{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:19:43Z","timestamp":1730254783416,"version":"3.28.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"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":[[2021,1,10]]},"DOI":"10.1109\/icpr48806.2021.9411997","type":"proceedings-article","created":{"date-parts":[[2021,5,5]],"date-time":"2021-05-05T22:15:54Z","timestamp":1620252954000},"page":"10010-10017","source":"Crossref","is-referenced-by-count":10,"title":["Region-based Non-local Operation for Video Classification"],"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":"ref39","first-page":"12 056","article-title":"Learning spatiotemporal representation with local and global diffusion","author":"qiu","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog (CVPR)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref32","first-page":"3","article-title":"Cbam: Convolutional block attention module","author":"woo","year":"0","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref36","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"37","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref35","first-page":"4510","article-title":"Mo-bilenetv2: Inverted residuals and linear bottlenecks","author":"sandler","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog (CVPR)"},{"key":"ref34","first-page":"6510","article-title":"Compact generalized non-local network","author":"yue","year":"0","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref40","first-page":"399","article-title":"Videos as space-time region graphs","author":"wang","year":"0","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref12","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Int Conf Learning Rep (ICLR)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref14","first-page":"2818","article-title":"Rethinking the inception architecture for comp. vision","author":"szegedy","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog (CVPR)"},{"key":"ref15","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"0","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref18","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref29","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.38"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref22","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","volume":"lncs 9912","author":"wang","year":"0","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref21","article-title":"Learning spatio-temporal representations with temporal squeeze pooling","author":"huang","year":"0","journal-title":"Proc IEEE Int Conf on Acoustics Speech and Signal Proc (ICASSP)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00117"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15567-3_11"},{"key":"ref26","first-page":"305","article-title":"Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification","volume":"lncs 11219","author":"xie","year":"0","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"}],"event":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2021,1,10]]},"location":"Milan, Italy","end":{"date-parts":[[2021,1,15]]}},"container-title":["2020 25th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9411940\/9411911\/09411997.pdf?arnumber=9411997","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:40:53Z","timestamp":1652182853000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9411997\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,10]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icpr48806.2021.9411997","relation":{},"subject":[],"published":{"date-parts":[[2021,1,10]]}}}