{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:14:55Z","timestamp":1776442495136,"version":"3.51.2"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"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":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9533515","type":"proceedings-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T17:27:41Z","timestamp":1632158861000},"page":"1-9","source":"Crossref","is-referenced-by-count":7,"title":["Multi-Temporal Convolutions for Human Action Recognition in Videos"],"prefix":"10.1109","author":[{"given":"Alexandros","family":"Stergiou","sequence":"first","affiliation":[]},{"given":"Ronald","family":"Poppe","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"More is less: Learning efficient video representations by big-little network and depthwise temporal aggregation","author":"fan","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref38","article-title":"Accurate, large minibatch SGD: training ImageNet in 1 hour","author":"goyal","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref33","article-title":"Refining activation downsam-nling with SoftPool","author":"stergiou","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref32","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref31","article-title":"TAM: Temporal adaptive module for video recognition","author":"liu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.11.012"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00023"},{"key":"ref36","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00817"},{"key":"ref27","first-page":"9401","article-title":"Gather-excite: Exploiting feature context in convolutional neural networks","author":"hu","year":"2018","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1088\/0954-898X\/6\/3\/003"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.102799"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref24","first-page":"12 056","article-title":"Learning spatiotemporal representation with local and global diffusion","author":"qiu","year":"0","journal-title":"Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00353"},{"key":"ref10","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref11","first-page":"3468","article-title":"Spatiotemporal residual networks for video action recognition","author":"feichtenhofer","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00188"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.168"},{"key":"ref14","first-page":"29","article-title":"Se-quential deep learning for human action recognition","author":"baccouche","year":"0","journal-title":"Int Workshop on Human Behavior Understanding"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref16","article-title":"Would mega-scale datasets further enhance spatiotemporal 3D CNNs?","author":"kataoka","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_22"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref4","first-page":"327","article-title":"Action identification theory","volume":"1","author":"vallacher","year":"2011","journal-title":"Handbook of Theories of Social Psychology"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2901464"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00876"},{"key":"ref7","article-title":"A short note on the Kinetics-700 human action dataset","author":"carreira","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01232"},{"key":"ref9","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"ArXiv Preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21236\/ADA164453"},{"key":"ref48","article-title":"Stochastic pooling for regularization of deep convolutional neural networks","author":"zeiler","year":"0","journal-title":"International Conference on Learning Representationsm (ICLR)"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2000.861302"},{"key":"ref42","article-title":"Assemblenet: Searching for multi-stream neural connectivity in video architectures","author":"ryoo","year":"0","journal-title":"Inernational Conference on Learning Representations (ICLR)"},{"key":"ref41","article-title":"Neural architecture search with reinforcement learning","author":"zoph","year":"0","journal-title":"Inernational Conference on Learning Representations (ICLR)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00806"},{"key":"ref43","first-page":"803","article-title":"Temporal relational reasoning in videos","author":"zhou","year":"0","journal-title":"European Conference on Computer Vision (ECCV)"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","location":"Shenzhen, China","start":{"date-parts":[[2021,7,18]]},"end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09533515.pdf?arnumber=9533515","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:46:16Z","timestamp":1652183176000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9533515\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9533515","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}