{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:40:54Z","timestamp":1730266854364,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007763","name":"Engineering Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007763","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10651273","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Coarse-to-Fine Recurrently Aligned Transformer with Balance Tokens for Video Moment Retrieval and Highlight Detection"],"prefix":"10.1109","author":[{"given":"Yi","family":"Pan","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujia","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Chang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiying","family":"Sun","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feihu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Chinese PLA General Hospital,The First Medical Centre,Department of Critical Care Medicine"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoguang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350985"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-023-04726-x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462823"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00135"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01365"},{"key":"ref7","first-page":"11 846","article-title":"Detecting moments and highlights in videos via natural language queries","volume":"34","author":"Lei","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"article-title":"Mh-detr: Video moment and highlight detection with cross-modal transformer","year":"2023","author":"Xu","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"article-title":"Locformer: Enabling transformers to perform temporal moment localization on long untrimmed videos with a feature sampling approach","year":"2021","author":"Rodriguez-Opazo","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104183"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00802"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_16"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298981"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01273"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00262"},{"article-title":"Dab-detr: Dynamic anchor boxes are better queries for detr","volume-title":"International Conference on Learning Representations","author":"Liu","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19972"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00630"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298994"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10651273.pdf?arnumber=10651273","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T07:34:19Z","timestamp":1725953659000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10651273\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10651273","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}