{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T05:39:30Z","timestamp":1761975570879,"version":"3.37.3"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2017,7,1]],"date-time":"2017-07-01T00:00:00Z","timestamp":1498867200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100003711","name":"Microsoft Research Asian and MOST","doi-asserted-by":"publisher","award":["103-2218-E-007-025"],"award-info":[{"award-number":["103-2218-E-007-025"]}],"id":[{"id":"10.13039\/501100003711","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2017,7]]},"DOI":"10.1109\/tip.2017.2666039","type":"journal-article","created":{"date-parts":[[2017,2,13]],"date-time":"2017-02-13T14:21:37Z","timestamp":1486995697000},"page":"3303-3316","source":"Crossref","is-referenced-by-count":6,"title":["Semantic Highlight Retrieval and Term Prediction"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9598-8178","authenticated-orcid":false,"given":"Min","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kuo-Hao","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yen-Chen","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Farhadi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"Proc NIPS"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1613\/jair.3994","article-title":"Framing image description as a ranking task: Data, models and evaluation metrics","volume":"47","author":"hodosh","year":"2013","journal-title":"J Artif Intell Res"},{"key":"ref33","first-page":"725","article-title":"Geodesic object proposals","author":"kr\u00e4henb\u00fchl","year":"2014","journal-title":"Proc ECCV"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247806"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.333"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.345"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540112"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806221"},{"key":"ref35","article-title":"EXMOVES: Classifier-based features for scalable action recognition","author":"tran","year":"2014","journal-title":"Proc ICLR"},{"key":"ref34","first-page":"181","article-title":"Streaming first story detection with application to twitter","author":"petrovi?","year":"2010","journal-title":"Proc Annu Conf North Amer Chapter Assoc Comput Linguistics Human Lang Technol"},{"key":"ref60","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc ICLR"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298789"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.332"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-015-2454-3"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247807"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.31"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_51"},{"key":"ref20","first-page":"2069","article-title":"Diverse sequential subset selection for supervised video summarization","author":"gong","year":"2014","journal-title":"Proc NIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.114"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298928"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.526"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2320814"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298994"},{"key":"ref25","first-page":"5179","article-title":"TVSum: Summarizing Web videos using titles","author":"song","year":"2015","journal-title":"Proc CVPR"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2578726.2578754"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2265080"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/218380.218454"},{"key":"ref58","first-page":"63","article-title":"NLTK: The natural language toolkit","author":"loper","year":"2002","journal-title":"Proc of ETMTNLP"},{"key":"ref57","first-page":"61","article-title":"Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods","volume":"10","author":"platt","year":"1999","journal-title":"Adv Large Margin Classifiers"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126229"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref54","first-page":"1871","article-title":"LIBLINEAR: A library for large linear classification","volume":"9","author":"fan","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/345508.345556"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2489841"},{"key":"ref10","first-page":"4","article-title":"Highlights extraction from sports video based on an audio-visual marker detection framework","author":"xiong","year":"2005","journal-title":"Proc ICME"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2006.262856"},{"key":"ref40","first-page":"15","article-title":"Every picture tells a story: Generating sentences from images","author":"farhadi","year":"2010","journal-title":"Proc ICCV"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.858397"},{"key":"ref13","first-page":"1","article-title":"Detecting highlights in sports videos: Cricket as a test case","author":"tang","year":"2011","journal-title":"Proc ICME"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1049\/iet-ipr.2012.0495"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2009.2013517"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.350"},{"key":"ref17","first-page":"1346","article-title":"Discovering important people and objects for egocentric video summarization","author":"lee","year":"2012","journal-title":"Proc CVPR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298836"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.348"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.322"},{"key":"ref3","first-page":"505","article-title":"Creating summaries from user videos","author":"gygli","year":"2014","journal-title":"Proc ECCV"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532982"},{"key":"ref5","first-page":"540","article-title":"Category-specific video summarization","author":"potapov","year":"2014","journal-title":"Proc ECCV"},{"key":"ref8","first-page":"1","article-title":"A survey on video-based graphics and video visualization","author":"borgo","year":"2011","journal-title":"Proc Eurographics"},{"key":"ref7","first-page":"1027","article-title":"K-means++: The advantages of careful seeding","author":"arthur","year":"2007","journal-title":"Proc 18th Annu ACM-SIAM Symp Discrete Algorithms"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2010.160"},{"key":"ref9","first-page":"599","article-title":"Sports highlight detection from keyword sequences using HMM","author":"wang","year":"2004","journal-title":"Proc ICME"},{"key":"ref46","first-page":"2397","article-title":"A discriminative latent model of image region and object tag correspondence","author":"wang","year":"2010","journal-title":"Proc NIPS"},{"key":"ref45","first-page":"2036","article-title":"Towards total scene understanding: Classification, annotation and segmentation in an automatic framework","author":"li","year":"2009","journal-title":"Proc CVPR"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref47","first-page":"316","article-title":"A new baseline for image annotation","author":"makadia","year":"2008","journal-title":"Proc ECCV"},{"key":"ref42","article-title":"The MediaMill TRECVID 2009 semantic video search engine","author":"snoek","year":"2009","journal-title":"7th TRECVID Workshop"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995402"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539985"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/7922633\/07852483.pdf?arnumber=7852483","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:38:32Z","timestamp":1641987512000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7852483\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7]]},"references-count":61,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tip.2017.2666039","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2017,7]]}}}