{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T06:47:33Z","timestamp":1783579653802,"version":"3.55.0"},"reference-count":56,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00970","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10421-10431","source":"Crossref","is-referenced-by-count":3,"title":["Beyond Label Semantics:Language-Guided Action Anatomy for Few-Shot Action Recognition"],"prefix":"10.1109","author":[{"given":"Zefeng","family":"Qian","sequence":"first","affiliation":[{"name":"School of Information Science and Electronic Engineering, Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xincheng","family":"Yao","sequence":"additional","affiliation":[{"name":"School of Information Science and Electronic Engineering, Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifei","family":"Huang","sequence":"additional","affiliation":[{"name":"The University of Tokyo"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chongyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Electronic Engineering, Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangyong","family":"Ying","sequence":"additional","affiliation":[{"name":"E-surfing Vision Technology Co., Ltd"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Sun","sequence":"additional","affiliation":[{"name":"E-surfing Vision Technology Co., Ltd"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"154","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":"10.1109\/CVPR.2017.502"},{"key":"ref5","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.79"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413502"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01937"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128649"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.328"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_21"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02017-7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"ref16","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_27"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00509"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i17.34004"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00046"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612279"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3175923"},{"key":"ref25","first-page":"3","article-title":"Language models are few-shot learners","volume":"1","author":"Mann","year":"2020","journal-title":"arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658044"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00054"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2025.104322"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3586118"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"International conference on machine learning"},{"issue":"140","key":"ref31","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01103"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01107"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3361157"},{"key":"ref35","article-title":"Prototypical networks for few-shot learning","volume":"30","author":"Snell","year":"2017","journal-title":"NeurIPS"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191072"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00633"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01933"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01932"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3262670"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01917-4"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01727"},{"key":"ref44","article-title":"Few-shot action recognition with captioning foundation models","author":"Wang","year":"2023","journal-title":"arXiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3354104"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00628"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_3"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01769"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111902"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00167"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111902"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/181"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_18"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3179314"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_46"}],"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\/11444915.pdf?arnumber=11444915","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:14:55Z","timestamp":1777612495000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444915\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00970","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}