{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T08:06:50Z","timestamp":1768723610017,"version":"3.49.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"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":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1109\/tcsvt.2021.3070688","type":"journal-article","created":{"date-parts":[[2021,4,2]],"date-time":"2021-04-02T19:58:25Z","timestamp":1617393505000},"page":"976-991","source":"Crossref","is-referenced-by-count":12,"title":["FactorNet: Holistic Actor, Object, and Scene Factorization for Action Recognition in Videos"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7389-6168","authenticated-orcid":false,"given":"Nitika","family":"Nigam","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2801-0687","authenticated-orcid":false,"given":"Tanima","family":"Dutta","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3207-1340","authenticated-orcid":false,"given":"Hari Prabhat","family":"Gupta","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1088\/1757-899X\/569\/3\/032035"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7012"},{"key":"ref4","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. NIPS","author":"Simonyan"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.522"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2712608"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00054"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_18"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018401"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00807"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00034"},{"key":"ref23","first-page":"34","article-title":"Attentional pooling for action recognition","volume-title":"Proc. NIPS","author":"Girdhar"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00817"},{"key":"ref26","article-title":"PIC: Permutation invariant convolution for recognizing long-range activities","author":"Hussein","year":"2020","journal-title":"arXiv:2003.08275"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00878"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3013518"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2019.00278"},{"key":"ref33","first-page":"754","article-title":"FishNet: A versatile backbone for image, region, and pixel level prediction","volume-title":"Proc. NIPS","author":"Sun"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref35","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. ICML","author":"Ioffe"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1080\/135062800394667"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00872"},{"key":"ref38","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume-title":"Proc. NIPS","author":"Xingjian"},{"key":"ref39","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume-title":"Proc. ICML","author":"Xu"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2576761"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref42","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":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref44","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref48","article-title":"ConvNet architecture search for spatiotemporal feature learning","author":"Tran","year":"2017","journal-title":"arXiv:1708.05038"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_44"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9730812\/09393944.pdf?arnumber=9393944","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T00:19:57Z","timestamp":1704845997000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9393944\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3]]},"references-count":50,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2021.3070688","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3]]}}}