{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T13:59:48Z","timestamp":1766066388070,"version":"3.37.3"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001459","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","award":["MOE2012-TIF-2-G-016"],"award-info":[{"award-number":["MOE2012-TIF-2-G-016"]}],"id":[{"id":"10.13039\/501100001459","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":[[2015,1]]},"DOI":"10.1109\/tcsvt.2014.2333151","type":"journal-article","created":{"date-parts":[[2014,6,25]],"date-time":"2014-06-25T18:29:46Z","timestamp":1403720986000},"page":"77-86","source":"Crossref","is-referenced-by-count":69,"title":["STAP: Spatial-Temporal Attention-Aware Pooling for Action Recognition"],"prefix":"10.1109","volume":"25","author":[{"given":"Tam V.","family":"Nguyen","sequence":"first","affiliation":[]},{"given":"Zheng","family":"Song","sequence":"additional","affiliation":[]},{"given":"Shuicheng","family":"Yan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1109\/TPAMI.2011.146","article-title":"Image signature: Highlighting sparse salient regions","volume":"34","author":"hou","year":"2012","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref38","first-page":"45","article-title":"Nonparametric bottom-up saliency detection by self-resemblance","author":"seo","year":"2009","journal-title":"Proc Comput Vis Pattern Recognit (CVPR)"},{"key":"ref33","first-page":"3426","article-title":"Hierarchical matching with side information for image classification","author":"chen","year":"2012","journal-title":"Proc Comput Vis Pattern Recognit (CVPR)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.341"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.214"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.341"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206596"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995506"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.89"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/507072.507078"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"ref27","first-page":"101","article-title":"Depth matters: Influence of depth cues on visual saliency","author":"lang","year":"2012","journal-title":"Proc 12th Eur Conf Comput Vis (ECCV)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408988"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1282280.1282340"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-9794-4"},{"key":"ref24","first-page":"545","article-title":"Graph-based visual saliency","author":"harel","year":"2006","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"Saliency based on information maximization","author":"bruce","year":"2005","journal-title":"Advances in neural information processing systems"},{"key":"ref26","first-page":"681","article-title":"Dynamic visual attention: Searching for coding length increments","author":"hou","year":"2008","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383267"},{"key":"ref50","first-page":"707","article-title":"Spatio-temporal phrases for activity recognition","author":"zhang","year":"2012","journal-title":"Proc 12th Eur Conf Comput Vis (ECCV)"},{"key":"ref51","first-page":"494","article-title":"Object, scene and actions: Combining multiple features for human action recognition","author":"ikizler-cinbis","year":"2010","journal-title":"Proc 11th Eur Conf Comput Vis (ECCV)"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.2307\/3001968"},{"key":"ref55","first-page":"404","article-title":"Surf: Speeded up robust features","author":"bay","year":"2006","journal-title":"Proc 9th Eur Conf Comput Vis (ECCV)"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995624"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995496"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5244\/C.23.124"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206779"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1080\/13506280902771138"},{"key":"ref12","first-page":"650","article-title":"An efficient dense and scale-invariant spatio-temporal interest point detector","author":"willems","year":"2008","journal-title":"Proc 10th Eur Conf Comput Vis (ECCV)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref14","first-page":"428","article-title":"Human detection using oriented histograms of flow and appearance","author":"dalal","year":"2006","journal-title":"Proc Eur Conf Comp Vis (ECCV)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459154"},{"key":"ref16","first-page":"674","article-title":"An iterative image registration technique with an application to stereo vision","author":"lucas","year":"1981","journal-title":"Proc Int Joint Conf Artif Intell (IJCAI)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995353"},{"key":"ref18","first-page":"1378","article-title":"Object bank: A high-level image representation for scene classification & semantic feature sparsification","author":"li","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247806"},{"key":"ref4","first-page":"2004","article-title":"Hierarchical spatio-temporal context modeling for action recognition","author":"sun","year":"2009","journal-title":"Proc Comput Vis Pattern Recognit (CVPR)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5244\/C.24.95"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.99"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539881"},{"key":"ref9","first-page":"842","article-title":"Dynamic eye movement datasets and learnt saliency models for visual action recognition","author":"mathe","year":"2012","journal-title":"Proc 12th Eur Conf Comput Vis (ECCV)"},{"key":"ref46","first-page":"1996","article-title":"Recognizing realistic actions from videos ‘in the wild’","author":"liu","year":"2009","journal-title":"Proc Comput Vis Pattern Recognit (CVPR)"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874249"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.144"},{"key":"ref42","first-page":"363","article-title":"Two-frame motion estimation based on polynomial expansion","author":"farneb\u00e4ck","year":"2003","journal-title":"Proc Scandinavian Conf Image Anal (SCIA)"},{"key":"ref41","article-title":"Predicting human gaze using low-level saliency combined with face detection","author":"cerf","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"ref44","article-title":"Support vector method for function approximation, regression estimation and signal processing","author":"vapnik","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502128"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/7001735\/06844027.pdf?arnumber=6844027","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:04:17Z","timestamp":1642003457000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6844027\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,1]]},"references-count":56,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2014.2333151","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2015,1]]}}}