{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:18:53Z","timestamp":1783527533078,"version":"3.55.0"},"reference-count":52,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,6]]},"DOI":"10.1109\/cvpr.2018.00705","type":"proceedings-article","created":{"date-parts":[[2018,12,17]],"date-time":"2018-12-17T20:49:37Z","timestamp":1545079777000},"page":"6742-6751","source":"Crossref","is-referenced-by-count":147,"title":["Temporal Deformable Residual Networks for Action Segmentation in Videos"],"prefix":"10.1109","author":[{"given":"Peng","family":"Lei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sinisa","family":"Todorovic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.287"},{"key":"ref38","article-title":"Online real time multiple spatiotemporal action localisation and prediction on a single platform","author":"singh","year":"2017","journal-title":"ICCV"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.140"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.341"},{"key":"ref31","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"NIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.353"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.216"},{"key":"ref36","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"NIPS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.155"},{"key":"ref34","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"MICCAI"},{"key":"ref28","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"2013","journal-title":"ICML"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123343"},{"key":"ref29","first-page":"744","article-title":"Multi-region two-stream r-cnn for action detection","author":"peng","year":"2016","journal-title":"ECCV"},{"key":"ref2","first-page":"3097","article-title":"Spatiotemporal vector of locally max pooled features for action recognition in videos","author":"duta","year":"2017","journal-title":"CVPR"},{"key":"ref1","author":"chollet","year":"2017"},{"key":"ref20","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477701"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487305"},{"key":"ref23","first-page":"36","article-title":"Segmental spatiotemporal cnns for fine-grained action segmentation","author":"lea","year":"2016","journal-title":"ECCV"},{"key":"ref26","first-page":"203","article-title":"Online human action detection using joint classification-regression recurrent neural networks","author":"li","year":"2016","journal-title":"ECCV"},{"key":"ref25","first-page":"47","article-title":"Temporal convolutional networks: A unified approach to action segmentation","author":"lea","year":"2016","journal-title":"ECCV Workshops"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.342"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref10","first-page":"3468","article-title":"Spatiotemporal residual networks for video action recognition","author":"feichtenhofer","year":"2016","journal-title":"NIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493482"},{"key":"ref12","article-title":"Jhu-isi gesture and skill assessment working set (jigsaws): A surgical activity dataset for human motion modeling","volume":"3","author":"gao","year":"2014","journal-title":"MICCAI Workshop"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref14","first-page":"753","article-title":"Bidirectional lstm networks for improved phoneme classification and recognition","author":"graves","year":"2005","journal-title":"Artificial Neural Networks Formal Models and Their Applications–ICANN 2005"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.620"},{"key":"ref17","first-page":"137","article-title":"Connectionist temporal modeling for weakly supervised action labeling","author":"huang","year":"2016","journal-title":"ECCV"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.472"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.610"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref6","author":"ding","year":"2017","journal-title":"Tricornet A hybrid temporal convolutional and recurrent network for video action segmentation"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.223"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.333"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126269"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995444"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.226"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.678"},{"key":"ref48","first-page":"1","article-title":"Every moment counts: Dense detailed labeling of actions in complex videos","author":"yeung","year":"2015","journal-title":"International Journal of Computer Vision"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.617"},{"key":"ref42","first-page":"339","article-title":"Surgical gesture segmentation and recognition","author":"tao","year":"2013","journal-title":"MICCAI"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.522"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"}],"event":{"name":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Salt Lake City, UT","start":{"date-parts":[[2018,6,18]]},"end":{"date-parts":[[2018,6,23]]}},"container-title":["2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx7\/8576498\/8578098\/08578803.pdf?arnumber=8578803","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,28]],"date-time":"2022-01-28T18:25:54Z","timestamp":1643394354000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/ieeexplore.ieee.org\/document\/8578803\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6]]},"references-count":52,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/cvpr.2018.00705","relation":{},"subject":[],"published":{"date-parts":[[2018,6]]}}}