{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T21:57:06Z","timestamp":1790200626806,"version":"4.1.0"},"reference-count":42,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,5]]},"DOI":"10.1109\/icra.2017.7989018","type":"proceedings-article","created":{"date-parts":[[2017,7,25]],"date-time":"2017-07-25T21:44:28Z","timestamp":1501019068000},"page":"138-145","source":"Crossref","is-referenced-by-count":7,"title":["DAP3D-Net: Where, what and how actions occur in videos?"],"prefix":"10.1109","author":[{"given":"Li","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298735"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"ref32","article-title":"C3d: generic features for video analysis","author":"tran","year":"2015","journal-title":"ICCV"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806222"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref37","author":"liu","year":"2009","journal-title":"Beyond pixels Exploring new representations and applications for motion analysis"},{"key":"ref36","article-title":"Learning discriminative representations from rgb-d video data","author":"liu","year":"2013","journal-title":"IJCAI"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.38"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"ref10","author":"liu","year":"2013","journal-title":"Synthesis of spatio-temporal descriptors for dynamic hand gesture recognition using genetic programming"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.341"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.100"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.177"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995353"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301331"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2013.2258152"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-013-0349-3"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.209"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref19","author":"soomro","year":"2012","journal-title":"Ucf101 A dataset of 1 0 1 human actions classes from videos in the wild"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299097"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587597"},{"key":"ref3","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"NIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298962"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2399172"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0861-6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2491925"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15567-3_11"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2014.07.006"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref22","author":"ren","year":"2015","journal-title":"Faster R-CNN Towards realtime object detection with region proposal networks"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.10"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5244\/C.25.65"},{"key":"ref23","article-title":"Dave: A unified framework for fast vehicle detection and annotation","author":"zhou","year":"2016","journal-title":"ECCV"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2017.01.013"}],"event":{"name":"2017 IEEE International Conference on Robotics and Automation (ICRA)","location":"Singapore, Singapore","start":{"date-parts":[[2017,5,29]]},"end":{"date-parts":[[2017,6,3]]}},"container-title":["2017 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7960754\/7988677\/07989018.pdf?arnumber=7989018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,10,3]],"date-time":"2017-10-03T03:21:38Z","timestamp":1507000898000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7989018\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icra.2017.7989018","relation":{},"subject":[],"published":{"date-parts":[[2017,5]]}}}