{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:01:44Z","timestamp":1740132104720,"version":"3.37.3"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2016,10,1]],"date-time":"2016-10-01T00:00:00Z","timestamp":1475280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/100006754","name":"Army Research Laboratory","doi-asserted-by":"publisher","award":["W911NF-10-2-0060"],"award-info":[{"award-number":["W911NF-10-2-0060"]}],"id":[{"id":"10.13039\/100006754","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":[[2016,10,1]]},"DOI":"10.1109\/tpami.2015.2505297","type":"journal-article","created":{"date-parts":[[2015,12,3]],"date-time":"2015-12-03T19:08:15Z","timestamp":1449169695000},"page":"2069-2081","source":"Crossref","is-referenced-by-count":8,"title":["Saying What You're Looking For: Linguistics Meets Video Search"],"prefix":"10.1109","volume":"38","author":[{"given":"Daniel Paul","family":"Barrett","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrei","family":"Barbu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"N.","family":"Siddharth","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeffrey Mark","family":"Siskind","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.888015"},{"key":"ref38","first-page":"102","article-title":"Video in sentences out","author":"barbu","year":"0","journal-title":"Proc Conf Uncertainty Artif Intell"},{"key":"ref33","first-page":"2949","article-title":"Fast template evaluation with vector quantization","author":"sadeghi","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539906"},{"key":"ref30","first-page":"595","article-title":"Multimodal neural language models","author":"kiros","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","first-page":"203","volume":"2","author":"barbu","year":"2012","journal-title":"Adv Cognitive Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1971.1090700"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1054010"},{"journal-title":"Dynamic Programming","year":"1957","author":"bellman","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995711"},{"key":"ref40","first-page":"53","article-title":"Grounded language learning from video described with sentences","author":"yu","year":"0","journal-title":"Proc 32nd Ann Meeting Assoc for Computational Linguistics"},{"key":"ref11","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","author":"mitchell","year":"0","journal-title":"Proc Conf Eur Chapter Assoc Comput Linguistics"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1561\/1500000014"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.99"},{"key":"ref14","article-title":"Language-driven video retrieval","author":"barbu","year":"0","journal-title":"Workshop on Vision meets Cognition CVPR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2002.1038097"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247806"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.80"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.457"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.367"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1007\/s11263-008-0142-8","article-title":"Searching for complex human activities with no visual examples","volume":"80","author":"forsyth","year":"2008","journal-title":"Int J Comput Vis"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.455"},{"key":"ref27","first-page":"1","article-title":"Searching video for complex activites with finite state models","author":"forsyth","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref3","article-title":"Deep visual-semantic alignments for generating image descriptions","author":"karpathy","year":"0","journal-title":"arXiv 1412 2306"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/957013.957018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.340"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-009-0403-8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2008.2005801"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995466"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"797","DOI":"10.1109\/TSMCC.2011.2109710","article-title":"A survey on visual content-based video indexing and retrieval","volume":"41","author":"hu","year":"2011","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.4086\/toc.2012.v008a019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.341"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459303"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326724"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/VETECF.2002.1040367"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88693-8_25"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.886275"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2009.5403131"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367294"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.237"},{"key":"ref26","first-page":"1","article-title":"Utilizing semantic word similarity measures for video retrieval","author":"aytar","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995329"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2578726.2578727"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/7558271\/07346469.pdf?arnumber=7346469","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,11]],"date-time":"2021-10-11T02:36:00Z","timestamp":1633919760000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7346469\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10,1]]},"references-count":47,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2015.2505297","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2016,10,1]]}}}