{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T23:38:56Z","timestamp":1771457936554,"version":"3.50.1"},"reference-count":87,"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"}],"funder":[{"DOI":"10.13039\/100004318","name":"Microsoft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004318","id-type":"DOI","asserted-by":"publisher"}]}],"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.2021.3058606","type":"journal-article","created":{"date-parts":[[2021,2,13]],"date-time":"2021-02-13T02:19:13Z","timestamp":1613182753000},"page":"6659-6673","source":"Crossref","is-referenced-by-count":22,"title":["Domain-Specific Priors and Meta Learning for Few-Shot First-Person Action Recognition"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4669-2220","authenticated-orcid":false,"given":"Huseyin","family":"Coskun","sequence":"first","affiliation":[{"name":"Technische Universität München, München, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8221-2637","authenticated-orcid":false,"given":"M. Zeeshan","family":"Zia","sequence":"additional","affiliation":[{"name":"Retrocausal, Inc., Redmond, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8811-9919","authenticated-orcid":false,"given":"Bugra","family":"Tekin","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, WA, USA"}]},{"given":"Federica","family":"Bogo","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6032-5611","authenticated-orcid":false,"given":"Nassir","family":"Navab","sequence":"additional","affiliation":[{"name":"Technische Universität München, München, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5598-5212","authenticated-orcid":false,"given":"Federico","family":"Tombari","sequence":"additional","affiliation":[{"name":"Technische Universität München, München, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3568-5164","authenticated-orcid":false,"given":"Harpreet S.","family":"Sawhney","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, WA, USA"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Optimization as a model for few-shot learning","author":"ravi","year":"2017","journal-title":"Proc 5th Int Conf Learn Representations"},{"key":"ref57","article-title":"TARN: Temporal attentive relation network for few-shot and zero-shot action recognition","author":"bishay","year":"2019","journal-title":"Proc 30th Brit Mach Vis Conf"},{"key":"ref12","first-page":"9537","article-title":"Probabilistic model-agnostic meta-learning","author":"finn","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref56","first-page":"3637","article-title":"Matching networks for one-shot learning","author":"vinyals","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_31"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.99"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_46"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00772"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-013-0665-3"},{"key":"ref11","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref55","article-title":"Learning to optimize","author":"li","year":"2017","journal-title":"Proc 5th Int Conf Learn Representations"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298625"},{"key":"ref54","first-page":"3988","article-title":"Learning to learn by gradient descent by gradient descent","author":"andrychowicz","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2009.5457659"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291311"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.333"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126269"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_7"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.034"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00561"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00543"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.209"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00034"},{"key":"ref86","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00166"},{"key":"ref44","first-page":"284","article-title":"Videograph: Recognizing minutes-long human activities in videos","author":"hussein","year":"2019","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00037"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.226"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.166"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00157"},{"key":"ref9","first-page":"753","article-title":"Scaling egocentric vision: The EPIC-KITCHENS dataset","author":"damen","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref4","first-page":"7844","article-title":"What have we learned from deep representations for action recognition?","author":"feichtenhofer","year":"2018","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref3","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref6","first-page":"1127","article-title":"Towards an unequivocal representation of actions","author":"wray","year":"2018","journal-title":"Proc IEEE Conf Comp Vis Pattern Recognit"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.562"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.216"},{"key":"ref81","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc USENIX Conf Operating Syst Des Implementation"},{"key":"ref40","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref84","article-title":"A closer look at few-shot classification","author":"chen","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"ref35","first-page":"4694","article-title":"Beyond short snippets: Deep networks for video classification","author":"ng","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref79","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"Proc Int Conf Learning Representations"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref37","article-title":"Action recognition using visual attention","author":"sharma","year":"2015","journal-title":"CoRR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15567-3_11"},{"key":"ref75","article-title":"Improving language understanding by generative pre-training","author":"radford","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref74","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2712608"},{"key":"ref77","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref76","first-page":"803","article-title":"Temporal relational reasoning in videos","author":"zhou","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref39","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref71","article-title":"A structured self-attentive sentence embedding","author":"lin","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref70","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume":"abs 1412 3555","author":"chung","year":"2014","journal-title":"ArXiv e-prints"},{"key":"ref73","first-page":"1033","article-title":"Learning recurrent neural networks with hessian-free optimization","author":"martens","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref72","article-title":"How to train your MAML","author":"antoniou","year":"2017","journal-title":"Proc 5th Int Conf Learn Representations"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.352"},{"key":"ref68","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/34.910878","article-title":"The representation and recognition of action using temporal templates","volume":"23","author":"bobick","year":"2001","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.399"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.443"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_23"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248010"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301344"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995406"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995444"},{"key":"ref65","first-page":"4974","article-title":"A simple neural network module for relational reasoning","author":"santoro","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref28","article-title":"UCF101: A dataset of 101 human action classes from videos in the wild","author":"soomro","year":"2012"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref60","first-page":"4077","article-title":"Prototypical networks for few-shot learning","author":"snell","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01019"},{"key":"ref61","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10120646\/09352536.pdf?arnumber=9352536","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T17:34:56Z","timestamp":1685381696000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9352536\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":87,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3058606","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]]}}}