{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:48:34Z","timestamp":1781020114826,"version":"3.54.1"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1718014"],"award-info":[{"award-number":["CNS-1718014"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1763981"],"award-info":[{"award-number":["IIS-1763981"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1566248"],"award-info":[{"award-number":["IIS-1566248"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Partner University Fund"},{"name":"the SUNY2020 Infrastructure Transportation Security Center"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2021,3,1]]},"DOI":"10.1109\/tpami.2019.2940225","type":"journal-article","created":{"date-parts":[[2019,9,11]],"date-time":"2019-09-11T06:21:50Z","timestamp":1568182910000},"page":"1009-1021","source":"Crossref","is-referenced-by-count":12,"title":["Sequence-to-Segments Networks for Detecting Segments in Videos"],"prefix":"10.1109","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2487-1041","authenticated-orcid":false,"given":"Zijun","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2075-3731","authenticated-orcid":false,"given":"Boyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minh","family":"Hoai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9954-6294","authenticated-orcid":false,"given":"Jianming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohui","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5558-0327","authenticated-orcid":false,"given":"Radomir","family":"Mech","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1373-0294","authenticated-orcid":false,"given":"Dimitris","family":"Samaras","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00572"},{"key":"ref71","article-title":"The kinetics human action video dataset","author":"kay","year":"2017"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"ref74","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298981"},{"key":"ref32","first-page":"1331","article-title":"Space-time video montage","author":"kang","year":"2006","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.318"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123328"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.392"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_47"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.211"},{"key":"ref34","first-page":"1346","article-title":"Discovering important people and objects for egocentric video summarization","author":"lee","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298928"},{"key":"ref62","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref61","first-page":"2069","article-title":"Diverse sequential subset selection for supervised video summarization","author":"gong","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref28","first-page":"5179","article-title":"TVSum: Summarizing web videos using titles","author":"song","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref64","article-title":"THUMOS challenge: Action recognition with a large number of classes","author":"jiang","year":"2014"},{"key":"ref27","first-page":"609","article-title":"Generation for user generated videos","author":"zeng","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298735"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.93"},{"key":"ref29","article-title":"Video summarization with attention-based encoder-decoder networks","author":"ji","year":"2017"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_16"},{"key":"ref68","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995470"},{"key":"ref69","article-title":"CUHK & ETHZ & SIAT submission to ActivityNet challenge 2016","author":"xiong","year":"2016"},{"key":"ref1","first-page":"2737","article-title":"Action unit detection with segment-based SVMs","author":"nguyen","year":"2010","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref20","article-title":"Neural turing machines","author":"graves","year":"2014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref21","first-page":"2773","article-title":"Grammar as a foreign language","author":"vinyals","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref24","first-page":"11","article-title":"Analysis and presentation of soccer highlights from digital video","author":"yow","year":"1995","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/500178.500181"},{"key":"ref25","first-page":"1","article-title":"Detecting highlights in sports videos: Cricket as a test case","author":"tang","year":"2011","journal-title":"Proc IEEE Int Conf Multimedia Expo"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref51","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","author":"srivastava","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_33"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref56","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref54","author":"luenberger","year":"1973","journal-title":"Introduction to Linear and Nonlinear Programming"},{"key":"ref53","first-page":"1865","article-title":"Stochastic methods for l1-regularized loss minimization","volume":"12","author":"shalev-shwartz","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref52","article-title":"Squared earth mover's distance-based loss for training deep neural networks","author":"hou","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2013.09.028"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952591"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/9969.003.0016","article-title":"Structured prediction for event detection","author":"hoai","year":"2014","journal-title":"Advanced Structured Prediction"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1064"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1101\/gr.227819.117"},{"key":"ref14","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref15","first-page":"2692","article-title":"Pointer networks","author":"vinyals","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.255"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref18","first-page":"318","article-title":"Learning internal representations by error propagation","volume":"1","author":"rumelhart","year":"1986","journal-title":"Parallel Distributed Processing"},{"key":"ref19","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0683-3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_24"},{"key":"ref5","first-page":"7582","article-title":"Deep reinforcement learning for unsupervised video summarization with diversity-representativeness reward","author":"zhou","year":"2017","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_51"},{"key":"ref49","first-page":"21","article-title":"SSD: Single shot MultiBox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.526"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21236\/ADA507101"},{"key":"ref46","first-page":"2342","article-title":"An empirical exploration of recurrent network architectures","author":"jozefowicz","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.675"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.214"},{"key":"ref47","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014"},{"key":"ref42","article-title":"Visualizing and understanding recurrent networks","author":"karpathy","year":"2016","journal-title":"Proc Int Conf Learn Representations Workshops"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.09.005"},{"key":"ref44","article-title":"Depth-Gated LSTM","author":"yao","year":"2015","journal-title":"arXiv 1508 03790"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/9346108\/8827968-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9346108\/08827968.pdf?arnumber=8827968","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T03:30:27Z","timestamp":1695180627000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8827968\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,1]]},"references-count":74,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2019.2940225","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,1]]}}}