{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,15]],"date-time":"2026-02-15T03:20:24Z","timestamp":1771125624480,"version":"3.50.1"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF"},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000185","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":[[2019,10,1]]},"DOI":"10.1109\/tpami.2019.2921539","type":"journal-article","created":{"date-parts":[[2019,6,7]],"date-time":"2019-06-07T20:35:20Z","timestamp":1559939720000},"page":"2319-2332","source":"Crossref","is-referenced-by-count":45,"title":["Two-Stream Region Convolutional 3D Network for Temporal Activity Detection"],"prefix":"10.1109","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4778-5584","authenticated-orcid":false,"given":"Huijuan","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2327-1618","authenticated-orcid":false,"given":"Abir","family":"Das","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kate","family":"Saenko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.214"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.65"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.617"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298735"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.362"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2548242"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref60","article-title":"YouTube-8M: A large-scale video classification benchmark","author":"abu-el-haija","year":"2016"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.599"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref27","article-title":"Learning and example selection for object and pattern detection","author":"sung","year":"1996"},{"key":"ref29","article-title":"THUMOS challenge: Action recognition with a large number of Classes","author":"jiang","year":"2014"},{"key":"ref2","first-page":"1","article-title":"The LEAR submission at Thumos 2014","author":"oneata","year":"2014","journal-title":"Proc European Conf Comp Vis Workshop"},{"key":"ref1","first-page":"1","article-title":"Fast saliency based pooling of fisher encoded dense trajectories","author":"karaman","year":"2014","journal-title":"Proc European Conf Comp Vis Workshop"},{"key":"ref20","article-title":"Efficient two-stream motion and appearance 3D CNNs for video classification","author":"diba","year":"2016"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.297"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref24","first-page":"4694","article-title":"Beyond short snippets: Deep networks for video classification","author":"ng","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.222"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.211"},{"key":"ref59","article-title":"Untrimmed video classification for activity detection: Submission to activityNet challenge","author":"singh","year":"2016"},{"key":"ref58","article-title":"ActivitNet large scale activity recognition challenge","year":"2016"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.337"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"ref55","article-title":"Online batch selection for faster training of neural networks","author":"loshchilov","year":"2015"},{"key":"ref54","article-title":"Fracking deep convolutional image descriptors","author":"simo-serra","year":"2014"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.610"},{"key":"ref10","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.93"},{"key":"ref12","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_47"},{"key":"ref14","article-title":"Temporal activity detection in untrimmed videos with recurrent neural networks","author":"montes","year":"2016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.216"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref18","first-page":"2553","article-title":"Deep neural networks for object detection","author":"szegedy","year":"2013","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.231"},{"key":"ref4","first-page":"1","article-title":"Action recognition and detection by combining motion and appearance features","volume":"1","author":"wang","year":"2014","journal-title":"Proc European Conf Comp Vis Workshop"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_37"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.13"},{"key":"ref7","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref46","first-page":"21","article-title":"SSD: Single shot MultiBox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.341"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref47","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","author":"dai","year":"2016","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.155"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.678"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.620"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/8824149\/08733121.pdf?arnumber=8733121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:09:26Z","timestamp":1657746566000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8733121\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,1]]},"references-count":61,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2019.2921539","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":[[2019,10,1]]}}}