{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T16:17:08Z","timestamp":1770740228212,"version":"3.49.0"},"reference-count":20,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010712","name":"Vietnam National University Ho Chi Minh City","doi-asserted-by":"publisher","award":["DS.C2025-26-07"],"award-info":[{"award-number":["DS.C2025-26-07"]}],"id":[{"id":"10.13039\/501100010712","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Intell. Syst."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/mis.2025.3581100","type":"journal-article","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T13:44:23Z","timestamp":1750167863000},"page":"75-85","source":"Crossref","is-referenced-by-count":0,"title":["YOWOv3: An Efficient and Generalized Framework for Spatiotemporal Action Detection"],"prefix":"10.1109","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0717-5439","authenticated-orcid":false,"given":"Dang Duc Manh","family":"Nguyen","sequence":"first","affiliation":[{"name":"University of Information Technology, Ho Chi Minh City, Vietnam"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0204-8142","authenticated-orcid":false,"given":"Bui Duc","family":"Nhan","sequence":"additional","affiliation":[{"name":"National Central University, Taoyuan City, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0024-6732","authenticated-orcid":false,"given":"Jia-Ching","family":"Wang","sequence":"additional","affiliation":[{"name":"National Central University, Taoyuan City, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9728-4438","authenticated-orcid":false,"given":"Viet-Hang","family":"Duong","sequence":"additional","affiliation":[{"name":"University of Information Technology, Ho Chi Minh City, Vietnam"}]}],"member":"263","reference":[{"key":"ref1","first-page":"29,441","article-title":"Hiera: A hierarchical vision transformer without the bells-and-whistles","volume-title":"Proc. 40th Int. Conf. Mach. Learn. (ICML)","author":"Ryali","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00476"},{"key":"ref3","article-title":"You only watch once: A unified CNN architecture for real-time spatiotemporal action localization","author":"Kpkl","year":"2019"},{"key":"ref4","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst. (NIPS) - Volume 1","author":"Simonyan","year":"2014"},{"key":"ref5","article-title":"YOWOv2: A stronger yet efficient multi-level detection framework for real-time spatio-temporal action detection","author":"Yang","year":"2023"},{"key":"ref6","first-page":"10,078","article-title":"VideoMAE: masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Tong","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00630"},{"key":"ref8","volume-title":"Ultralytics YOLO","author":"Jocher","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw.2019.00240"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.502"},{"key":"ref11","article-title":"YOLOX: Exceeding YOLO series in 2021","author":"Ge","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00745"},{"key":"ref13","first-page":"21002","article-title":"Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Li","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00972"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00349"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00037"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"ref18","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00633"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01323"}],"container-title":["IEEE Intelligent Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9670\/11373689\/11039211.pdf?arnumber=11039211","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:11:26Z","timestamp":1770671486000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11039211\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":20,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/mis.2025.3581100","relation":{},"ISSN":["1541-1672","1941-1294"],"issn-type":[{"value":"1541-1672","type":"print"},{"value":"1941-1294","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}