{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:07:00Z","timestamp":1761898020590,"version":"3.28.0"},"reference-count":18,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222207,62072245"],"award-info":[{"award-number":["62222207,62072245"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20211520"],"award-info":[{"award-number":["BK20211520"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,15]]},"DOI":"10.1109\/icmew63481.2024.10645431","type":"proceedings-article","created":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T17:43:36Z","timestamp":1724953416000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Leveraging Multimodal Knowledge for Spatio-Temporal Action Localization"],"prefix":"10.1109","author":[{"given":"Keke","family":"Chen","sequence":"first","affiliation":[{"name":"Nanjing university of science and technology,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"T.","family":"Zhewei","sequence":"additional","affiliation":[{"name":"Nanjing university of science and technology,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangbo","family":"Shu","sequence":"additional","affiliation":[{"name":"Nanjing university of science and technology,Nanjing,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\/CVPR46437.2021.00053"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01849"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_20"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611945"},{"key":"ref7","article-title":"Actionclip: A new paradigm for video action recognition","author":"Wang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_5"},{"key":"ref10","first-page":"284","article-title":"Long-term feature banks for detailed video understanding","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"C"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01323"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00807"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01414"},{"key":"ref14","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00035"},{"key":"ref16","first-page":"10078","article-title":"Videomae: Masked autoen-coders are data-efficient learners for self-supervised video pre-training","volume":"35","author":"Tong","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","start":{"date-parts":[[2024,7,15]]},"location":"Niagara Falls, ON, Canada","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\/10645431.pdf?arnumber=10645431","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T10:39:50Z","timestamp":1725014390000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10645431\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icmew63481.2024.10645431","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}