{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T06:15:15Z","timestamp":1744179315940},"reference-count":58,"publisher":"IEEE","license":[{"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":[],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/cvpr52729.2023.01107","type":"proceedings-article","created":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T13:30:52Z","timestamp":1692711052000},"page":"11504-11513","source":"Crossref","is-referenced-by-count":11,"title":["AutoLabel: CLIP-based framework for Open-Set Video Domain Adaptation"],"prefix":"10.1109","author":[{"given":"Giacomo","family":"Zara","sequence":"first","affiliation":[{"name":"University of Trento,Italy"}]},{"given":"Subhankar","family":"Roy","sequence":"additional","affiliation":[{"name":"LTCI, Télécom Paris, Institut polytechnique de Paris,France"}]},{"given":"Paolo","family":"Rota","sequence":"additional","affiliation":[{"name":"University of Trento,Italy"}]},{"given":"Elisa","family":"Ricci","sequence":"additional","affiliation":[{"name":"University of Trento,Italy"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Scaling egocentric vision: The epic-kitchens dataset","author":"damen","year":"2018","journal-title":"ECCV"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00229"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01058"},{"key":"ref15","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"ICLRE"},{"key":"ref14","article-title":"Longterm recurrent convolutional networks for visual recognition and description","author":"donahue","year":"2015","journal-title":"CVPR"},{"key":"ref58","article-title":"A comprehensive study of deep video action recognition","author":"zhu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref53","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-79175-8_4","article-title":"Visual domain adaptation in the deep learning era","author":"csurka","year":"2022","journal-title":"Synthesis Lectures on Computer Vision"},{"key":"ref55","article-title":"Actionclip: A new paradigm for video action recognition","author":"wang","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-58347-1_1"},{"key":"ref54","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"2016","journal-title":"ECCV"},{"key":"ref17","article-title":"Spatiotemporal multiplier networks for video action recog-nition","author":"feichtenhofer","year":"2017","journal-title":"CVPR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20610"},{"key":"ref19","article-title":"Exploring the limits of out-of-distribution detection","author":"fort","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"ref50","article-title":"Ucf10 1: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"ArXiv Preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00887"},{"key":"ref45","article-title":"Learning transferable visual models from natural language super-vision","author":"radford","year":"2021","journal-title":"ICML"},{"key":"ref48","article-title":"Open set domain adaptation by backpropa-gation","author":"saito","year":"2018","journal-title":"ECCV"},{"key":"ref47","article-title":"Maximum classifier discrepancy for unsuper-vised domain adaptation","author":"saito","year":"2018","journal-title":"CVPR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413897"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09904-8"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.88"},{"key":"ref49","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"NeurIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3469877.3490600"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00642"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_40"},{"key":"ref4","article-title":"Space-time mixing attention for video transformer","author":"bulat","year":"2021","journal-title":"NeurIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_25"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref5","article-title":"Open set domain adaptation for image and action recognition","author":"busto","year":"2018","journal-title":"TPAMI"},{"key":"ref40","article-title":"Learning spa-tiotemporal attention for egocentric action recognition","author":"lu","year":"2019","journal-title":"ICCVW"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.03.005"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref31","article-title":"Vilt: Vision-and-language transformer without convolution or region su-pervision","author":"kim","year":"2021","journal-title":"ICML"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01336"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01594-9"},{"key":"ref2","article-title":"On the opportunities and risks of foundation models","author":"bommasani","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298799"},{"key":"ref39","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"ICLRE"},{"key":"ref38","article-title":"Deep transfer learning with joint adaptation networks","author":"long","year":"2016","journal-title":"ICML"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.373"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00586"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref21","article-title":"Domain-adversarial training of neural networks","author":"ganin","year":"2015","journal-title":"JMLR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.604"},{"key":"ref27","article-title":"3d convolutional neural networks for human action recognition","author":"ji","year":"2012","journal-title":"TPAMI"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"}],"event":{"name":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","start":{"date-parts":[[2023,6,17]]},"location":"Vancouver, BC, Canada","end":{"date-parts":[[2023,6,24]]}},"container-title":["2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10203037\/10203050\/10205213.pdf?arnumber=10205213","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T14:05:44Z","timestamp":1694441144000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10205213\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/cvpr52729.2023.01107","relation":{},"subject":[],"published":{"date-parts":[[2023,6]]}}}