{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T09:50:55Z","timestamp":1769161855710,"version":"3.49.0"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"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":[[2023,6,1]]},"DOI":"10.1109\/tpami.2021.3058649","type":"journal-article","created":{"date-parts":[[2021,2,13]],"date-time":"2021-02-13T02:19:13Z","timestamp":1613182753000},"page":"6674-6687","source":"Crossref","is-referenced-by-count":17,"title":["Learning to Recognize Actions on Objects in Egocentric Video With Attention Dictionaries"],"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":"FBK, Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0617-8873","authenticated-orcid":false,"given":"Sergio","family":"Escalera","sequence":"additional","affiliation":[{"name":"Universitat de Barcelona and Computer Vision Center, Barcelona, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4793-4276","authenticated-orcid":false,"given":"Oswald","family":"Lanz","sequence":"additional","affiliation":[{"name":"FBK, Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Recognizing manipulation actions from state-transformations","author":"Aboubakr","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.406"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00548"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00537"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2422573"},{"key":"ref9","first-page":"720","article-title":"Scaling egocentric vision: The EPIC-KITCHENS dataset","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Damen"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref11","first-page":"3468","article-title":"Spatiotemporal residual networks for video action recognition","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Feichtenhofer"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2558148"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00635"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.41"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2000.861302"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015015"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01232"},{"key":"ref19","first-page":"34","article-title":"Attentional pooling for action recognition","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Girdhar"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3007841"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00540"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref29","first-page":"7482","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Kendall"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298625"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00642"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.170"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref37","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2901707"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00543"},{"key":"ref40","article-title":"Multi-task sequence to sequence learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Luong"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00710"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.209"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.87"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00176"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref46","article-title":"An evaluation of action recognition models on EPIC-Kitchens","author":"Price","year":"2019"},{"key":"ref47","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298691"},{"key":"ref49","first-page":"365","article-title":"Action recognition using visual attention","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop","author":"Sharma"},{"key":"ref50","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Shi"},{"key":"ref51","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Simonyan"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.287"},{"key":"ref53","article-title":"Learning general purpose distributed sentence representations via large scale multi-task learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Subramanian"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.276"},{"key":"ref57","article-title":"Attention is all we need: Nailing down object-centric attention for egocentric activity recognition","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Sudhakaran"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3233\/IA-190021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296915"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2875441"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2639323"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00464"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451249"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6907"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00037"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.176"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2937724"},{"key":"ref75","first-page":"14 702","article-title":"A self validation network for object-level human attention estimation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.210"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2919764"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10120646\/09353268.pdf?arnumber=9353268","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:32:39Z","timestamp":1704843159000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9353268\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":79,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3058649","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":[[2023,6,1]]}}}