{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T19:48:23Z","timestamp":1784922503492,"version":"3.55.0"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2017,12,1]],"date-time":"2017-12-01T00:00:00Z","timestamp":1512086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/tcsvt.2016.2576761","type":"journal-article","created":{"date-parts":[[2016,6,7]],"date-time":"2016-06-07T14:10:44Z","timestamp":1465308644000},"page":"2613-2622","source":"Crossref","is-referenced-by-count":96,"title":["Temporal Pyramid Pooling-Based Convolutional Neural Network for Action Recognition"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5649-0086","authenticated-orcid":false,"given":"Peng","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanzhouhan","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingqiao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298993"},{"key":"ref32","first-page":"1871","article-title":"LIBLINEAR: A library for large linear classification","volume":"9","author":"fan","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref31","author":"soomro","year":"2012","journal-title":"Ucf101 A Dataset of 101 Human Actions Classes from Videos in the Wild"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.235"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.330"},{"key":"ref34","first-page":"842","article-title":"Dynamic eye movement datasets and learnt saliency models for visual action recognition","author":"mathe","year":"2012","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref10","first-page":"2004","article-title":"Hierarchical spatio-temporal context modeling for action recognition","author":"sun","year":"2009","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref11","first-page":"428","article-title":"Human detection using oriented histograms of flow and appearance","author":"dalal","year":"2006","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref12","author":"peng","year":"2014","journal-title":"Bag of visual words and fusion methods for action recognition Comprehensive study and good practice"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.83"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_38"},{"key":"ref15","first-page":"1341","article-title":"Submodular attribute selection for action recognition in video","author":"zheng","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502089"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.336"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.442"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2807412"},{"key":"ref4","first-page":"143","article-title":"Improving the Fisher kernel for large-scale image classification","author":"perronnin","year":"2010","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.374"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref6","first-page":"248","article-title":"ImageNet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"ref5","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref7","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459154"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref20","author":"tran","year":"2014","journal-title":"C3d generic features for video analysis"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298691"},{"key":"ref21","author":"mansimov","year":"2015","journal-title":"Initialization Strategies of Spatio-Temporal Convolutional Neural Networks"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref26","first-page":"1","article-title":"Return of the devil in the details: Delving deep into convolutional nets","author":"chatfield","year":"2014","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref25","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","author":"srivastava","year":"2015","journal-title":"Proc ICML"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/8186326\/07484698.pdf?arnumber=7484698","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:41:45Z","timestamp":1641987705000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7484698\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":38,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2016.2576761","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,12]]}}}