{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T16:00:57Z","timestamp":1781366457898,"version":"3.54.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Industrial Fundamental Technology Development Program","award":["20018699"],"award-info":[{"award-number":["20018699"]}]},{"name":"MOTIE of Korea"},{"name":"IITP","award":["2021-0-02068"],"award-info":[{"award-number":["2021-0-02068"]}]},{"name":"IITP","award":["RS-2023-00256629"],"award-info":[{"award-number":["RS-2023-00256629"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/lra.2023.3307285","type":"journal-article","created":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T18:05:46Z","timestamp":1692641146000},"page":"6411-6418","source":"Crossref","is-referenced-by-count":12,"title":["Fluxformer: Flow-Guided Duplex Attention Transformer via Spatio-Temporal Clustering for Action Recognition"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6752-5605","authenticated-orcid":false,"given":"Younggi","family":"Hong","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3189-0669","authenticated-orcid":false,"given":"Min Ju","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2698-6971","authenticated-orcid":false,"given":"Isack","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6528-701X","authenticated-orcid":false,"given":"Seok Bong","family":"Yoo","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence Convergence, Chonnam National University, Gwangju, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref52","article-title":"A short note about kinetics-600","author":"carreira","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3056361"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00795"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3251843"},{"key":"ref54","article-title":"Kinetics dataset (5%)","year":"2022"},{"key":"ref17","first-page":"3476","article-title":"Spatiotemporal residual networks for video action recognition","author":"christoph","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref51","article-title":"The kinetics human action video dataset","author":"kay","year":"2017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00137"},{"key":"ref45","first-page":"6222","article-title":"Multi-agent reinforcement learning based frame sampling for effective untrimmed video recognition","author":"wenhao","year":"0","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1017616"},{"key":"ref47","first-page":"2678","article-title":"End-to-end learning of action detection from frame glimpses in videos","author":"serena","year":"0","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00086"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01341"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20013"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3390\/s23031616"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00309"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3139369"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref3","first-page":"3212","article-title":"Best frame selection in a short video","author":"jian","year":"0","journal-title":"Proc IEEE Winter Conf Appl Comput Vis"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref5","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00333"},{"key":"ref35","first-page":"4804","article-title":"MViTv2: Improved multiscale vision transformers for classification and detection","author":"yanghao","year":"0","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref31","first-page":"813","article-title":"Is space-time attention all you need for video understanding?","author":"bertasius","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"ref33","article-title":"Reformer: The efficient transformer","author":"kitaev","year":"2020"},{"key":"ref32","article-title":"Linformer: Self-attention with linear complexity","author":"wang","year":"2022"},{"key":"ref2","first-page":"6232","article-title":"SCSampler: Sampling salient clips from video for efficient action recognition","author":"bruno","year":"0","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01432"},{"key":"ref38","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8546131"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"ref25","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref29","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"0","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10220574\/10225669.pdf?arnumber=10225669","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T18:11:09Z","timestamp":1695060669000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10225669\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":55,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3307285","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}