{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:05:23Z","timestamp":1730297123972,"version":"3.28.0"},"reference-count":36,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/smartworld.2018.00123","type":"proceedings-article","created":{"date-parts":[[2018,12,6]],"date-time":"2018-12-06T19:38:21Z","timestamp":1544125101000},"page":"596-602","source":"Crossref","is-referenced-by-count":1,"title":["Constructing Hierarchical Spatiotemporal Information for Action Recognition"],"prefix":"10.1109","author":[{"given":"Guangle","family":"Yao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiandan","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Lei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianyuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Unsupervised learning of video representations using LSTMs","author":"srivastava","year":"2015","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477589"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.172"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.604"},{"key":"ref36","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref35","article-title":"Return of the devil in the details: delving deep into convolutional nets","author":"chatfield","year":"2014","journal-title":"Proceedings of the British Machine Vision Conference"},{"key":"ref34","article-title":"Modeling spatial-temporal clues in a hybrid deep learning framework for video classification","author":"wu","year":"2018","journal-title":"Proceedings of the ACM Multimedia Conference"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","article-title":"ConvNet Architecture Search for Spatiotemporal Feature Learning","author":"tran","year":"2017","journal-title":"arXiv preprint arXiv 1708 05227"},{"key":"ref12","article-title":"Long-term temporal convolutions for action recognition","author":"varol","year":"2017","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2016.2569061"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref15","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"ref16","article-title":"Towards good practices for very deep two-stream convnets","author":"wang","year":"2015","journal-title":"arXiv preprint arXiv 1507 02159"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref18","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"Proceedings of the European Conference on Computer Vision"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.231"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2599174"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref6","first-page":"495","article-title":"3D convolutional neural networks for human action recognition","author":"ji","year":"2010","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.212"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref8","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"International Conference on Learning Representations"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref2","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proceedings of the Annual Conference on Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref20","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","volume":"150","author":"peng","year":"2016","journal-title":"Comput Vis Image Underst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref21","first-page":"214","article-title":"A duality based approach for realtime tv-Ll optical flow","author":"zach","year":"2007","journal-title":"Proceedings of the DAGM Symposium on Pattern Recognition"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref23","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"Univ Central Florida Tech Rep"},{"key":"ref26","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":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"}],"event":{"name":"2018 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld\/SCALCOM\/UIC\/ATC\/CBDCom\/IOP\/SCI)","start":{"date-parts":[[2018,10,8]]},"location":"Guangzhou, China","end":{"date-parts":[[2018,10,12]]}},"container-title":["2018 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld\/SCALCOM\/UIC\/ATC\/CBDCom\/IOP\/SCI)"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx7\/8533596\/8559978\/08560101.pdf?arnumber=8560101","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T07:47:44Z","timestamp":1643269664000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/ieeexplore.ieee.org\/document\/8560101\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":36,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/smartworld.2018.00123","relation":{},"subject":[],"published":{"date-parts":[[2018,10]]}}}