{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:28:55Z","timestamp":1772908135824,"version":"3.50.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62072041"],"award-info":[{"award-number":["62072041"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3361157","type":"journal-article","created":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T18:47:30Z","timestamp":1706813250000},"page":"8395-8405","source":"Crossref","is-referenced-by-count":9,"title":["Commonsense Knowledge Prompting for Few-Shot Action Recognition in Videos"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7573-4279","authenticated-orcid":false,"given":"Yuheng","family":"Shi","sequence":"first","affiliation":[{"name":"Beijing Laboratory of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2056-6947","authenticated-orcid":false,"given":"Xinxiao","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing Laboratory of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4734-9639","authenticated-orcid":false,"given":"Hanxi","family":"Lin","sequence":"additional","affiliation":[{"name":"Beijing Laboratory of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4516-9729","authenticated-orcid":false,"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Rochester, Rochester, NY, USA"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"TARN: Temporal attentive relation network for few-shot and zero-shot action recognition","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Bishay","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01063"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_46"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_31"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00054"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00313"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00046"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref11","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref14","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cho","year":"2021"},{"key":"ref15","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Tsimpoukelli","year":"2021"},{"key":"ref16","article-title":"Actionclip: A new paradigm for video action recognition","author":"Wang","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00640"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20029"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2940684"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2877886"},{"key":"ref21","first-page":"1","article-title":"A closer look at few-shot video classification: A new baseline and benchmark","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Zhu","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02025"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00939"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20610"},{"key":"ref25","article-title":"Clip on wheels: Zero-shot object navigation as object localization and exploration","author":"Gadre","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-017-2390-9_10"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3007511"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01933"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00894"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01932"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_21"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref35","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00116-6"},{"key":"ref41","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"issue":"11","key":"ref42","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10418536.pdf?arnumber=10418536","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T08:00:49Z","timestamp":1722585649000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10418536\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3361157","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}