{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T15:01:08Z","timestamp":1783868468490,"version":"3.55.0"},"reference-count":74,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003816","name":"Huawei Technologies","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003816","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016343","name":"EGI","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016343","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956679","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:34:13Z","timestamp":1669750453000},"page":"1258-1265","source":"Crossref","is-referenced-by-count":10,"title":["Unsupervised Domain Adaptation for Video Transformers in Action Recognition"],"prefix":"10.1109","author":[{"given":"Victor G. Turrisi","family":"da Costa","sequence":"first","affiliation":[{"name":"University of Trento"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giacomo","family":"Zara","sequence":"additional","affiliation":[{"name":"University of Trento"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paolo","family":"Rota","sequence":"additional","affiliation":[{"name":"University of Trento"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thiago","family":"Oliveira-Santos","sequence":"additional","affiliation":[{"name":"Universidade Federal do Espírito Santo"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicu","family":"Sebe","sequence":"additional","affiliation":[{"name":"University of Trento"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vittorio","family":"Murino","sequence":"additional","affiliation":[{"name":"University of Verona"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elisa","family":"Ricci","sequence":"additional","affiliation":[{"name":"University of Trento"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2019"},{"key":"ref72","article-title":"Vicreg: Variance-invariance-covariance regularization for self-supervised learning","author":"bardes","year":"2021"},{"key":"ref71","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"ICML"},{"key":"ref70","article-title":"Revisiting batch normalization for practical domain adaptation","author":"li","year":"2017","journal-title":"ICLR Workshop"},{"key":"ref74","article-title":"Supervised contrastive learning","author":"khosla","year":"2021"},{"key":"ref39","article-title":"Domain-adversarial training of neural networks","author":"ganin","year":"2016","journal-title":"JMLR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00145"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00970"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.542"},{"key":"ref31","article-title":"Learning Transferable Features with Deep Adaptation Networks","author":"long","year":"2015","journal-title":"ICML"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3444685.3446289"},{"key":"ref37","article-title":"Conditional Adversarial Domain Adaptation","author":"long","year":"2018","journal-title":"NeurIPS"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00503"},{"key":"ref35","article-title":"Deep domain confusion: Maximizing for domain invariance","author":"tzeng","year":"2014"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00397"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref62","article-title":"A short note on the kinetics-700 human action dataset","author":"carreira","year":"2019","journal-title":"CoRR"},{"key":"ref61","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012"},{"key":"ref63","article-title":"Yolov3: An incremental improvement","author":"redmon","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/s21165339"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"key":"ref27","article-title":"Trear: Transformer-based rgb-d egocentric action recognition","author":"li","year":"2020","journal-title":"IEEE Transactions on Cognitive and Developmental Systems"},{"key":"ref65","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"NeurIPS"},{"key":"ref66","first-page":"1180","article-title":"Unsupervised domain adaptation by back-propagation","author":"ganin","year":"2015","journal-title":"Int Conference on Machine Learning"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1109\/ICME51207.2021.9428459","article-title":"Hierarchical transformer: Unsupervised representation learning for skeleton-based human action recognition","author":"cheng","year":"2021","journal-title":"2021 IEEE International Conference on Multimedia and Expo (ICME) IEEE"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00392"},{"key":"ref68","article-title":"Unsupervised Domain Adaptation by Backpropagation","author":"ganin","year":"2015","journal-title":"ICML"},{"key":"ref69","article-title":"Deep transfer learning with joint adaptation networks","author":"long","year":"2017","journal-title":"ICML"},{"key":"ref2","article-title":"Temporal relational reasoning in videos","author":"zhou","year":"2018","journal-title":"ECCV"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412124"},{"key":"ref22","article-title":"Is space-time attention all you need for video understanding?","author":"bertasius","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"108487","DOI":"10.1016\/j.patcog.2021.108487","article-title":"Action transformer: A self-attention model for short-time pose-based human action recognition","volume":"124","author":"mazzia","year":"2022","journal-title":"Pattern Recognition"},{"key":"ref23","article-title":"Towards training stronger video vision transformers for epic-kitchens-100 action recognition","author":"huang","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68796-0_50"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref50","article-title":"Shuffle and attend: Video domain adaptation","author":"woo choi","year":"2020","journal-title":"ECCV"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01336"},{"key":"ref59","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","author":"zbontar","year":"2021"},{"key":"ref58","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref57","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019"},{"key":"ref56","article-title":"The kinetics human action video dataset","author":"kay","year":"2017"},{"key":"ref55","article-title":"Cross-domain self-supervised learning for domain adaptation with few source labels","author":"kim","year":"2020"},{"key":"ref54","article-title":"Joint contrastive learning for unsupervised domain adaptation","author":"park","year":"2020"},{"key":"ref53","first-page":"1181","article-title":"Dual-head contrastive domain adaptation for video action recognition","author":"da costa","year":"2022","journal-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00966"},{"key":"ref10","article-title":"Pretrained transformers as universal computation engines","author":"lu","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00642"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093511"},{"key":"ref13","article-title":"Hierarchical contrastive motion learning for video action recognition","author":"yang","year":"2020"},{"key":"ref14","article-title":"Spatiotemporal contrastive video representation learning","author":"qian","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_30"},{"key":"ref16","article-title":"Multi-modal self-supervision from generalized data transformations","author":"patrick","year":"2020"},{"key":"ref17","article-title":"Adafuse: Adaptive temporal fusion network for efficient action recognition","author":"meng","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2020.104090"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.11.012"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref6","article-title":"The information bottleneck method","author":"tishby","year":"2000"},{"key":"ref5","article-title":"An image is worth 16x16 words, what is a video worth?","author":"sharir","year":"2021"},{"key":"ref8","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2015.7133169"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6854"},{"key":"ref9","article-title":"Attention is all you need","author":"vaswani","year":"2017"},{"key":"ref46","article-title":"Transformer-based source-free domain adaptation","author":"yang","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30645-8_7"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00020"},{"key":"ref47","article-title":"Cdtrans: Cross-domain transformer for unsupervised domain adaptation","author":"xu","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00576"},{"key":"ref41","article-title":"CyCADA: Cycle-Consistent Adversarial Domain Adaptation","author":"hoffman","year":"2018","journal-title":"ICML"},{"key":"ref44","article-title":"Unsupervised domain adaptation through self-supervision","author":"sun","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00887"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","location":"Montreal, QC, Canada","start":{"date-parts":[[2022,8,21]]},"end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956679.pdf?arnumber=9956679","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:03:33Z","timestamp":1671480213000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956679\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956679","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}