{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:31:33Z","timestamp":1761895893577,"version":"build-2065373602"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209150","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic Feature-Focusing with Cross-Modal Semantic Alignment for Video Moment Retrieval and Highlight Detection"],"prefix":"10.1109","author":[{"given":"Xuehui","family":"Liang","sequence":"first","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruomei","family":"Wang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Software Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baoquan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Artificial Intelligence,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Feng","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"11846","article-title":"Detecting moments and highlights in videos via natural language queries","volume":"34","author":"Lei","year":"2021","journal-title":"NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01770"},{"key":"ref3","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume":"35","author":"Liang","year":"2022","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445735"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687426"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650814"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687844"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref11","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref14","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref15","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref16","first-page":"11525","article-title":"Object-centric learning with slot attention","volume":"33","author":"Locatello","year":"2020","journal-title":"NeurIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00336"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7299154"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_51"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00135"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00802"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209150.pdf?arnumber=11209150","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T06:01:38Z","timestamp":1761890498000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209150\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209150","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}