{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:28:41Z","timestamp":1775579321450,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,22]],"date-time":"2022-07-22T00:00:00Z","timestamp":1658448000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,22]],"date-time":"2022-07-22T00:00:00Z","timestamp":1658448000000},"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":[[2022,7,22]]},"DOI":"10.1109\/dsit55514.2022.9943844","type":"proceedings-article","created":{"date-parts":[[2022,11,17]],"date-time":"2022-11-17T20:39:41Z","timestamp":1668717581000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Group RandAugment: Video Augmentation for Action Recognition"],"prefix":"10.1109","author":[{"given":"Fengmin","family":"An","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Dalian Minzu University,Dalian,China"}]},{"given":"Bingbing","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology,Dalian,China"}]},{"given":"Zhenwei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Dalian Minzu University,Dalian,China"}]},{"given":"Wei","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Dalian Minzu University,Dalian,China"}]},{"given":"Jianxin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Dalian Minzu University,Dalian,China"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_21"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16401"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00154"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190839"},{"key":"ref31","first-page":"5842","article-title":"The","author":"goyal","year":"0","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66096-3_27"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_22"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00561"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref13","article-title":"Ean: event adaptive network for enhanced action recognition","author":"tian","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref14","article-title":"Ct-net: Channel tensorization network for video classification","author":"li","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref15","first-page":"8046","article-title":"Relational self-attention: What's missing in attention for video understanding","volume":"34","author":"kim","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref17","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","author":"tong","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref18","first-page":"4804","article-title":"Mvitv 2: Improved multiscale vision transformers for classification and detection","author":"li","year":"0","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref28","first-page":"702","article-title":"Randaugment: Practical auto-mated data augmentation with a reduced search space","author":"cubuk","year":"0","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref27","article-title":"Fast autoaugment","volume":"32","author":"lim","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"simonyan","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref29","article-title":"VideoMix: Rethinking data augmentation for video classification","author":"yun","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref7","first-page":"6546","article-title":"Can spatiotempo-ral 3d cnns retrace the history of 2d cnns and imagenet?","author":"hara","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref2","first-page":"1725","article-title":"Large-scale video clas-sification with convolutional neural networks","author":"karpathy","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref1","article-title":"The kinetics human action video dataset","author":"kay","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01432"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref24","article-title":"Improved regularization of convolutional neural networks with cutout","author":"devries","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref41","article-title":"Tsi: Temporal saliency integration for video action recognition","author":"su","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref23","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"0","journal-title":"2018 International Conference on Learning Representations"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"}],"event":{"name":"2022 5th International Conference on Data Science and Information Technology (DSIT)","location":"Shanghai, China","start":{"date-parts":[[2022,7,22]]},"end":{"date-parts":[[2022,7,24]]}},"container-title":["2022 5th International Conference on Data Science and Information Technology (DSIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9943793\/9943812\/09943844.pdf?arnumber=9943844","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T20:00:34Z","timestamp":1670875234000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9943844\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,22]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/dsit55514.2022.9943844","relation":{},"subject":[],"published":{"date-parts":[[2022,7,22]]}}}