{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,28]],"date-time":"2026-06-28T07:32:46Z","timestamp":1782631966019,"version":"3.54.5"},"reference-count":67,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,6]]},"DOI":"10.1109\/cvpr.2015.7298839","type":"proceedings-article","created":{"date-parts":[[2015,10,15]],"date-time":"2015-10-15T22:42:06Z","timestamp":1444948926000},"page":"2264-2273","source":"Crossref","is-referenced-by-count":76,"title":["Can humans fly? Action understanding with multiple classes of actors"],"prefix":"10.1109","author":[{"given":"Chenliang","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"Shao-Hang Hsieh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caiming","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason J.","family":"Corso","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.341"},{"key":"ref38","article-title":"Recognizing realistic actions from videos “in the wild","author":"liu","year":"0","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition 2009"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref32","article-title":"Beyond actions: Discriminative models for contextual group activities","author":"lan","year":"0","journal-title":"Advances in Neural Information Processing Systems 2010"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-011-0489-0"},{"key":"ref30","article-title":"What, where and how many? combining object detectors and crfs","author":"ladicky","year":"2010","journal-title":"European Conference on Computer Vision"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995353"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.340"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.273"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126471"},{"key":"ref60","article-title":"Evaluation of super-voxel methods for early video processing","author":"xu","year":"2012","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref62","article-title":"Streaming hierarchical video segmentation","author":"xu","year":"2012","journal-title":"European Conference on Computer Vision"},{"key":"ref61","article-title":"A study of actor and action semantic retention in video su-pervoxel segmentation","author":"xu","year":"2014","journal-title":"International Journal of Semantic Computing"},{"key":"ref63","article-title":"Describing the scene as a whole: Joint object detection, scene classification and semantic segmentation","author":"yao","year":"2012","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref28","article-title":"Joint semantic segmentation and 3d reconstruction from monocular video","author":"kundu","year":"0","journal-title":"European Conference on Computer Vision 2014"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.87"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.280"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.411"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459248"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.442"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.283"},{"key":"ref1","article-title":"Video in sentences out","author":"barbu","year":"0","journal-title":"UAI 2012"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_31"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.100"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.234"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383512"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"ref26","article-title":"Efficient inference in fully connected crfs with gaussian edge potentials","author":"krahenbuhl","year":"0","journal-title":"Advances in Neural Information Processing Systems 2011"},{"key":"ref25","article-title":"Motion interchange patterns for action recognition in unconstrained videos","author":"kliper-gross","year":"2012","journal-title":"European Conference on Computer Vision"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630632"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0574-z"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.341"},{"key":"ref55","article-title":"Understanding natural language commands for robotic navigation and mobile manipulation","author":"tellex","year":"2011","journal-title":"inAAAI\/IAAI"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.321"},{"key":"ref53","article-title":"Indoor segmentation and support inference from rgbd images","author":"silberman","year":"0","journal-title":"European Conference on Computer Vision 2012"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0109-1"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2466715.2466723"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70711"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459211"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.83"},{"key":"ref16","article-title":"Weakly supervised learning of object segmentations from web-scale video","author":"hartmann","year":"0","journal-title":"European Conference on Computer Vision Workshops 2012"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995470"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-0031-y"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.739"},{"key":"ref4","article-title":"Segmentation and recognition using structure from motion point clouds","author":"brostow","year":"0","journal-title":"European Conference on Computer Vision 2008"},{"key":"ref3","article-title":"Interactive graph cuts for optimal boundary region segmentation of objects in nd images","author":"boykov","year":"0","journal-title":"ICCV 2001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.101"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.267"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995711"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248007"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587727"},{"key":"ref45","article-title":"Recognizing 50 human action categories of web videos","author":"reddy","year":"2012","journal-title":"Machine Vision and Applications Journal"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247806"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0090-8"},{"key":"ref42","article-title":"Modeling temporal structure of decomposable motion segments for activity classification","author":"niebles","year":"2010","journal-title":"European Conference on Computer Vision"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126279"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.223"}],"event":{"name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Boston, MA, USA","start":{"date-parts":[[2015,6,7]]},"end":{"date-parts":[[2015,6,12]]}},"container-title":["2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7293313\/7298593\/07298839.pdf?arnumber=7298839","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,24]],"date-time":"2017-03-24T21:28:45Z","timestamp":1490390925000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7298839\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/cvpr.2015.7298839","relation":{},"subject":[],"published":{"date-parts":[[2015,6]]}}}