{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:05:07Z","timestamp":1780765507318,"version":"3.54.1"},"reference-count":52,"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":["62372133,62125201,U24B20174"],"award-info":[{"award-number":["62372133,62125201,U24B20174"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017607","name":"Shenzhen Fundamental Research Program","doi-asserted-by":"publisher","award":["JCYJ20220818102415032"],"award-info":[{"award-number":["JCYJ20220818102415032"]}],"id":[{"id":"10.13039\/501100017607","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\/iccv51701.2025.01053","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-10","source":"Crossref","is-referenced-by-count":2,"title":["D\n                    <sup>2<\/sup>\n                    ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-Shot Action Recognition"],"prefix":"10.1109","author":[{"given":"Wenjie","family":"Pei","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qizhong","family":"Tan","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangming","family":"Lu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiandong","family":"Tian","sequence":"additional","affiliation":[{"name":"Shenyang Institute of Automation, Chinese Academy of Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"TARN: Temporal attentive relation network for few-shot and zero-shot action recognition","author":"Bishay","year":"2019","journal-title":"BMVC"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681081"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01063"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1212"},{"key":"ref5","first-page":"5","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413502"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref9","first-page":"1, 3","article-title":"Towards a unified view of parameter-efficient transfer learning","author":"He","year":"2021","journal-title":"ICLR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","author":"Houlsby","year":"2019","journal-title":"ICML"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_21"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref14","first-page":"5, 6","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_27"},{"key":"ref17","first-page":"4","article-title":"Uniformer: Unified transformer for efficient spatio-temporal representation learning","author":"Li","year":"2022","journal-title":"ICLR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20029"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_27"},{"key":"ref21","first-page":"1, 3, 6, 7","article-title":"ST-Adapter: Parameter-efficient image-to-video transfer learning","author":"Pan","year":"2022","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00219"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00054"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref25","first-page":"2","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"Simonyan","year":"2014","journal-title":"NeurIPS"},{"key":"ref26","first-page":"5","article-title":"Prototypical networks for few-shot learning","volume":"30","author":"Snell","year":"2017","journal-title":"NeurIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01933"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.510"},{"key":"ref30","first-page":"3","article-title":"Matching networks for one shot learning","volume":"29","author":"Vinyals","year":"2016","journal-title":"NeurIPS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.121"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01932"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01727"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01917-4"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00628"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_3"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00894"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01769"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref41","first-page":"6","article-title":"Multimodal adaptation of clip for few-shot action recognition","author":"Xing","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25403"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00167"},{"key":"ref44","first-page":"1, 3, 6, 7","article-title":"AIM: Adapting image models for efficient video action recognition","author":"Yang","year":"2022","journal-title":"ICLR"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_31"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/181"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612192"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_18"},{"key":"ref49","first-page":"1024","article-title":"Saliency-guided finegrained temporal mask learning for few-shot action recognition","author":"Zheng","year":"2024","journal-title":"ACMMM"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_46"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3007511"}],"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\/11443516.pdf?arnumber=11443516","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:08:56Z","timestamp":1777612136000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443516\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01053","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}