{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:28:07Z","timestamp":1761060487401},"reference-count":52,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,10]]},"DOI":"10.1109\/iccv.2017.219","type":"proceedings-article","created":{"date-parts":[[2017,12,25]],"date-time":"2017-12-25T21:51:45Z","timestamp":1514238705000},"source":"Crossref","is-referenced-by-count":43,"title":["Joint Learning of Object and Action Detectors"],"prefix":"10.1109","author":[{"given":"Vicky","family":"Kalogeiton","sequence":"first","affiliation":[]},{"given":"Philippe","family":"Weinzaepfel","sequence":"additional","affiliation":[]},{"given":"Vittorio","family":"Ferrari","sequence":"additional","affiliation":[]},{"given":"Cordelia","family":"Schmid","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"NIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247807"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248065"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.175"},{"key":"ref30","article-title":"Learning to refine object segments","author":"pinheiro","year":"2016","journal-title":"ECCV"},{"key":"ref37","article-title":"Deep learning for detecting multiple space-time action tubes in videos","author":"saha","year":"2016","journal-title":"BMVC"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995711"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587727"},{"key":"ref34","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"NIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126383"},{"key":"ref27","article-title":"Deep captioning with multimodal recurrent neural networks (m-rnn)","author":"mao","year":"2015","journal-title":"ICLRE"},{"key":"ref29","article-title":"Multi-region two-stream r-cnn for action detection","author":"peng","year":"2016","journal-title":"ECCV"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.283"},{"key":"ref1","year":"2015","journal-title":"Imagenet large scale visual recognition challenge (ILSVRC)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995353"},{"key":"ref21","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"ECCV"},{"key":"ref24","article-title":"Visual relationship detection with language priors","author":"lu","year":"2016","journal-title":"ECCV"},{"key":"ref23","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"ECCV"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126229"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.341"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298839"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126386"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539893"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.83"},{"key":"ref40","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"ICLRE"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2551239"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.95"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.99"},{"key":"ref17","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.140"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.517"},{"key":"ref4","article-title":"Improving semantic embedding consistency by metric learning for zero-shot classiffication","author":"bucher","year":"2016","journal-title":"ECCV"},{"key":"ref3","article-title":"High accuracy optical flow estimation based on a theory for warping","author":"brox","year":"2004","journal-title":"ECCV"},{"key":"ref6","author":"everingham","year":"2007","journal-title":"The PASCAL Visual Object Classes Challenge 2007 Results"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298730"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.336"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"ref46","article-title":"A robust and efficient video representation for action recognition","author":"wang","year":"2015","journal-title":"IJCV"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990517"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.362"},{"key":"ref47","article-title":"Temporal segment networks: towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"ECCV"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref41","article-title":"UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild","author":"soomro","year":"2012","journal-title":"CRCV-TR-12-01"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"}],"event":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","location":"Venice","start":{"date-parts":[[2017,10,22]]},"end":{"date-parts":[[2017,10,29]]}},"container-title":["2017 IEEE International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8234942\/8237262\/08237481.pdf?arnumber=8237481","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,25]],"date-time":"2022-01-25T22:55:14Z","timestamp":1643151314000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8237481\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv.2017.219","relation":{},"subject":[],"published":{"date-parts":[[2017,10]]}}}