{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:58:33Z","timestamp":1783529913525,"version":"3.55.0"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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","doi-asserted-by":"publisher","award":["U20A20184"],"award-info":[{"award-number":["U20A20184"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tcsvt.2023.3262754","type":"journal-article","created":{"date-parts":[[2023,3,29]],"date-time":"2023-03-29T19:33:08Z","timestamp":1680118388000},"page":"5959-5972","source":"Crossref","is-referenced-by-count":7,"title":["Multi-Modal Multi-Grained Embedding Learning for Generalized Zero-Shot Video Classification"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1537-6468","authenticated-orcid":false,"given":"Mingyao","family":"Hong","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7517-3868","authenticated-orcid":false,"given":"Xinfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3954-2387","authenticated-orcid":false,"given":"Guorong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-296X","authenticated-orcid":false,"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01934"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2846664"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01030"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413517"},{"key":"ref14","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"arXiv 1212 0402"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0983-5"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.282"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2900134"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2908487"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.01.078"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00983"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2984666"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.288"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2022.102177"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.03.070"},{"key":"ref46","article-title":"Zero-shot learning by convex combination of semantic embeddings","author":"norouzi","year":"2013","journal-title":"arXiv 1312 5650"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298911"},{"key":"ref48","article-title":"GAN for vision, KG for relation: A two-stage deep network for zero-shot action recognition","author":"sun","year":"2021","journal-title":"arXiv 2105 11789"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00047"},{"key":"ref42","article-title":"Learning confidence for out-of-distribution detection in neural networks","author":"devries","year":"2018","journal-title":"arXiv 1802 04865"},{"key":"ref41","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2857768"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3015848"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S0923-5965(00)00011-4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539893"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2832602"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref40","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"arXiv 1706 03762"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/157"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.117"},{"key":"ref37","first-page":"1","article-title":"Visual categorization with bags of keypoints","volume":"1","author":"csurka","year":"2004","journal-title":"Proc Workshop Stat Learn Comput Vis (ECCV)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2969787"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_22"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.17"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2443558"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"907","DOI":"10.1109\/TMM.2005.854410","article-title":"A generic framework of user attention model and its application in video summarization","volume":"7","author":"ma","year":"2005","journal-title":"IEEE Trans Multimedia"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/0306-4573(88)90021-0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3208256"},{"key":"ref26","article-title":"Generative adversarial networks","author":"j goodfellow","year":"2014","journal-title":"arXiv 1406 2661"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00581"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2900171"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3050803"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3147902"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533149"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995353"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.476"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10269772\/10086663.pdf?arnumber=10086663","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T18:30:44Z","timestamp":1698085844000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10086663\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":57,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3262754","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}