{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T21:40:08Z","timestamp":1750369208093,"version":"3.41.0"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1109\/icassp.2017.7952430","type":"proceedings-article","created":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T21:35:36Z","timestamp":1497994536000},"page":"1617-1621","source":"Crossref","is-referenced-by-count":4,"title":["Dynamic tracking attention model for action recognition"],"prefix":"10.1109","author":[{"given":"Chien-Yao","family":"Wang","sequence":"first","affiliation":[]},{"given":"Chin-Chin","family":"Chiang","sequence":"additional","affiliation":[]},{"given":"Jian-Jiun","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Jia-Ching","family":"Wang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291311"},{"key":"ref11","article-title":"A spatiotemporal descriptor based on 3d-gradients","author":"klaser","year":"2008","journal-title":"British Machine Vision Conference"},{"key":"ref12","article-title":"An efficient dense and scale-invariant spatio-temporal interest point detector","author":"willems","year":"2008","journal-title":"European Conference on Computer Vision"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2013.741"},{"journal-title":"Show attend and tell Neural image caption generation with visual attention","year":"2015","author":"xu","key":"ref14"},{"key":"ref15","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408988"},{"journal-title":"Temporal pyramid pooling based convolutional neural networks for action recognition","year":"2015","author":"wang","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2004-376","article-title":"Convolutional networks for speech detection","author":"sukittanon","year":"2004","journal-title":"InterSpeech"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref5","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","author":"he","year":"2014","journal-title":"European Conference on Computer Vision"},{"journal-title":"Densecap Fully convolutional localization networks for dense captioning","year":"2015","author":"johnson","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref2","article-title":"Sign language recognition using convolutional neural networks","author":"pigou","year":"2014","journal-title":"European Conference on Computer Vision Workshop"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477042"},{"key":"ref20","article-title":"Beyond short snippets: Deep networks for video classification","author":"ng","year":"2015","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref21","article-title":"High accuracy optical flow estimation based on a theory for warping","author":"brox","year":"2004","journal-title":"European Conference on Computer Vision"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref23","article-title":"Recognizing realistic actions from videos in the wild","author":"liu","year":"2009","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"journal-title":"Action recognition using visual attention","year":"2015","author":"sharma","key":"ref25"}],"event":{"name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2017,3,5]]},"location":"New Orleans, LA","end":{"date-parts":[[2017,3,9]]}},"container-title":["2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7943262\/7951776\/07952430.pdf?arnumber=7952430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T21:00:36Z","timestamp":1750366836000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7952430\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp.2017.7952430","relation":{},"subject":[],"published":{"date-parts":[[2017,3]]}}}