{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:48Z","timestamp":1777865328129,"version":"3.51.4"},"reference-count":61,"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\/501100014188","name":"MSIT","doi-asserted-by":"publisher","award":["RS-2022-II220264\/50%,RS-2022-II220951\/20%,RS-2022II220612\/20%,RS-2020-II201373\/10%"],"award-info":[{"award-number":["RS-2022-II220264\/50%,RS-2022-II220951\/20%,RS-2022II220612\/20%,RS-2020-II201373\/10%"]}],"id":[{"id":"10.13039\/501100014188","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\/iccv51701.2025.01907","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20508-20518","source":"Crossref","is-referenced-by-count":0,"title":["Zero-Shot Compositional Video Learning with Coding Rate Reduction"],"prefix":"10.1109","author":[{"given":"Heeseok","family":"Jung","sequence":"first","affiliation":[{"name":"Hanyang University,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun-Hyeon","family":"Bak","sequence":"additional","affiliation":[{"name":"Hanyang University,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujin","family":"Jeong","sequence":"additional","affiliation":[{"name":"Hanyang University,Department of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gyugeun","family":"Lee","sequence":"additional","affiliation":[{"name":"Hanyang University,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinwoo","family":"Ahn","sequence":"additional","affiliation":[{"name":"Hanyang University,Department of Artificial Intelligence Application"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eun-Sol","family":"Kim","sequence":"additional","affiliation":[{"name":"Hanyang University,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref3","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"issue":"114","key":"ref6","first-page":"1","article-title":"Redunet: A white-box deep network from the principle of maximizing rate reduction","volume":"23","author":"Chan","year":"2022","journal-title":"Journal of machine learning research"},{"key":"ref7","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref11","article-title":"CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning","volume-title":"ICLR","author":"Girdhar","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/11564089_7"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01470"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","article-title":"beta-vae: Learning basic visual concepts with a constrained variational framework","volume-title":"ICLR (Poster)","volume":"3","author":"Higgins","year":"2017"},{"issue":"2","key":"ref17","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02266"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref20","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","first-page":"19849","article-title":"Compositional zeroshot learning via fine-grained dense feature composition","volume":"33","author":"Huynh","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02011"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01175"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00912"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00522"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.29"},{"key":"ref28","article-title":"Language-driven semantic segmentation","volume-title":"International Conference on Learning Representations","author":"Li","year":"2022"},{"key":"ref29","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72920-1_21"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01612"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref34","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref36","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02256"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02655"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1085"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00518"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00113"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.129"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00101"},{"key":"ref44","article-title":"Learning to compose soft prompts for compositional zero-shot learning","author":"Nayak","year":"2022","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00369"},{"key":"ref47","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":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01329"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1514"},{"key":"ref50","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01077"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00717"},{"key":"ref53","article-title":"Token statistics transformer: Lineartime attention via variational rate reduction","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Simplifying dino via coding rate regularization","author":"Wu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Aim: Adapting image models for efficient video action recognition","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","first-page":"9422","article-title":"Learning diverse and discriminative representations via the principle of maximal coding rate reduction","volume":"33","author":"Yu","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0413"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01774"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00174"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"}],"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\/11443308.pdf?arnumber=11443308","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:16:56Z","timestamp":1777529816000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443308\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01907","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}