{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T10:32:52Z","timestamp":1768473172239,"version":"3.49.0"},"reference-count":94,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2021,9]]},"DOI":"10.1109\/tcsvt.2020.3042476","type":"journal-article","created":{"date-parts":[[2020,12,5]],"date-time":"2020-12-05T02:28:51Z","timestamp":1607135331000},"page":"3559-3574","source":"Crossref","is-referenced-by-count":12,"title":["Adaptive Context Reading Network for Movie Scene Detection"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7350-933X","authenticated-orcid":false,"given":"Dong","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nagendra","family":"Kamath","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Subhabrata","family":"Bhattacharya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohit","family":"Puri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00369"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972757.25"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/34.868688"},{"key":"ref70","author":"manning","year":"2009","journal-title":"An Introduction to Information Retrieval"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref77","article-title":"Towards good practices for very deep two-stream ConvNets","author":"wang","year":"2015","journal-title":"ArXiv 1507 02159"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00710"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref78","article-title":"Layer normalization","author":"lei ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref79","year":"2015","journal-title":"TensorFlow Large-Scale Machine Learning on Heterogeneous Systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01016"},{"key":"ref37","first-page":"399","article-title":"Videos as space-time region graphs","author":"wang","year":"2018","journal-title":"Proc ECCV"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.508"},{"key":"ref34","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","author":"srivastava","year":"2015","journal-title":"Proc ICML"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298928"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00809"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00193"},{"key":"ref63","first-page":"1857","article-title":"Improved deep metric learning with multi-class n-pair loss objective","author":"sohn","year":"2016","journal-title":"Proc NIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.876299"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.237"},{"key":"ref27","first-page":"1551","article-title":"Joint video scene segmentation and classification based on hidden Markov model","author":"huang","year":"2000","journal-title":"Proc IEEE Int Conf Multimedia Expo Latest Adv Fast Changing World Multimedia (ICME)"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.434"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-018-1244-6"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102379"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.1265860"},{"key":"ref69","first-page":"785","article-title":"Structured learning with approximate inference","author":"kulesza","year":"2007","journal-title":"Proc NIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/BF01210504"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s005300050138"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2003.1211489"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-002-0184-9"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2002.808084"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.858392"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2004.841694"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2007.4284701"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.1997.0628"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00976"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"ref94","first-page":"127","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref93","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc AISTATS"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-10467-1_82"},{"key":"ref91","first-page":"1","article-title":"Video scene segmentation using a novel boundary evaluation criterion and dynamic programming","author":"han","year":"2011","journal-title":"Proc IEEE Int Conf Multimedia Expo"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019167"},{"key":"ref58","article-title":"Adaptive memory networks","author":"li","year":"2018"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00102"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00971"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.80"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/76.767124"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1998.698632"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_7"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2016.0061"},{"key":"ref13","first-page":"1378","article-title":"Ask me anything: Dynamic memory networks for natural language processing","author":"kumar","year":"2016","journal-title":"Proc ICML"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1147"},{"key":"ref15","first-page":"2440","article-title":"End-to-end memory networks","author":"sukhbaatar","year":"2015","journal-title":"Proc NIPS"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015341"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00576"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-013-0306-4"},{"key":"ref84","article-title":"Condensed movies: Story based retrieval with contextual embeddings","author":"bain","year":"2020","journal-title":"arXiv 2005 04208"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2002.1035721"},{"key":"ref83","year":"2014","journal-title":"Fandango Movieclips"},{"key":"ref19","first-page":"1","article-title":"Rule-based scene extraction from video","author":"chen","year":"2002","journal-title":"Proc Int Conf Image Process"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.5594\/JMI.2018.2827278"},{"key":"ref89","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc ICLR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2644872"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806316"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206055"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.2008924"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2002.802021"},{"key":"ref8","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc NIPS"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2011.2138830"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383489"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01189-x"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1142\/S1793351X17400086"},{"key":"ref88","year":"2007","journal-title":"Blender Institute"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref46","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00440"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00043"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00037"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9527373\/09281335.pdf?arnumber=9281335","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:23Z","timestamp":1652194223000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9281335\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9]]},"references-count":94,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2020.3042476","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9]]}}}