{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T17:42:52Z","timestamp":1783964572932,"version":"3.55.0"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956467","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:34:13Z","timestamp":1669750453000},"page":"3273-3279","source":"Crossref","is-referenced-by-count":8,"title":["Unified Recurrence Modeling for Video Action Anticipation"],"prefix":"10.1109","author":[{"given":"Tsung-Ming","family":"Tai","sequence":"first","affiliation":[{"name":"Free University of Bozen-Bolzano,NVIDIA AI Technology Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giuseppe","family":"Fiameni","sequence":"additional","affiliation":[{"name":"NVIDIA AI Technology Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng-Kuang","family":"Lee","sequence":"additional","affiliation":[{"name":"NVIDIA AI Technology Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simon","family":"See","sequence":"additional","affiliation":[{"name":"NVIDIA AI Technology Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oswald","family":"Lanz","sequence":"additional","affiliation":[{"name":"Free University of Bozen-Bolzano"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"10524","article-title":"On layer normalization in the transformer architecture","author":"xiong","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref38","article-title":"Is space-time attention all you need for video understanding?","author":"bertasius","year":"2021","journal-title":"CoRR"},{"key":"ref33","article-title":"Universal transformers","author":"dehghani","year":"2018"},{"key":"ref32","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref31","article-title":"Graph attention networks","author":"veli?kovi?","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref36","article-title":"Deepvit: Towards deeper vision transformer","author":"zhou","year":"2021"},{"key":"ref35","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref34","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059923"},{"key":"ref40","article-title":"Smooth loss functions for deep top-k classification","author":"berrada","year":"2018","journal-title":"ICLRE"},{"key":"ref11","article-title":"Slowfast rollingunrolling lstms for action anticipation in egocentric videos","author":"osman","year":"2021"},{"key":"ref12","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","author":"damen","year":"2018","journal-title":"ECCV"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.18"},{"key":"ref14","article-title":"RED: reinforced encoder-decoder networks for action anticipation","author":"gao","year":"2017","journal-title":"BMVC"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00560"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00351"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.18"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01302"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00635"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00943"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103252"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-019-0407-y"},{"key":"ref3","article-title":"Rolling-unrolling lstms for action anticipation from first-person video","author":"furnari","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.508"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00801"},{"key":"ref5","first-page":"16","article-title":"Personalized dynamics models for adaptive assistive navigation systems","author":"ohnbar","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1109\/VRW50115.2020.00077","article-title":"Towards An Egocentric Framework for Rigid and Articulated Object Tracking in Virtual Reality","author":"taylor","year":"2020","journal-title":"2020 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) VRW"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2807972"},{"key":"ref2","article-title":"Leveraging uncertainty to rethink loss functions and evaluation measures for egocentric action anticipation","author":"furnari","year":"2018","journal-title":"ECCV Workshops"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-91131-1_4"},{"key":"ref1","article-title":"A comprehensive study of deep video action recognition","author":"zhu","year":"2020","journal-title":"CoRR"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref20","article-title":"Higher order recurrent space-time transformer","author":"tai","year":"2021"},{"key":"ref45","article-title":"Rescaling egocentric vision","author":"damen","year":"2020","journal-title":"CoRR"},{"key":"ref48","article-title":"Lookahead optimizer: k steps forward, 1 step back","volume":"32","author":"zhang","year":"2019","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_10"},{"key":"ref47","article-title":"Adabelief optimizer: Adapting stepsizes by the belief in observed gradients","author":"zhuang","year":"2020","journal-title":"NeurIPS"},{"key":"ref21","first-page":"6202","article-title":"Slowfast networks for video recognition","author":"feichtenhofer","year":"2019","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.214"},{"key":"ref24","first-page":"1263","article-title":"Neural message passing for quantum chemistry","author":"gilmer","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00173"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01325"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3040521"},{"key":"ref26","article-title":"Neural message passing with edge updates for predicting properties of molecules and materials","author":"j\u00f8rgensen","year":"2018","journal-title":"Neural Information Processing Systems Conference"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487478"},{"key":"ref25","article-title":"Dual message passing neural network for molecular property prediction","author":"ma","year":"2020"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","location":"Montreal, QC, Canada","start":{"date-parts":[[2022,8,21]]},"end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956467.pdf?arnumber=9956467","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:04:56Z","timestamp":1671480296000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956467\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956467","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}