{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T10:00:25Z","timestamp":1766138425013,"version":"3.37.3"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1109\/icme55011.2023.00336","type":"proceedings-article","created":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T17:18:08Z","timestamp":1692983888000},"page":"1961-1966","source":"Crossref","is-referenced-by-count":6,"title":["MIM: Lightweight Multi-Modal Interaction Model for Joint Video Moment Retrieval and Highlight Detection"],"prefix":"10.1109","author":[{"given":"Jinyu","family":"Li","sequence":"first","affiliation":[{"name":"National Engineering Research Center of Digital Life,School of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fuwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Digital Life,School of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shujin","family":"Lin","sequence":"additional","affiliation":[{"name":"Guangdong Key Laboratory for Big Data Analysis and Simulation of Public Opinion"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Zhou","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Digital Life,School of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruomei","family":"Wang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Digital Life,School of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00155"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_18"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298994"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3175520"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_21"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00042"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00802"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00785"},{"key":"ref2","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"ECCV"},{"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":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.526"},{"key":"ref16","first-page":"447","article-title":"Tvr: A large-scale dataset for video-subtitle moment retrieval","author":"lei","year":"2020","journal-title":"ECCV"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00787"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00135"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018199"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.112"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983349"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_16"}],"event":{"name":"2023 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2023,7,10]]},"location":"Brisbane, Australia","end":{"date-parts":[[2023,7,14]]}},"container-title":["2023 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10219544\/10219545\/10219646.pdf?arnumber=10219646","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T17:42:50Z","timestamp":1695058970000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10219646\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icme55011.2023.00336","relation":{},"subject":[],"published":{"date-parts":[[2023,7]]}}}