{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T02:19:12Z","timestamp":1768789152798,"version":"3.49.0"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore under its AI Singapore Program","doi-asserted-by":"publisher","award":["AISG2-RP-2020-016"],"award-info":[{"award-number":["AISG2-RP-2020-016"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore under its AI Singapore Program","doi-asserted-by":"publisher","award":["AISG-RP-2019-010"],"award-info":[{"award-number":["AISG-RP-2019-010"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2021.3113114","type":"journal-article","created":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T20:14:02Z","timestamp":1632341642000},"page":"8116-8129","source":"Crossref","is-referenced-by-count":32,"title":["Action Anticipation Using Pairwise Human-Object Interactions and Transformers"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8779-1241","authenticated-orcid":false,"given":"Debaditya","family":"Roy","sequence":"first","affiliation":[{"name":"Institute of High-Performance Computing (IHPC), A*STAR, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6920-9916","authenticated-orcid":false,"given":"Basura","family":"Fernando","sequence":"additional","affiliation":[{"name":"Institute of High-Performance Computing (IHPC), A*STAR, Singapore"}]}],"member":"263","reference":[{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.179"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_25"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2430335"},{"key":"ref31","first-page":"792","article-title":"Learning spatio-temporal structure from RGB-D videos for human activity detection and anticipation","author":"koppula","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_43"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref36","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6326"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref60","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00956"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.18"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00116"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.219"},{"key":"ref64","first-page":"2582","article-title":"Deep CNNs meet global covariance pooling: Better representation and generalization","volume":"43","author":"wang","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.573"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref66","first-page":"569","article-title":"Forecasting events using an augmented hidden conditional random field","author":"wei","year":"2014","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01016"},{"key":"ref67","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","author":"xingjian","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00563"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.283"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00077"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00560"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref22","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"2011","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00872"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-75765-6_41"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.339"},{"key":"ref25","first-page":"237","article-title":"Gradient flow in recurrent nets: The difficulty of learning longterm dependencies","author":"kolen","year":"2001","journal-title":"A Field Guide to Dynamical Recurrent Networks"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126349"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.39"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.75"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00371"},{"key":"ref57","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_20"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493482"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.530"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_19"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_10"},{"key":"ref10","article-title":"Rescaling egocentric vision","author":"damen","year":"2020","journal-title":"arXiv 2006 13256"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_38"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.476"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00369"},{"key":"ref13","first-page":"13224","article-title":"Anticipating human actions by correlating past with the future with Jaccard similarity measures","author":"fernando","year":"2021","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref14","volume":"1","author":"friedman","year":"2001","journal-title":"The Elements of Statistical Learning"},{"key":"ref15","first-page":"1","article-title":"Leveraging uncertainty to rethink loss functions and evaluation measures for egocentric action anticipation","author":"furnari","year":"2018","journal-title":"Proc Eur Conf Comput Vis Workshops (ECCVW)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00635"},{"key":"ref17","first-page":"298","article-title":"Forecasting future action sequences with neural memory networks","author":"gammulle","year":"2019","journal-title":"Proc 30th Brit Mach Vis Conf (BMVC)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00566"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00092"},{"key":"ref4","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc 3rd Int Conf Learn Represent (ICLR)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.20965"},{"key":"ref6","first-page":"1","article-title":"Smooth loss functions for deep top-k classification","author":"berrada","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1111-5"},{"key":"ref7","first-page":"136","article-title":"Anticipating accidents in dashcam videos","author":"chan","year":"2016","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref49","first-page":"1","article-title":"Action anticipation by predicting future dynamic images","author":"rodriguez","year":"2018","journal-title":"Proc Eur Conf Comput Vis Workshops (ECCV)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2991965"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-3222-z"},{"key":"ref48","first-page":"171","article-title":"Pedestrian action anticipation using contextual feature fusion in stacked RNNs","author":"rasouli","year":"2019","journal-title":"Proc 30th Brit Mach Vis Conf (BMVC)"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298713"},{"key":"ref42","first-page":"163","article-title":"Ego-topo: Environment affordances from egocentric video","author":"nagarajan","year":"2020","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref41","first-page":"1","article-title":"Leveraging the present to anticipate the future in videos","author":"miech","year":"2019","journal-title":"Proc IEEE Conf Comp Vis Pattern Recognit"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_44"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3021497"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09546623.pdf?arnumber=9546623","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T03:34:55Z","timestamp":1733888095000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9546623\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/tip.2021.3113114","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}