{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T23:18:58Z","timestamp":1792797538822,"version":"4.5.0"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Spanish projects","award":["PID2019-105093GB-I00"],"award-info":[{"award-number":["PID2019-105093GB-I00"]}]},{"name":"Spanish projects","award":["TED2021-131317B-I00"],"award-info":[{"award-number":["TED2021-131317B-I00"]}]},{"name":"Spanish projects","award":["PDC2022-133305-I00"],"award-info":[{"award-number":["PDC2022-133305-I00"]}]},{"DOI":"10.13039\/501100008815","name":"Libera Universit\u00e0 di Bolzano","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008815","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Amazon","id":[{"id":"https:\/\/ror.org\/04mv4n011","id-type":"ROR","asserted-by":"crossref"}]},{"name":"ICREA Academia Programme"},{"name":"NVIDIA AI Technology Centre","id":[{"id":"https:\/\/ror.org\/02tc3qm58","id-type":"ROR","asserted-by":"crossref"}]},{"name":"EMEA"},{"name":"CINECA Award"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,9,1]]},"DOI":"10.1109\/tpami.2023.3268134","type":"journal-article","created":{"date-parts":[[2023,4,19]],"date-time":"2023-04-19T13:27:28Z","timestamp":1681910848000},"page":"10913-10928","source":"Crossref","is-referenced-by-count":36,"title":["Gate-Shift-Fuse for Video Action Recognition"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7261-3581","authenticated-orcid":false,"given":"Swathikiran","family":"Sudhakaran","sequence":"first","affiliation":[{"name":"Samsung AI Center, Cambridge, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0617-8873","authenticated-orcid":false,"given":"Sergio","family":"Escalera","sequence":"additional","affiliation":[{"name":"Computer Vision Center, Universitat de Barcelona, Barcelona, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4793-4276","authenticated-orcid":false,"given":"Oswald","family":"Lanz","sequence":"additional","affiliation":[{"name":"Free University of Bozen-Bolzano, Bolzano, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00151"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.522"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref14","first-page":"3468","article-title":"Spatiotemporal residual networks for video action recognition","author":"feichtenhofer","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803153"},{"key":"ref52","article-title":"A short note on the kinetics-700–2020 human action dataset","author":"smaira","year":"2020"},{"key":"ref11","first-page":"2264","article-title":"More is less: Learning efficient video representations by big-little network and depthwise temporal aggregation","author":"fan","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00630"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01019"},{"key":"ref17","first-page":"34","article-title":"Attentional pooling for action recognition","author":"girdhar","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref51","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00136"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01018"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_39"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_3"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref41","article-title":"AdaFuse: Adaptive temporal fusion network for efficient action recognition","author":"meng","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00176"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2901464"},{"key":"ref49","article-title":"AssembleNet: Searching for multi-stream neural connectivity in video architectures","author":"ryoo","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref8","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_30"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_22"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_35"},{"key":"ref5","article-title":"Rescaling egocentric vision","author":"damen","year":"2020"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00359"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_6"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00054"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref78","first-page":"2208","article-title":"Trajectory convolution for action recognition","author":"zhao","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00806"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00446"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_24"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_17"},{"key":"ref77","article-title":"Maximum-entropy adversarial data augmentation for improved generalization and robustness","author":"zhao","year":"2020"},{"key":"ref32","article-title":"CT-net: Channel tensorization network for video classification","author":"li","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref76","article-title":"V4D: 4D convolutional neural networks for video-level representation learning","author":"zhang","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00044"},{"key":"ref1","first-page":"813","article-title":"Is space-time attention all you need for video understanding?","author":"bertasius","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00558"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00561"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00137"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01508-1"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/105"},{"key":"ref23","article-title":"VideoGraph: Recognizing minutes-long human activities in videos","author":"hussein","year":"2019"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00037"},{"key":"ref26","article-title":"The kinetics human action video dataset","author":"kay","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16401"},{"key":"ref20","article-title":"Ego4D: Around the world in 3,000 hours of egocentric video","author":"grauman","year":"2021"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00034"},{"key":"ref66","article-title":"Eidetic 3D LSTM: A model for video prediction and beyond","author":"wang","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00633"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01576"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_21"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00043"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10210213\/10105518.pdf?arnumber=10105518","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T14:28:58Z","timestamp":1720535338000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10105518\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,1]]},"references-count":82,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3268134","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,1]]}}}