{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:18:23Z","timestamp":1783527503210,"version":"3.55.0"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2018,9,1]],"date-time":"2018-09-01T00:00:00Z","timestamp":1535760000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"ERC","award":["307574"],"award-info":[{"award-number":["307574"]}]},{"name":"ERC","award":["336845"],"award-info":[{"award-number":["336845"]}]},{"name":"CIFAR Learning in Machines & Brains program"},{"name":"ESIF"},{"name":"OP Research, development and education","award":["CZ.02.1.01\/0.0\/0.0\/15_003\/0000468"],"award-info":[{"award-number":["CZ.02.1.01\/0.0\/0.0\/15_003\/0000468"]}]},{"name":"Google Research Award"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2018,9,1]]},"DOI":"10.1109\/tpami.2017.2749223","type":"journal-article","created":{"date-parts":[[2017,9,5]],"date-time":"2017-09-05T18:14:56Z","timestamp":1504635296000},"page":"2194-2208","source":"Crossref","is-referenced-by-count":8,"title":["Learning from Narrated Instruction Videos"],"prefix":"10.1109","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3071-4157","authenticated-orcid":false,"given":"Jean-Baptiste","family":"Alayrac","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Piotr","family":"Bojanowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nishant","family":"Agrawal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Josef","family":"Sivic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ivan","family":"Laptev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6485-6180","authenticated-orcid":false,"given":"Simon","family":"Lacoste-Julien","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1089\/cmb.1994.1.337"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.342"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_35"},{"key":"ref31","first-page":"593","article-title":"Minding the gaps for block Frank-Wolfe optimization of structured SVMs","author":"osokin","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0122-4"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_51"},{"key":"ref36","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.509"},{"key":"ref34","first-page":"979","article-title":"Learning script knowledge with Web experiments","author":"regneri","year":"2010","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref10","first-page":"449","article-title":"Generating typed dependency parses from phrase structure parses","author":"de marneffe","year":"2006","journal-title":"Proc Int Conf on Lang Resources and Evaluation"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459279"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/7287.001.0001","author":"fellbaum","year":"1998","journal-title":"WordNet An Electronic Lexical Database"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/E14-1006"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/0378-1119(88)90330-7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-014-9192-1"},{"key":"ref16","first-page":"-427i","article-title":"Revisiting Frank-Wolfe: Projection-free sparse convex optimization","author":"jaggi","year":"2013","journal-title":"Proc 29th Int Conf Mach Learn"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_17"},{"key":"ref18","article-title":"Convergence rate of Frank-Wolfe for non-convex objectives","author":"lacoste-julien","year":"2016"},{"key":"ref19","first-page":"496","article-title":"On the global linear convergence of Frank-Wolfe optimization variants","author":"lacoste-julien","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.283"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref3","first-page":"49","article-title":"DIFFRAC: A discriminative and flexible framework for clustering","author":"bach","year":"2007","journal-title":"Proc 20th Int Conf Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.507"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15552-9_29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_41"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299193"},{"key":"ref7","first-page":"789","article-title":"Unsupervised learning of narrative event chains","author":"chambers","year":"2008","journal-title":"Proc 32nd Ann Meeting Assoc for Computational Linguistics"},{"key":"ref2","year":"0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299007"},{"key":"ref1","year":"0"},{"key":"ref20","first-page":"-53i","article-title":"Block-coordinate Frank-Wolfe optimization for structural SVMs","author":"lacoste-julien","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/18.3.452"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref24","first-page":"143","article-title":"What’s cookin’? Interpreting cooking videos using text, speech and vision","author":"malmaud","year":"2015","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Human Language Technol"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"1857","DOI":"10.1016\/j.patcog.2005.01.025","article-title":"Clustering of time series data, a survey","volume":"38","author":"liao","year":"2014","journal-title":"Pattern Recognit"},{"key":"ref26","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.562"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/8424845\/08025823.pdf?arnumber=8025823","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:23:07Z","timestamp":1642004587000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8025823\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9,1]]},"references-count":39,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2017.2749223","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":[[2018,9,1]]}}}