{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T21:58:31Z","timestamp":1725487111709},"reference-count":33,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462612","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T18:24:48Z","timestamp":1537554288000},"page":"1932-1936","source":"Crossref","is-referenced-by-count":1,"title":["Mgn: Multi-Glimpse Network for Action Recognition"],"prefix":"10.1109","author":[{"given":"Chaoxu","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tingzhao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huxiang","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiming","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunhong","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"438","article-title":"Pose for action-action for pose","author":"iqbal","year":"2017","journal-title":"FG IEEE"},{"journal-title":"Body joint guided 3d deep convolutional descriptors for action recognition","year":"2017","author":"cao","key":"ref32"},{"key":"ref31","first-page":"3218","article-title":"P-cnn: Pose-based cnn features for action recognition","author":"ch\u00e9ron","year":"2015","journal-title":"ICCV IEEE"},{"journal-title":"Semantic guided network for open domain action recognition","year":"0","author":"yu","key":"ref30"},{"journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition","year":"2014","author":"simonyan","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"NIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref15","article-title":"Cascade temporal spatial features for video action recognition","author":"yu","year":"2017","journal-title":"ICIP IEEE"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.331"},{"key":"ref17","first-page":"3468","article-title":"Spatiotemporal residual networks for video action recognition","author":"feichtenhofer","year":"2016","journal-title":"NIPS"},{"key":"ref18","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"ECCV"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.280"},{"key":"ref4","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"NIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref3","article-title":"Large-scale video classification with convolutional neural networks","author":"karpathy","year":"2014","journal-title":"CVPR IEEE"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.162"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.99"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref9","first-page":"1097","article-title":"Im-age net classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NIPS"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"journal-title":"Convnet architecture search for spatiotemporal feature learning","year":"2017","author":"tran","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref21","first-page":"4694","article-title":"Beyond short snippets: Deep networks for video classification","author":"ng","year":"2015","journal-title":"CVPR IEEE"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"journal-title":"Ucf101 A Dataset of 101 Human Actions Classes from Videos in the Wild","year":"2012","author":"soomro","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.07.013"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2018,4,15]]},"location":"Calgary, AB","end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08462612.pdf?arnumber=8462612","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T23:17:48Z","timestamp":1598224668000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462612\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462612","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}