{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T20:46:35Z","timestamp":1761597995168,"version":"3.37.3"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61602014"],"award-info":[{"award-number":["61602014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Fundamental Research Program","award":["JCYJ20170818141120312"],"award-info":[{"award-number":["JCYJ20170818141120312"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Province Scientific Research on Big Data","award":["U1611461"],"award-info":[{"award-number":["U1611461"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2018]]},"DOI":"10.1109\/access.2018.2872759","type":"journal-article","created":{"date-parts":[[2018,9,28]],"date-time":"2018-09-28T20:36:50Z","timestamp":1538167010000},"page":"59126-59140","source":"Crossref","is-referenced-by-count":9,"title":["Active Temporal Action Detection in Untrimmed Videos Via Deep Reinforcement Learning"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3688-6766","authenticated-orcid":false,"given":"Nannan","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui-Wen","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ge","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.675"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2771462"},{"key":"ref30","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":"ref37","first-page":"768","article-title":"DAPs: Deepaction proposals for action understanding","author":"escorcia","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.392"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.155"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.617"},{"journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition","year":"2014","author":"simonyan","key":"ref61"},{"key":"ref63","first-page":"1","article-title":"End-to-end, single-stream temporal action detection in untrimmed videos","author":"buch","year":"2017","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref28","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"journal-title":"Cascaded boundary regression for temporal action detection","year":"2017","author":"gao","key":"ref64"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"article-title":"The LEAR submission at Thumos 2014","year":"2014","author":"oneata","key":"ref66"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.341"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.337"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref1","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.342"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2404779"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.214"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1016\/j.cviu.2010.10.002","article-title":"A survey of vision-based methods for action representation, segmentation and recognition","volume":"115","author":"weinland","year":"2011","journal-title":"Comput Vis Image Understand"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1922649.1922653"},{"journal-title":"Review of action recognition and detection methods","year":"2016","author":"kang","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2017.01.010"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.033"},{"journal-title":"Ucf101 A Dataset of 101 Human Actions Classes from Videos in the Wild","year":"2012","author":"soomro","key":"ref51"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.228"},{"journal-title":"THUMOS Challenge Action Recognition with A Large Number of Classes","year":"2014","author":"jiang","key":"ref58"},{"key":"ref57","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1145\/2671188.2749404","article-title":"Bag-of-fragments: Selecting and encoding video fragments for event detection and recounting","author":"mettes","year":"2015","journal-title":"Proc ACM Int Conf Multimedia Retr (ICMR)"},{"key":"ref56","first-page":"1914","article-title":"Fast temporal activity proposals for efficient detection of human actions in untrimmed videos","author":"caba","year":"2016","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"journal-title":"Proc BigLearn Adv Neural Inf Process Syst Workshop","year":"2011","author":"collobert","key":"ref55"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"journal-title":"Reinforcement learning–an introduction","year":"1998","author":"sutton","key":"ref53"},{"journal-title":"A self-adaptive proposal model for temporal action detection based on reinforcement learning","year":"2017","author":"huang","key":"ref52"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.286"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"journal-title":"Deep learning for detecting multiple space-time action tubes in videos","year":"2016","author":"saha","key":"ref40"},{"key":"ref12","first-page":"127","article-title":"Tree-structured reinforcement learning for sequential object localization","author":"jie","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"journal-title":"Hierarchical Object Detection with Deep Reinforcement Learning","year":"2016","author":"bellver","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref17","first-page":"428","article-title":"Human detection using oriented histograms of flow and appearance","author":"dalal","year":"2006","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.219"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126349"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref3","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"Proc ECCV"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"journal-title":"Efficient action detection in untrimmed videos via multi-task learning","year":"2016","author":"zhu","key":"ref5"},{"journal-title":"A pursuit of temporal accuracy in general activity detection","year":"2017","author":"xiong","key":"ref8"},{"key":"ref7","first-page":"143","article-title":"Improving the fisher kernel for large-scale image classification","author":"perronnin","year":"2010","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref49","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref45","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":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.316"},{"key":"ref47","first-page":"391","article-title":"Edge boxes: Locating object proposals from edges","author":"zitnick","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref42","first-page":"744","article-title":"Multi-region two-stream R-CNN for action detection","author":"peng","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"journal-title":"Online Real-time Multiple Spatiotemporal Action Localisation and Prediction[J]","year":"2016","author":"singh","key":"ref41"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.122"},{"journal-title":"Towards weakly-supervised action localization","year":"2016","author":"weinzaepfel","key":"ref43"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8274985\/08476583.pdf?arnumber=8476583","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T16:43:24Z","timestamp":1643215404000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8476583\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/access.2018.2872759","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2018]]}}}