{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:30:06Z","timestamp":1777865406247,"version":"3.51.4"},"reference-count":57,"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":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376217,62273347,62301434"],"award-info":[{"award-number":["62376217,62273347,62301434"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.01189","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12800-12810","source":"Crossref","is-referenced-by-count":0,"title":["Learning to Generalize Without Bias for Open-Vocabulary Action Recognition"],"prefix":"10.1109","author":[{"given":"Yating","family":"Yu","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Congqi","family":"Cao","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanning","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"How to train your maml","volume-title":"International conference on learning representations","author":"Antoniou","year":"2018"},{"key":"ref2","article-title":"Devias: Learning disentangled video representations of action and scene for holistic video understanding","author":"Bae","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00467"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3461718"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681081"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.29007\/h68j"},{"key":"ref7","article-title":"Fitclip: Refining large-scale pretrained image-text models for zero-shot video understanding tasks","author":"Castro","year":"2022","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01787"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0878"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01768"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2828"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.187"},{"key":"ref14","first-page":"22158","article-title":"Comprehensive knowledge distillation with causal intervention","volume":"34","author":"Deng","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","article-title":"An image is worth 16 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25069-9_36"},{"key":"ref17","first-page":"1126","article-title":"Modelagnostic meta-learning for fast adaptation of deep networks","volume-title":"International conference on machine learning","author":"Finn","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00089"},{"key":"ref21","article-title":"Froster: Frozen clip is a strong teacher for open-vocabulary action recognition","volume-title":"International Conference on Learning Representations","author":"Huang","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2122"},{"key":"ref23","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01755"},{"key":"ref26","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11596"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01823"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00267"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17057"},{"key":"ref33","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref35","article-title":"On first-order meta-learning algorithms","author":"Nichol","year":"2018","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1919"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02544"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01820"},{"key":"ref39","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":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"ref41","article-title":"Fitnets: Hints for thin deep nets","author":"Romero","year":"2014","journal-title":"arXiv preprint"},{"key":"ref42","first-page":"31716","article-title":"Clipood: Generalizing clip to out-of-distributions","volume-title":"International Conference on Machine Learning","author":"Shu","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"issue":"11","key":"ref44","article-title":"Visualizing data using t -sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6069"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28347"},{"key":"ref47","article-title":"Actionclip: A new paradigm for video action recognition","author":"Wang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-023-00027-6"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02206"},{"key":"ref50","first-page":"3697836989","article-title":"Open-vclip: Transforming clip to an open-vocabulary video model via interpolated weight optimization","volume-title":"International Conference on Machine Learning","author":"Weng","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25386"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3357503"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_22"},{"key":"ref55","article-title":"Aim: Adapting image models for efficient video action recognition","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33050"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611903"}],"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\/11445436.pdf?arnumber=11445436","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:27:50Z","timestamp":1777530470000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445436\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01189","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}