{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T06:32:08Z","timestamp":1762324328748,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/icip.2018.8451662","type":"proceedings-article","created":{"date-parts":[[2018,9,7]],"date-time":"2018-09-07T13:59:22Z","timestamp":1536328762000},"page":"808-812","source":"Crossref","is-referenced-by-count":11,"title":["Two-Stream Designed 2D\/3D Residual Networks with Lstms for Action Recognition in Videos"],"prefix":"10.1109","author":[{"given":"Lifei","family":"Song","sequence":"first","affiliation":[]},{"given":"Liguo","family":"Weng","sequence":"additional","affiliation":[]},{"given":"Lingfeng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xia","family":"Min","sequence":"additional","affiliation":[]},{"given":"Chunhong","family":"Pan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_38"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.cviu.2016.03.013","article-title":"Bag of visual words and fusion methods for action recognition: Comprehensive study and good practice","volume":"150","author":"peng","year":"2016","journal-title":"Computer Vision and Image Understanding"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"journal-title":"Towards good practices for very deep two-stream convnets","year":"2015","author":"wang","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref19","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.522"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.330"},{"key":"ref27","first-page":"204","article-title":"Beyond gaussian pyramid: Multi-skip feature stacking for action recognition","author":"lan","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref3","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"},{"key":"ref6","first-page":"9","article-title":"Actlon recognition based on a bag of 3d points","author":"li","year":"2010","journal-title":"Computer Vision and Pattern Recognition Workshops (CVPRW) 2010 IEEE Computer Society Conference On IEEE"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984061"},{"key":"ref7","first-page":"4694","article-title":"Beyond short snippets: Deep networks for video classification","author":"ng","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref9","article-title":"Long-term temporal convolutions for action recognition","author":"varol","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"journal-title":"Ucf101 A Dataset of 101 Human Actions Classes from Videos in the Wild","year":"2012","author":"soomro","key":"ref20"},{"journal-title":"Youtube-8m A large-scale video classification benchmark","year":"2016","author":"abu-ei-haija","key":"ref22"},{"key":"ref21","first-page":"571","article-title":"Hmdb51: A large video database for human motion recognition","volume":"12","author":"kuehne","year":"2013","journal-title":"High Performance Computing in Science and Engineering"},{"key":"ref24","first-page":"3468","article-title":"S-patiotemporal residual networks for video action recognition","author":"feichtenhofer","year":"0","journal-title":"Neural Inform Process Syst 2016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Advances in neural information processing systems"},{"journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition","year":"2014","author":"simonyan","key":"ref25"}],"event":{"name":"2018 25th IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2018,10,7]]},"location":"Athens","end":{"date-parts":[[2018,10,10]]}},"container-title":["2018 25th IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8436606\/8451009\/08451662.pdf?arnumber=8451662","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T06:52:54Z","timestamp":1643179974000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8451662\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icip.2018.8451662","relation":{},"subject":[],"published":{"date-parts":[[2018,10]]}}}