{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T19:58:33Z","timestamp":1780084713960,"version":"3.54.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"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":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,2,1]]},"DOI":"10.1109\/tpami.2022.3169976","type":"journal-article","created":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T21:08:36Z","timestamp":1650920916000},"page":"2533-2550","source":"Crossref","is-referenced-by-count":43,"title":["Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3698-4086","authenticated-orcid":false,"given":"Rui","family":"Dai","sequence":"first","affiliation":[{"name":"Inria, Universite Cote d'Azur, Valbonne, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3373-6749","authenticated-orcid":false,"given":"Srijan","family":"Das","sequence":"additional","affiliation":[{"name":"Inria, Universite Cote d'Azur, Valbonne, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saurav","family":"Sharma","sequence":"additional","affiliation":[{"name":"Inria, Universite Cote d'Azur, Valbonne, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Minciullo","sequence":"additional","affiliation":[{"name":"Toyota Motor Europe, Zaventem, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lorenzo","family":"Garattoni","sequence":"additional","affiliation":[{"name":"Toyota Motor Europe, Zaventem, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2988-2142","authenticated-orcid":false,"given":"Francois","family":"Bremond","sequence":"additional","affiliation":[{"name":"Inria, Universite Cote d'Azur, Valbonne, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gianpiero","family":"Francesca","sequence":"additional","affiliation":[{"name":"Toyota Motor Europe, Zaventem, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.339"},{"key":"ref4","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref6","article-title":"THUMOS challenge: Action recognition with a large number of classes","author":"Jiang","year":"2014"},{"key":"ref7","article-title":"Youtube-8m: A large-scale video classification benchmark","author":"Abu-El-Haija","year":"2016"},{"key":"ref8","article-title":"Human action localization with sparse spatial supervision","author":"Weinzaepfel","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1013-y"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00876"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3132734.3132739"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.67"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00092"},{"key":"ref19","article-title":"How2: A large-scale dataset for multimodal language understanding","volume-title":"Proc. Workshop Visually Grounded Interaction Lang.","author":"Sanabria"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00130"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248010"},{"key":"ref22","article-title":"Charades-ego: A large-scale dataset of paired third and first person videos","author":"Sigurdsson","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493482"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995444"},{"key":"ref25","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Damen"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0851-8"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913478446"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11752-2_15"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6906983"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_40"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298714"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00034"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00556"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00369"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00173"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-07827-3"},{"key":"ref47","first-page":"5152","article-title":"Temporal gaussian mixture layer for videos","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Piergiovanni"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2892985"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00794"},{"key":"ref50","article-title":"Tla software: Elan","year":"2019"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.235"},{"key":"ref52","article-title":"The devil is in the tails: Fine-grained classification in the wild","author":"Horn","year":"2017","journal-title":"CoRR"},{"key":"ref53","article-title":"A study on action detection in the wild","author":"Zhang","year":"2019"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.599"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-44851-9_28"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.617"},{"key":"ref62","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"CoRR"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.333"},{"key":"ref64","first-page":"5152","article-title":"Temporal gaussian mixture layer for videos","author":"Piergiovanni","year":"2019","journal-title":"Proc. Int. Conf. Mach. Learn."},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.235"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00022"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093263"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093361"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10008914\/09762531.pdf?arnumber=9762531","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:03:35Z","timestamp":1705957415000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9762531\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,1]]},"references-count":65,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3169976","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":[[2023,2,1]]}}}