{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T01:14:14Z","timestamp":1790385254314,"version":"4.1.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2017,5,1]],"date-time":"2017-05-01T00:00:00Z","timestamp":1493596800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Citt\u00e0 educante","award":["CTN01_00034_393801"],"award-info":[{"award-number":["CTN01_00034_393801"]}]},{"name":"National Technological Cluster on Smart Communities"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2017,5]]},"DOI":"10.1109\/tmm.2016.2644872","type":"journal-article","created":{"date-parts":[[2016,12,24]],"date-time":"2016-12-24T15:10:23Z","timestamp":1482592223000},"page":"955-968","source":"Crossref","is-referenced-by-count":40,"title":["Recognizing and Presenting the Storytelling Video Structure With Deep Multimodal Networks"],"prefix":"10.1109","volume":"19","author":[{"given":"Lorenzo","family":"Baraldi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Costantino","family":"Grana","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rita","family":"Cucchiara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"0","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref38","volume":"1","author":"friedman","year":"2001","journal-title":"The Elements of Statistical Learning"},{"key":"ref33","first-page":"3111","article-title":"Distributed representations of words and phrases and their\n compositionality","author":"mikolov","year":"0","journal-title":"Proc 26th Int Conf Neural Inf Process Syst"},{"key":"ref32","first-page":"449","article-title":"Generating typed dependency parses from phrase\n structure parses","volume":"6","author":"marneffe","year":"0","journal-title":"Proc 5th Int Conf Lang Resources Eval"},{"key":"ref31","article-title":"Mel frequency cepstral coefficients for music\n modeling","author":"logan","year":"0","journal-title":"Proc Int Symp Music Inf Retrieval"},{"key":"ref30","article-title":"VideoStory embeddings recognize events when examples are scarce","author":"habibian","year":"2015","journal-title":"CoRR"},{"key":"ref37","first-page":"1929","article-title":"Dropout: A simple\n way to prevent neural networks from overfitting","volume":"15","author":"hinton","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref36","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref34","first-page":"248","article-title":"ImageNet: A large-scale hierarchical image\n database","author":"deng","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2011.2138830"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299155"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806316"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2614185"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.538"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-47979-1_26"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.29"},{"key":"ref16","first-page":"505","article-title":"Creating summaries from user\n videos","author":"gygli","year":"0","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.112"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1126004.1126005"},{"key":"ref28","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2008.07.009"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298994"},{"key":"ref3","author":"petersohn","year":"2010","journal-title":"Temporal Video Segmentation"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2238522"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/76.767124"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1117\/12.206067"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.2008924"},{"key":"ref2","article-title":"Third Annual Millennial Video Entertainment Survey","year":"2015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.858392"},{"key":"ref1","article-title":"Global Internet Phenomena Report","year":"2016"},{"key":"ref46","first-page":"13","article-title":"Segmenting TV series into\n scenes using speaker diarization","author":"ercolessi","year":"0","journal-title":"Proc Workshop Image Anal Multimedia Interactive Services"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.900156"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854873"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.340"},{"key":"ref47","year":"2016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.05.009"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/775047.775067"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101242"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298642"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2557249"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2011.2181231"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2011.6116155"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2002.802021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.179"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/7902243\/07797131.pdf?arnumber=7797131","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:09:10Z","timestamp":1642003750000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7797131\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5]]},"references-count":47,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2016.2644872","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,5]]}}}