{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:26:41Z","timestamp":1759332401918,"version":"3.37.3"},"reference-count":59,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T00:00:00Z","timestamp":1667174400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T00:00:00Z","timestamp":1667174400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation (NSF)","doi-asserted-by":"publisher","award":["OIA-1946391,NSF 1920920,NSF FAIN-2223793,NIH lR01CA277739"],"award-info":[{"award-number":["OIA-1946391,NSF 1920920,NSF FAIN-2223793,NIH lR01CA277739"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,31]]},"DOI":"10.1109\/ieeeconf56349.2022.10052051","type":"proceedings-article","created":{"date-parts":[[2023,3,7]],"date-time":"2023-03-07T18:41:29Z","timestamp":1678214489000},"page":"1326-1333","source":"Crossref","is-referenced-by-count":7,"title":["Contextual Explainable Video Representation: Human Perception-based Understanding"],"prefix":"10.1109","author":[{"given":"Khoa","family":"Vo","sequence":"first","affiliation":[{"name":"University of Arkansas,Dept. of CSCE,Fayetteville,AR,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kashu","family":"Yamazaki","sequence":"additional","affiliation":[{"name":"University of Arkansas,Dept. of CSCE,Fayetteville,AR,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Phong X.","family":"Nguyen","sequence":"additional","affiliation":[{"name":"FPT Software,AI Lab,Ho Chi Minh City,Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Phat","family":"Nguyen","sequence":"additional","affiliation":[{"name":"FPT Software,AI Lab,Ho Chi Minh City,Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Khoa","family":"Luu","sequence":"additional","affiliation":[{"name":"University of Arkansas,Dept. of CSCE,Fayetteville,AR,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ngan","family":"Le","sequence":"additional","affiliation":[{"name":"University of Arkansas,Dept. of CSCE,Fayetteville,AR,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09904-8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3099856"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"ref4","article-title":"Self-supervised learning via multi-transformation classification for action recognition","author":"Vu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3183112"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956634"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6815"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415101"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3110973"},{"key":"ref12","article-title":"Aei: Actors-environment interaction with adaptive attention for temporal action proposals generation","author":"Vo","year":"2021","journal-title":"BMVC"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01702-9"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00719"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.233"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25412"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00365"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298698"},{"journal-title":"THUMOS challenge: Action recognition with a large number of classes","year":"2014","author":"Jiang","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"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":"10.1609\/aaai.v35i3.16363"},{"key":"ref28","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS. Curran Associates, Inc."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_1"},{"key":"ref30","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69541-5_32"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_8"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01327"},{"key":"ref34","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"Simonyan","year":"2014","journal-title":"NIPS, ser. NIPS14"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref37","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"CVPR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897766"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01109"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.610"},{"key":"ref41","article-title":"Msr asia msm at activitynet challenge 2017: Trimmed action recognition, temporal action proposals and densecaptioning events in videos","author":"Yao","year":"2017","journal-title":"CVP RW"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.93"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_5"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2953187"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00372"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_32"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00194"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00055"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-021-10500-2"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref51","article-title":"COOT: cooperative hierarchical trans-former for video-text representation learning","author":"Ging","year":"2020","journal-title":"NIPS"},{"key":"ref52","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002","journal-title":"ACL"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.445"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_29"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00677"}],"event":{"name":"2022 56th Asilomar Conference on Signals, Systems, and Computers","start":{"date-parts":[[2022,10,31]]},"location":"Pacific Grove, CA, USA","end":{"date-parts":[[2022,11,2]]}},"container-title":["2022 56th Asilomar Conference on Signals, Systems, and Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10051833\/10051818\/10052051.pdf?arnumber=10052051","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T18:39:51Z","timestamp":1707849591000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10052051\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,31]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/ieeeconf56349.2022.10052051","relation":{},"subject":[],"published":{"date-parts":[[2022,10,31]]}}}