{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:24:26Z","timestamp":1778171066347,"version":"3.51.4"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1109\/wacv45572.2020.9093361","type":"proceedings-article","created":{"date-parts":[[2020,5,14]],"date-time":"2020-05-14T23:41:09Z","timestamp":1589499669000},"page":"565-574","source":"Crossref","is-referenced-by-count":66,"title":["Stacked Spatio-Temporal Graph Convolutional Networks for Action Segmentation"],"prefix":"10.1109","author":[{"given":"Pallabi","family":"Ghosh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Larry S.","family":"Davis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ajay","family":"Divakaran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00627"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.85"},{"key":"ref31","article-title":"Temporal gaussian mixture layer for videos","author":"piergiovanni","year":"2018"},{"key":"ref30","article-title":"Learning latent superevents to detect multiple activities in videos","volume":"4","author":"piergiovanni","year":"2018","journal-title":"Proceedings ofthe IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref37","article-title":"Temporal action detection using a statisticallanguage model","author":"richard","year":"2016","journal-title":"Conference on Computer Vision and Pattern Recognition IEEE"},{"key":"ref36","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref34","first-page":"401","article-title":"Learning human-object interactions by graph parsing neural networks","author":"qi","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref60","article-title":"Graph edge convolutional neural networks for skeleton based action recognition","author":"zhang","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00174"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-011-0858-2"},{"key":"ref29","first-page":"483","article-title":"Stacked hourglass networks for human pose estimation","author":"newell","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref2","first-page":"1993","article-title":"Diffusion-convolutional neural networks","author":"atwood","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref1","year":"0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913478446"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2430335"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.448"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00705"},{"key":"ref26","article-title":"Gated graph sequence neural networks","author":"li","year":"2015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_21"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240621"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref59","first-page":"1655","article-title":"Deep spatio-temporal residual networks for citywide crowd flows prediction","author":"zhang","year":"2017","journal-title":"AAAI"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.597"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.253"},{"key":"ref56","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12328","article-title":"Spatial temporal graph convolutional networks for skeleton-based action recognition","author":"yan","year":"2018","journal-title":"AAAI"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.617"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451364"},{"key":"ref53","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01228-1_25","article-title":"Videos as space-time region graphs","author":"wang","year":"2018"},{"key":"ref52","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref10","article-title":"Tricornet: A hybrid temporal convolutional and recurrent network for video action segmentation","author":"ding","year":"2017"},{"key":"ref11","author":"ding","year":"2018","journal-title":"Video action segmentation with hybrid temporal networks"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WI.2005.67"},{"key":"ref12","first-page":"6508","article-title":"Weakly-supervised action segmentation with iterative soft boundary assignment","author":"ding","year":"2018","journal-title":"Proc IEEE Conf Computer Vision and Pattern Recognition"},{"key":"ref13","first-page":"2224","article-title":"Convolutional networks on graphs for learning molecular fingerprints","author":"duvenaud","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00369"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_40"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2010.04.005"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.573"},{"key":"ref18","article-title":"The kinetics human action video dataset","author":"kay","year":"2017"},{"key":"ref19","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2016"},{"key":"ref4","author":"bruna","year":"2017","journal-title":"Community detection with graph neural networks"},{"key":"ref3","article-title":"The description length of deep learning models","author":"blier","year":"2018","journal-title":"NIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/UMEDIA.2017.8074105"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref8","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","author":"defferrard","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Predictivecor- rective networks for action detection","author":"dave","year":"2017","journal-title":"Proceedings of the Computer Vision and Pattern Recognition"},{"key":"ref49","article-title":"Weakly supervised action segmentation using mutual consistency","author":"souri","year":"2019"},{"key":"ref9","article-title":"Temporal 3d convnets: New architecture and transfer learning for video classification","author":"diba","year":"2017"},{"key":"ref46","article-title":"Hollywood in homes: Crowdsourcing data collection for activity understanding","author":"sigurdsson","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00772"},{"key":"ref48","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref47","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93417-4_38"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.599"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CCPR.2008.92"}],"event":{"name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","location":"Snowmass Village, CO, USA","start":{"date-parts":[[2020,3,1]]},"end":{"date-parts":[[2020,3,5]]}},"container-title":["2020 IEEE Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9087828\/9093261\/09093361.pdf?arnumber=9093361","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T15:46:25Z","timestamp":1666539985000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9093361\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/wacv45572.2020.9093361","relation":{},"subject":[],"published":{"date-parts":[[2020,3]]}}}