{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T16:57:32Z","timestamp":1788886652544,"version":"build-2803163510"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"MIT-IBM Watson AI Lab"},{"name":"Nexplore and Woodside"},{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100013177","name":"Interior Business Center","doi-asserted-by":"publisher","award":["D17PC00341"],"award-info":[{"award-number":["D17PC00341"]}],"id":[{"id":"10.13039\/100013177","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022,12,1]]},"DOI":"10.1109\/tpami.2021.3126682","type":"journal-article","created":{"date-parts":[[2021,11,9]],"date-time":"2021-11-09T20:42:40Z","timestamp":1636490560000},"page":"9434-9445","source":"Crossref","is-referenced-by-count":43,"title":["Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understanding"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6373-5520","authenticated-orcid":false,"given":"Mathew","family":"Monfort","sequence":"first","affiliation":[{"name":"MIT CSAIL, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bowen","family":"Pan","sequence":"additional","affiliation":[{"name":"MIT CSAIL, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kandan","family":"Ramakrishnan","sequence":"additional","affiliation":[{"name":"MIT-IBM Watson AI Lab, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Andonian","sequence":"additional","affiliation":[{"name":"MIT CSAIL, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Barry A.","family":"McNamara","sequence":"additional","affiliation":[{"name":"MIT CSAIL, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Lascelles","sequence":"additional","affiliation":[{"name":"MIT CSAIL, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quanfu","family":"Fan","sequence":"additional","affiliation":[{"name":"IBM Research, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5101-4443","authenticated-orcid":false,"given":"Dan","family":"Gutfreund","sequence":"additional","affiliation":[{"name":"IBM Research, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6399-0679","authenticated-orcid":false,"given":"Rogerio Schmidt","family":"Feris","sequence":"additional","affiliation":[{"name":"IBM Research, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aude","family":"Oliva","sequence":"additional","affiliation":[{"name":"MIT CSAIL, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858759"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2006.162"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.251"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref31","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012"},{"key":"ref30","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2812605"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-7305-2"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.37"},{"key":"ref34","first-page":"2764","article-title":"WSABIE: Scaling up to large vocabulary image annotation","author":"weston","year":"2011","journal-title":"Proc 22nd Int Joint Conf Artif Intell"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.254"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref11","article-title":"Scaling egocentric vision: The epic-kitchens dataset","author":"damen","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref13","first-page":"681","article-title":"A kernel method for multi-labelled classification","author":"elisseeff","year":"2001","journal-title":"Proc 14th Int Conf Neural Inf Process Syst Natural Synthetic"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00924"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref16","article-title":"Deep convolutional ranking for multilabel image annotation","author":"gong","year":"2014","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref17","article-title":"The “something something","author":"goyal","year":"2017","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref19","article-title":"THUMOS challenge: Action recognition with a large number of classes","author":"jiang","year":"2014"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.354"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2901464"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.354"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2462002"},{"key":"ref5","article-title":"GAN dissection: Visualizing and understanding generative adversarial networks","author":"bau","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0\\_31"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref7","first-page":"1014","article-title":"Proper network interpretability helps adversarial robustness in classification","author":"boopathy","year":"2020","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref2","first-page":"892","article-title":"SoundNet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref1","article-title":"YouTube-8M: A large-scale video classification benchmark","author":"abu-el-haija","year":"2016","journal-title":"CoRR"},{"key":"ref20","article-title":"The kinetics human action video dataset","author":"kay","year":"2017","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.199"},{"key":"ref21","article-title":"HMDB51: A large video database for human motion recognition","author":"kuehne","year":"2013","journal-title":"High Performance Computing in Science and Engineering"},{"key":"ref24","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref25","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"Proc 1st Int Conf Learn Representations"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9940446\/09609554.pdf?arnumber=9609554","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T22:37:46Z","timestamp":1670279866000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9609554\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,1]]},"references-count":42,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3126682","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,1]]}}}