{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T16:09:19Z","timestamp":1785427759804,"version":"3.56.0"},"reference-count":63,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"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":[[2019,10]]},"DOI":"10.1109\/iccv.2019.00635","type":"proceedings-article","created":{"date-parts":[[2020,2,28]],"date-time":"2020-02-28T10:27:52Z","timestamp":1582885672000},"page":"6251-6260","source":"Crossref","is-referenced-by-count":139,"title":["What Would You Expect? Anticipating Egocentric Actions With Rolling-Unrolling LSTMs and Modality Attention"],"prefix":"10.1109","author":[{"given":"Antonino","family":"Furnari","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giovanni","family":"Farinella","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.508"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759048"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_45"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.616"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.214"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.209"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298625"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.377"},{"key":"ref62","first-page":"803","article-title":"Temporal relational reasoning in videos","author":"zhou","year":"2018","journal-title":"European Conference on Computer Vision"},{"key":"ref61","first-page":"135","article-title":"Adding attentiveness to the neurons in recurrent neural networks","author":"zhang","year":"2018","journal-title":"European Conference on Computer Vision"},{"key":"ref28","first-page":"201","article-title":"Activity forecasting","author":"kitani","year":"2012","journal-title":"European Conference on Computer Vision"},{"key":"ref63","first-page":"4498","article-title":"Temporal perception and prediction in ego-centric video","author":"zhou","year":"2016","journal-title":"International Conference on Computer Vision"},{"key":"ref27","first-page":"1725","article-title":"Large-scale video classification with convolutional neural networks","author":"karpathy","year":"2014","journal-title":"Computer Vision and Pattern Recognition"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2430335"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.39"},{"key":"ref1","first-page":"5343","article-title":"When will you do what?-anticipating temporal occurrences of activities","author":"abu farha","year":"2018","journal-title":"Computer Vision and Pattern Recognition"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0683-3"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_32"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_27"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.364"},{"key":"ref23","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2200554"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487478"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2009.5204354"},{"key":"ref51","article-title":"Lsta: Long short-term attention for egocentric action recognition","author":"sudhakaran","year":"2018","journal-title":"arXiv preprint arXiv 181 1 10959"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.326"},{"key":"ref58","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref57","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":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.18"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref52","article-title":"Attention is all we need: Nailing down object-centric attention for egocentric activity recognition","author":"sudhakaran","year":"2018","journal-title":"British Machine Vision Conference"},{"key":"ref10","article-title":"Forecasting hand and object locations in future frames","volume":"abs 1705 7328","author":"fan","year":"2017","journal-title":"CoRR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248010"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126269"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_23"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.362"},{"key":"ref16","article-title":"Leveraging uncertainty to rethink loss functions and evaluation measures for egocentric action anticipation","author":"furnari","year":"2018","journal-title":"European Conf on Comp Vision Workshop"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2017.10.004"},{"key":"ref18","article-title":"RED: Reinforced encoder-decoder networks for action anticipation","author":"gao","year":"2017","journal-title":"British Machine Vision Conference"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00173"},{"key":"ref4","article-title":"Am I done? predicting action progress in videos","author":"becattini","year":"2017","journal-title":"British Machine Vision Conference"},{"key":"ref3","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.343"},{"key":"ref5","first-page":"346","article-title":"Long-term activity forecasting using first-person vision","author":"bokhari","year":"2016","journal-title":"Asian Conference on Computer Vision"},{"key":"ref8","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","author":"damen","year":"2018","journal-title":"European Conference on Computer Vision"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.530"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_17"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477717"},{"key":"ref45","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":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.07.031"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.287"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126349"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.399"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298691"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2696454.2696462"}],"event":{"name":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Seoul, Korea (South)","start":{"date-parts":[[2019,10,27]]},"end":{"date-parts":[[2019,11,2]]}},"container-title":["2019 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8972782\/9008105\/09008264.pdf?arnumber=9008264","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:52:29Z","timestamp":1658094749000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9008264\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/iccv.2019.00635","relation":{},"subject":[],"published":{"date-parts":[[2019,10]]}}}