{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:52:17Z","timestamp":1740102737224,"version":"3.37.3"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447413","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"3645-3649","source":"Crossref","is-referenced-by-count":0,"title":["Spatio-Temporal Action Detection with a Motion Sense and Semantic Correction Framework"],"prefix":"10.1109","author":[{"given":"Yong","family":"Zhang","sequence":"first","affiliation":[{"name":"Huzhou University,School of Information Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunan","family":"Yu","sequence":"additional","affiliation":[{"name":"Huzhou University,School of Information Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenglong","family":"Fu","sequence":"additional","affiliation":[{"name":"Huzhou University,School of Information Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanqi","family":"Hu","sequence":"additional","affiliation":[{"name":"Huzhou University,School of Information Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Zang","sequence":"additional","affiliation":[{"name":"Huzhou University,School of Information Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.472"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01226"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_27"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01323"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.620"},{"article-title":"You only watch once: A unified cnn architecture for real-time spatiotemporal action localization","year":"2019","author":"K\u00f6p\u00fckl\u00fc","key":"ref10"},{"article-title":"Yowov2: A stronger yet efficient multi-level detection framework for real-time spatio-temporal action detection","year":"2023","author":"Yang","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00671"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","year":"2012","author":"Soomro","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_5"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01229"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533300"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00053"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00334"},{"article-title":"End-to-end spatio-temporal action localisation with video transformers","year":"2023","author":"Gritsenko","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00807"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447413.pdf?arnumber=10447413","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:37:45Z","timestamp":1722577065000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447413\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447413","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}