{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:19:35Z","timestamp":1769732375221,"version":"3.49.0"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672519"],"award-info":[{"award-number":["61672519"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771339"],"award-info":[{"award-number":["61771339"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004517","name":"Tianjin University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004517","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1109\/tcsvt.2019.2896029","type":"journal-article","created":{"date-parts":[[2019,1,31]],"date-time":"2019-01-31T20:58:45Z","timestamp":1548968325000},"page":"748-759","source":"Crossref","is-referenced-by-count":51,"title":["Temporal\u2013Spatial Mapping for Action Recognition"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6376-5068","authenticated-orcid":false,"given":"Xiaolin","family":"Song","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9145-9957","authenticated-orcid":false,"given":"Cuiling","family":"Lan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2531-3137","authenticated-orcid":false,"given":"Wenjun","family":"Zeng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6801-0510","authenticated-orcid":false,"given":"Junliang","family":"Xing","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3638-5566","authenticated-orcid":false,"given":"Xiaoyan","family":"Sun","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7521-7920","authenticated-orcid":false,"given":"Jingyu","family":"Yang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.270"},{"key":"ref38","author":"lin","year":"2017","journal-title":"Action recognition with coarse-to-fine deep feature integration and asynchronous fusion"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00054"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.522"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2712608"},{"key":"ref30","first-page":"581","article-title":"Action recognition with stacked Fisher vectors","author":"peng","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2862341"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2749159"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2666540"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2665359"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298789"},{"key":"ref2","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":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1922649.1922653"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.226"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912001"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2691768"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.235"},{"key":"ref50","first-page":"3468","article-title":"Spatiotemporal residual networks for video action recognition","author":"feichtenhofer","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.142"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964328"},{"key":"ref11","author":"wang","year":"2016","journal-title":"Hierarchical attention network for action recognition in videos"},{"key":"ref40","author":"shu","year":"2018","journal-title":"Hierarchical long short-term concurrent memory for human interaction recognition"},{"key":"ref12","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":"ref13","author":"simonyan","year":"2014","journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref17","author":"redmon","year":"2016","journal-title":"YOLO9000 Better Faster Stronger"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.168"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.219"},{"key":"ref3","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref6","first-page":"4694","article-title":"Beyond short snippets: Deep networks for video classification","author":"ng","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref8","author":"sharma","year":"2015","journal-title":"Action recognition using visual attention"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref9","author":"li","year":"2016","journal-title":"Videolstm convolves attends and flows for action recognition"},{"key":"ref46","author":"soomro","year":"2012","journal-title":"Ucf101 A Dataset of 101 Human Actions Classes from Videos in the Wild"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref47","article-title":"Network in network","author":"lin","year":"2014","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240572"},{"key":"ref44","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proceedings of the 32nd Intl Conf on Machine Learning"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9025308\/08630593.pdf?arnumber=8630593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:39:15Z","timestamp":1651070355000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8630593\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":52,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2019.2896029","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3]]}}}