{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:47:25Z","timestamp":1772905645407,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/icmew63481.2024.10645477","type":"proceedings-article","created":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T17:43:36Z","timestamp":1724953416000},"page":"1-6","source":"Crossref","is-referenced-by-count":6,"title":["Self-Supervised Learning via Multi-Transformation Classification for Action Recognition"],"prefix":"10.1109","author":[{"given":"Duc-Quang","family":"Vu","sequence":"first","affiliation":[{"name":"Thai Nguyen University of Education,Dept. of CSIS,Thai Nguyen,Vietnam"}]},{"given":"Ngan","family":"Le","sequence":"additional","affiliation":[{"name":"University of Arkansas,Dept. of CSCE,Fayetteville,USA"}]},{"given":"Jia-Ching","family":"Wang","sequence":"additional","affiliation":[{"name":"National Central University,Dept. of CSIE,Taoyuan,Taiwan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097121"},{"key":"ref2","first-page":"327","article-title":"Voice separation using multi learning on squash-norm embedding matrix and mask","volume-title":"International Conference on Advances in Information and Communication Technology","author":"Minh Tan","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3307350"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.607"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.29007\/h68j"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00413"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00025"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"ref11","article-title":"Skip-clip: Self-supervised spatiotemporal representation learning by future clip order ranking","author":"EI-Nouby","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01058"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.226"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053985"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3328932"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3099856"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP53242.2021.9675335"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956634"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00188"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"ref23","first-page":"1","article-title":"Self-supervised learning for action recognition by video denoising","volume-title":"RIVF","author":"Thu","year":"2021"},{"key":"ref24","article-title":"Decomposing motion and content for natural video sequence prediction","author":"Villegas","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018545"},{"key":"ref26","first-page":"770","article-title":"Improving spatiotem-poral self-supervision by deep reinforcement learning","volume-title":"ECCV","author":"Buchler","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00586"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-12939-2_17"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00186"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10645349\/10645352\/10645477.pdf?arnumber=10645477","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T04:30:31Z","timestamp":1725251431000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10645477\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icmew63481.2024.10645477","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}