{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T15:35:11Z","timestamp":1757777711797,"version":"3.37.3"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003452","name":"Innovation and Technology Commission of the Hong Kong SAR Government","doi-asserted-by":"publisher","award":["K-ZM3F"],"award-info":[{"award-number":["K-ZM3F"]}],"id":[{"id":"10.13039\/501100003452","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tnnls.2022.3202835","type":"journal-article","created":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T19:48:38Z","timestamp":1663012118000},"page":"5211-5225","source":"Crossref","is-referenced-by-count":7,"title":["Holistic-Guided Disentangled Learning With Cross-Video Semantics Mining for Concurrent First-Person and Third-Person Activity Recognition"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3831-8893","authenticated-orcid":false,"given":"Tianshan","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2733-3617","authenticated-orcid":false,"given":"Rui","family":"Zhao","sequence":"additional","affiliation":[{"name":"Hisilicon Semiconductor Huawei Technologies, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenqi","family":"Jia","sequence":"additional","affiliation":[{"name":"College of Computing, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0422-8454","authenticated-orcid":false,"given":"Kin-Man","family":"Lam","sequence":"additional","affiliation":[{"name":"Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2551-4748","authenticated-orcid":false,"given":"Jun","family":"Kong","sequence":"additional","affiliation":[{"name":"Key Laboratory of Advanced Process Control for Light Industry, Ministry of Education, Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/CVPR.2013.352"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/tpami.2021.3058649"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1007\/978-3-030-01228-1_38"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/TPAMI.2020.2991965"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/tpami.2020.3015894"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/tnnls.2021.3105184"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/TNNLS.2020.2978942"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/TMM.2016.2626959"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/TCYB.2016.2519448"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.48550\/ARXIV.1212.0402"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ICCV.2011.6126543"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/CVPR.2016.288"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/CVPR.2019.00812"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/CVPR.2017.502"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/TPAMI.2018.2868668"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICCV.2019.00209"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/CVPR.2019.01019"},{"key":"ref18","article-title":"Attention is all we need: Nailing down object-centric attention for egocentric activity recognition","author":"Sudhakaran","year":"2018","journal-title":"arXiv:1807.11794"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/TPAMI.2016.2577031"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/ICCV.2015.510"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1007\/978-3-030-01267-0_19"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/CVPR.2018.00675"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref24","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Simonyan"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/CVPR.2018.00813"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/ICCV.2019.00630"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/CVPR.2016.209"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/CVPR.2016.319"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1609\/aaai.v34i07.6907"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.48550\/ARXIV.1706.03762"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1007\/978-3-030-58536-5_21"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1109\/CVPR46437.2021.01313"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/TNNLS.2020.2978613"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/CVPR46437.2021.01052"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1609\/aaai.v33i01.33015565"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1109\/ICCV.2019.00381"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1109\/CVPR.2014.183"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1109\/TPAMI.2020.3026079"},{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1109\/TNNLS.2020.3041018"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1145\/2998574"},{"doi-asserted-by":"publisher","key":"ref41","DOI":"10.1145\/2733373.2806216"},{"doi-asserted-by":"publisher","key":"ref42","DOI":"10.1109\/CVPR.2016.217"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref44","article-title":"Multi-moments in time: Learning and interpreting models for multi-action video understanding","author":"Monfort","year":"2019","journal-title":"arXiv:1911.00232"},{"doi-asserted-by":"publisher","key":"ref45","DOI":"10.1007\/978-3-030-58595-2_27"},{"doi-asserted-by":"publisher","key":"ref46","DOI":"10.1137\/0105003"},{"doi-asserted-by":"publisher","key":"ref47","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref48","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"doi-asserted-by":"publisher","key":"ref49","DOI":"10.1109\/ICCVW.2009.5457461"},{"doi-asserted-by":"publisher","key":"ref50","DOI":"10.1109\/CVPR.2019.01020"},{"doi-asserted-by":"publisher","key":"ref51","DOI":"10.1007\/978-3-030-58545-7_11"},{"doi-asserted-by":"publisher","key":"ref52","DOI":"10.1109\/CVPR42600.2020.00092"},{"doi-asserted-by":"publisher","key":"ref53","DOI":"10.1109\/ICCV48922.2021.01341"},{"doi-asserted-by":"publisher","key":"ref54","DOI":"10.1109\/CVPR.2017.365"},{"doi-asserted-by":"publisher","key":"ref55","DOI":"10.1007\/978-3-030-58452-8_5"},{"doi-asserted-by":"publisher","key":"ref56","DOI":"10.1109\/CVPR52688.2022.00300"},{"doi-asserted-by":"publisher","key":"ref57","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref58","article-title":"More is less: Learning efficient video representations by big-little network and depthwise temporal aggregation","author":"Fan","year":"2019","journal-title":"arXiv:1912.00869"},{"doi-asserted-by":"publisher","key":"ref59","DOI":"10.1109\/CVPR46437.2021.00610"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10492491\/09887964.pdf?arnumber=9887964","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T19:43:10Z","timestamp":1712691790000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9887964\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":59,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3202835","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}