{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T16:08:09Z","timestamp":1773418089802,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054200","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"2103-2107","source":"Crossref","is-referenced-by-count":13,"title":["Learning Spatio-Temporal Representations With Temporal Squeeze Pooling"],"prefix":"10.1109","author":[{"given":"Guoxi","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adrian G.","family":"Bors","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref13","first-page":"4278","article-title":"Inception-v4, inception-resnet and the impact of resid¬ual connections on learning","author":"szegedy","year":"2017","journal-title":"Proc AAAI Conf on Artificial Intelligence"},{"key":"ref14","first-page":"214","article-title":"A duality based ap¬proach for realtime TV-L1 optical flow","author":"zach","year":"2007","journal-title":"Proc Joint Pattern Recog Symp vol LNCS 4713"},{"key":"ref15","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref17","first-page":"248","article-title":"Imagenet: A large-scale hierarchical im¬age database","author":"deng","year":"2009","journal-title":"IEEE Comp Vision and Pattern Recog (CVPR)"},{"key":"ref18","first-page":"20","article-title":"Temporal segment networks: To¬wards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"Proc European Conf on Computer Vision (ECCV) vol LNCS 9912"},{"key":"ref19","first-page":"581","article-title":"Action recog¬nition with stacked fisher vectors","author":"peng","year":"2014","journal-title":"Proc European Conf on Computer Vision (ECCV) vol LNCS 8693)"},{"key":"ref4","first-page":"3551","article-title":"Action recognition with im¬proved trajectories","author":"wang","year":"2013","journal-title":"Proc IEEE Int Conf Comp Vis"},{"key":"ref3","first-page":"650","article-title":"An effi¬cient dense and scale-invariant spatio-temporal interest point detector","author":"willems","year":"2008","journal-title":"Proc Eur Conf on Comp Vision (ECCV) Vol LNCS 5303"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2769085"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2018.03.021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref7","first-page":"568","article-title":"Two-stream con¬volutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Advances in Neural Inf Proc Systems (NIPS)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.99"},{"key":"ref9","first-page":"4724","article-title":"Quo vadis, action recog¬nitionƒ a new model and the kinetics dataset","author":"carreira","year":"2017","journal-title":"IEEE Comp Vision and Pattern Recog (CVPR)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.03.013"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref21","first-page":"1933","article-title":"Convolu¬tional two-stream network fusion for video action recog¬nition","author":"feichtenhofer","year":"2016","journal-title":"Proc of the IEEE Conf on Comp Vision and Pattern Recognition (CVPR)"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054200.pdf?arnumber=9054200","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:08:59Z","timestamp":1656374939000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054200\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054200","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}