affiliation":[{"name":"Intel Labs"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gyeong-Moon","family":"Park","sequence":"additional","affiliation":[{"name":"Korea University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinwoo","family":"Choi","sequence":"additional","affiliation":[{"name":"Kyung Hee University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00246"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref3","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref5","article-title":"Dark experience for general continual learning: a strong, simple baseline","author":"Buzzega","year":"2020","journal-title":"NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73390-1_22"},{"key":"ref9","article-title":"Why can\u2019t i dance in the mall? learning to mitigate scene bias in action recognition","author":"Choi","year":"2019","journal-title":"NeurIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref11","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-4328(01)00365-5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01055"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01563"},{"key":"ref18","article-title":"An empirical investigation of catastrophic forgetting in gradient-based neural networks","author":"Goodfellow","year":"2014","journal-title":"ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00092"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref23","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01361"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref26","article-title":"Cast: Crossattention in space and time for video action recognition","author":"Lee","year":"2023","journal-title":"NeurIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28117"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00319"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/s0079-7421(08)60536-8"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/S0926-6410(01)00120-3"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7299101"},{"key":"ref34","article-title":"St-adapter: Parameter-efficient image-to-video transfer learning","author":"Pan","year":"2022","journal-title":"NeurIPS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01344"},{"key":"ref36","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","author":"Patrick","year":"2021","journal-title":"NeurIPS"},{"key":"ref37","article-title":"Learning a condensed frame for memoryefficient video class-incremental learning","author":"Pei","year":"2022","journal-title":"NeurIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01096"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_31"},{"key":"ref40","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_15"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00058"},{"key":"ref44","article-title":"Two-stream convolutional networks for action recognition in videos","author":"Simonyan","year":"2014","journal-title":"NeurIPS"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01146"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02194"},{"key":"ref48","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","author":"Tong","year":"2022","journal-title":"NeurIPS"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"issue":"11","key":"ref51","first-page":"2579","article-title":"Visualizing data using t -sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"JMLR"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02319"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01845"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3111019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref56","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":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_36"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/S0028-3932(98)00044-X"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01322"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"ref62","article-title":"Rethinking spatiotemporal feature learning for video understanding","author":"Xie","year":"2018","journal-title":"ECCV"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00333"},{"key":"ref64","article-title":"Aim: Adapting image models for efficient video action recognition","author":"Yang","year":"2023","journal-title":"ICLR"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475265"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"}],"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\/11446034.pdf?arnumber=11446034","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:58:12Z","timestamp":1777611492000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446034\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01630","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}