{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T14:58:16Z","timestamp":1761490696099},"reference-count":34,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1109\/icpr.2018.8545710","type":"proceedings-article","created":{"date-parts":[[2018,11,30]],"date-time":"2018-11-30T00:17:38Z","timestamp":1543537058000},"source":"Crossref","is-referenced-by-count":68,"title":["End-to-end Video-level Representation Learning for Action Recognition"],"prefix":"10.1109","author":[{"given":"Jiagang","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Action Recognition with Dynamic Image Networks","author":"bilen","year":"2017","journal-title":"TPAMI"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref30","author":"wang","year":"2017","journal-title":"Eigen Evolution Pooling for Human Action Recognition"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref12","author":"soomro","year":"2012","journal-title":"Ucf10l A dataset of 101 human actions classes from videos in the wild"},{"key":"ref13","article-title":"Action-VLAD: Learning spatio-temporal aggregation for action classification","author":"girdhar","year":"2017","journal-title":"CVPR"},{"key":"ref14","article-title":"ImageNet classication with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0859-0"},{"key":"ref16","author":"varol","year":"2016","journal-title":"Long-term temporal convolutions for action recognition"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref18","article-title":"A duality based approach for realtime tv-Ll optical flow","author":"zach","year":"2007","journal-title":"29th DAGM Symposium on Pattern Recognition"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.168"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref4","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":"10.1007\/s11263-012-0594-8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref6","author":"wang","year":"2017","journal-title":"Temporal segment networks for action recognition in videos"},{"key":"ref29","author":"xiong","year":"0","journal-title":"TSN Pretrained Models on Kinetics Dataset"},{"key":"ref5","article-title":"Temporal segment networks: towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"ECCV"},{"key":"ref8","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"ICML"},{"key":"ref7","author":"jia","year":"2014","journal-title":"Caffe Convolutional Architecture for Fast Feature Embedding"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.522"},{"key":"ref1","article-title":"Beyond Gaussian Pyramid: Multi-skip Feature Stacking for Action Recognition","author":"lan","year":"2015","journal-title":"CVPR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.161"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref21","article-title":"Spatiotemporal Residual Networks for Video Action Recognition","author":"feichtenhofer","year":"2016","journal-title":"NIPS"},{"key":"ref24","author":"zhu","year":"2017","journal-title":"Learning Gating ConvNet for Two-Stream based Methods in Action Recognition"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.435"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref25","author":"wang","year":"2015","journal-title":"Temporal pyramid pooling based convolutional neural networks for action recognition"}],"event":{"name":"2018 24th International Conference on Pattern Recognition (ICPR)","location":"Beijing","start":{"date-parts":[[2018,8,20]]},"end":{"date-parts":[[2018,8,24]]}},"container-title":["2018 24th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8527858\/8545020\/08545710.pdf?arnumber=8545710","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T16:55:20Z","timestamp":1643302520000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8545710\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icpr.2018.8545710","relation":{},"subject":[],"published":{"date-parts":[[2018,8]]}}}