{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T09:59:05Z","timestamp":1790675945884,"version":"4.1.0"},"reference-count":85,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2017,10,1]],"date-time":"2017-10-01T00:00:00Z","timestamp":1506816000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2017,10,1]]},"DOI":"10.1109\/tpami.2016.2627563","type":"journal-article","created":{"date-parts":[[2016,11,10]],"date-time":"2016-11-10T20:03:00Z","timestamp":1478808180000},"page":"2089-2103","source":"Crossref","is-referenced-by-count":55,"title":["Video2vec Embeddings Recognize Events When Examples Are Scarce"],"prefix":"10.1109","volume":"39","author":[{"given":"Amirhossein","family":"Habibian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Mensink","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cees G. M.","family":"Snoek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101236"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref71","first-page":"1737","article-title":"Large margin taxonomy embedding for document categorization","author":"weinberger","year":"2009","journal-title":"Proc 21st Int Conf Neural Inf Process Syst"},{"key":"ref70","first-page":"1453","article-title":"Large margin methods for structured and interdependent output variables","volume":"6","author":"tsochantaridis","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/1991996.1992025"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.335"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref75","first-page":"2573","article-title":"Creating HAVIC: Heterogeneous audio visual internet collection","author":"strassel","year":"2012","journal-title":"Proc Int Conf Lang Resources Eval"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.330"},{"key":"ref79","year":"2015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2578726.2578729"},{"key":"ref32","article-title":"Building a large concept bank for representing events in video","author":"cui","year":"2014","journal-title":"arXiv 1403 7591"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.341"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654913"},{"key":"ref36","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref35","first-page":"663","article-title":"Automatic attribute discovery and characterization from noisy Web data","author":"berg","year":"2010","journal-title":"Proc 11th Eur Conf Comput Vis"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806221"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126281"},{"key":"ref62","first-page":"2694","article-title":"Self-paced curriculum learning","author":"jiang","year":"2015","journal-title":"Proc 29th AAAI Conf Artif Intell"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/2578726.2578764"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/2578726.2578746"},{"key":"ref28","first-page":"3841","article-title":"Complex event detection via event oriented dictionary learning","author":"yan","year":"2015","journal-title":"Proc 29th AAAI Conf Artif Intell"},{"key":"ref64","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1145\/2671188.2749402","article-title":"Encoding concept prototypes for video event detection and summarization","author":"mazloom","year":"2015","journal-title":"Proc 5th ACM Int Conf Multimedia Retrieval"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.331"},{"key":"ref65","first-page":"1857","article-title":"Zero-shot video retrieval using content and concepts","author":"dalton","year":"2013","journal-title":"Proc ACM Int Conf Inf Knowl Manag"},{"key":"ref66","first-page":"2234","article-title":"Semantic concept discovery for large-scale zero-shot event detection","author":"chang","year":"2015","journal-title":"Proc 24th Int Conf Artif Intell"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806237"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/2009916.2010008"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/312624.312649"},{"key":"ref69","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1561\/0600000058","article-title":"Sparse modeling for image and vision processing","volume":"8","author":"mairal","year":"2012","journal-title":"Found Trends Comput Graph Vis"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0846-5"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298789"},{"key":"ref20","first-page":"430","article-title":"Recognizing complex events using large margin joint low-level event model","author":"izadinia","year":"2012","journal-title":"Proc 12th Eur Conf Comput Vis"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.339"},{"key":"ref21","article-title":"From concepts to events: A progressive process for multimedia content analysis","author":"ma","year":"2013"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2359771"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2014.02.003"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.287"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2306419"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.340"},{"key":"ref59","first-page":"1","article-title":"Utilizing semantic word similarity measures for video retrieval","author":"aytar","year":"2008","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/2433396.2433456"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540000"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/28.3-4.321"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"},{"key":"ref54","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.142"},{"key":"ref52","first-page":"2346","article-title":"Jointly modeling deep video and compositional text to bridge vision and language in a unified framework","author":"xu","year":"2015","journal-title":"Proc 29th AAAI Conf Artif Intell"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.235"},{"key":"ref11","article-title":"TRECVID 2013-an overview of the goals, tasks, data, evaluation mechanisms and metrics","author":"over","year":"2013","journal-title":"Proc TRECVID Workshop"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.228"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref13","article-title":"BBN VISER TRECVID 2013 multimedia event detection and multimedia event recounting systems","author":"natarajan","year":"2013","journal-title":"Proc TRECVID Workshop"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-013-0525-x"},{"key":"ref15","article-title":"Informedia@ TRECVID 2014 MED and MER","author":"yu","year":"2014","journal-title":"Proc TRECVID Workshop"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.329"},{"key":"ref16","first-page":"1410","article-title":"Zero-shot learning with semantic output codes","author":"palatucci","year":"2009","journal-title":"Proc 22nd Int Conf Neural Inf Process Syst"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247808"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.521"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806218"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2168948"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.339"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247814"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-012-0024-2"},{"key":"ref6","first-page":"140","article-title":"Convolutional learning of spatio-temporal features","author":"taylor","year":"2010","journal-title":"Proc 11th Eur Conf Comput Vis"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248114"},{"key":"ref85","article-title":"VRFP: On-the-fly video retrieval using web images and fast fisher vector products","author":"han","year":"2016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref9","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/860458.860460"},{"key":"ref45","first-page":"433","article-title":"Learning visual attributes","author":"ferrari","year":"2007","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.111"},{"key":"ref47","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":"ref42","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref41","article-title":"Columbia-UCF TRECVID 2010 multimedia event detection: Combining multiple modalities, contextual concepts, and temporal matching","author":"jiang","year":"2010","journal-title":"Proc TRECVID Workshop"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"ref43","first-page":"178.1","article-title":"Event Fisher vectors: Robust encoding visual diversity of visual streams","author":"nagel","year":"2015","journal-title":"Proc British Mach Vis Conf"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/8024097\/07740886.pdf?arnumber=7740886","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:41:35Z","timestamp":1642005695000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7740886\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10,1]]},"references-count":85,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2016.2627563","relation":{},"ISSN":["0162-8828","2160-9292"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,10,1]]}}}