{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:34:31Z","timestamp":1778049271681,"version":"3.51.4"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"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":[[2019,6]]},"DOI":"10.1109\/cvpr.2019.00137","type":"proceedings-article","created":{"date-parts":[[2020,1,9]],"date-time":"2020-01-09T21:06:13Z","timestamp":1578603973000},"page":"1278-1287","source":"Crossref","is-referenced-by-count":173,"title":["AdaFrame: Adaptive Frame Selection for Fast Video Recognition"],"prefix":"10.1109","author":[{"given":"Zuxuan","family":"Wu","sequence":"first","affiliation":[{"name":"UMD"}]},{"given":"Caiming","family":"Xiong","sequence":"additional","affiliation":[{"name":"Salesforce Research"}]},{"given":"Chih-Yao","family":"Ma","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}]},{"given":"Richard","family":"Socher","sequence":"additional","affiliation":[{"name":"Salesforce"}]},{"given":"Larry S.","family":"Davis","sequence":"additional","affiliation":[{"name":"Univ. of Maryland"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.441"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.297"},{"key":"ref33","author":"wu","year":"2018","journal-title":"Frontiers of multimedia research chapter Deep Learning for Video Classification and Captioning"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00919"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00631"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_25"},{"key":"ref37","article-title":"Memory architectures in recurrent neural network language models","author":"yogatama","year":"2018","journal-title":"ICLRE"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"ref35","article-title":"Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification","author":"xie","year":"2018","journal-title":"ECCV"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref10","article-title":"Super fast event recognition in internet videos","author":"jiang","year":"2015","journal-title":"IEEE TMM"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2670560"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.214"},{"key":"ref13","article-title":"Deciding how to decide: Dynamic routing in artificial neural networks","author":"mcgill","year":"2017","journal-title":"ICML"},{"key":"ref14","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"NIPS"},{"key":"ref15","article-title":"Autofocus: Efficient multi-scale inference","author":"najibi","year":"2018","journal-title":"arXiv preprint arXiv 1812 02588"},{"key":"ref16","article-title":"Beyond short snippets: Deep networks for video classification","author":"ng","year":"2015","journal-title":"CVPR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00166"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref19","article-title":"Twostream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"NIPS"},{"key":"ref28","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"ECCV"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.194"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000013087.49260.fb"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/98"},{"key":"ref6","article-title":"Adaptive computation time for recurrent neural networks","author":"graves","year":"2016","journal-title":"arXiv preprint arXiv 1603 05474"},{"key":"ref29","author":"wang","year":"2018","journal-title":"Non-local neural networks"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00724"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","article-title":"A survey on policy search for robotics","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref9","article-title":"Multiscale dense convolutional networks for efficient prediction","author":"huang","year":"2018","journal-title":"ICLRE"},{"key":"ref1","article-title":"Capacity and trainability in recurrent neural networks","author":"collins","year":"2017","journal-title":"ICLRE"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_48"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.11231","article-title":"Inception-v4, inceptionresnet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"AAAI"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref24","article-title":"C3d: Generic features for video analysis","author":"tran","year":"2015","journal-title":"ICCV"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"ref26","article-title":"Convolutional networks with adaptive inference graphs","author":"veit","year":"2018","journal-title":"ECCV"},{"key":"ref25","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"}],"event":{"name":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Long Beach, CA, USA","start":{"date-parts":[[2019,6,15]]},"end":{"date-parts":[[2019,6,20]]}},"container-title":["2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8938205\/8953184\/08953643.pdf?arnumber=8953643","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T18:34:01Z","timestamp":1755714841000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8953643\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/cvpr.2019.00137","relation":{},"subject":[],"published":{"date-parts":[[2019,6]]}}}