{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T21:31:37Z","timestamp":1762896697873},"reference-count":30,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/icip.2018.8451692","type":"proceedings-article","created":{"date-parts":[[2018,9,7]],"date-time":"2018-09-07T13:59:22Z","timestamp":1536328762000},"page":"918-922","source":"Crossref","is-referenced-by-count":7,"title":["Joint Spatio-Temporal Action Localization in Untrimmed Videos with Per-Frame Segmentation"],"prefix":"10.1109","author":[{"given":"Xuhuan","family":"Duan","sequence":"first","affiliation":[]},{"given":"Le","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Changbo","family":"Zhai","sequence":"additional","affiliation":[]},{"given":"Nanning","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Qilin","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zhenxing","family":"Niu","sequence":"additional","affiliation":[]},{"given":"Gang","family":"Hua","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.87"},{"key":"ref10","article-title":"Action recognition and detection by combining motion and appearance features","author":"wang","year":"0","journal-title":"THUMOS14 Action Recognition Challenge"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.211"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.341"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.155"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.362"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.472"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11903","article-title":"Video-based sign language recognition without temporal segmentation","author":"huang","year":"2018","journal-title":"AAAI"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2487833"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.3390\/s17102421","article-title":"A hyperspectral image classification framework with spatial pixel pair features","author":"ran","year":"2017","journal-title":"SENSORS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126471"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"journal-title":"Ucf101 A Dataset of 101 Human Actions Classes from Videos in the Wild","year":"2012","author":"soomro","key":"ref27"},{"journal-title":"Temporal action localization by structured maximal sums","year":"2017","author":"zehuan","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.214"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.223"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.226"},{"key":"ref7","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"NIPS"},{"journal-title":"THUMOS Challenge Action Recognition with A Large Number of Classes","year":"2014","author":"jiang","key":"ref2"},{"journal-title":"Temporal activity detection in untrimmed videos with recurrent neural networks","year":"2016","author":"montes","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.227"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806224"},{"key":"ref22","article-title":"Video object co-segmentation by regulated maximum weight cliques","author":"zhang","year":"2014","journal-title":"ECCV"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2612187"},{"key":"ref23","article-title":"Video object discovery and co-segmentation with extremely weak supervision","author":"wang","year":"2014","journal-title":"EC-CV"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126231"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/34.969114"}],"event":{"name":"2018 25th IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2018,10,7]]},"location":"Athens","end":{"date-parts":[[2018,10,10]]}},"container-title":["2018 25th IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8436606\/8451009\/08451692.pdf?arnumber=8451692","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T19:21:23Z","timestamp":1693855283000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8451692\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icip.2018.8451692","relation":{},"subject":[],"published":{"date-parts":[[2018,10]]}}}