{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T05:39:17Z","timestamp":1769751557694,"version":"3.49.0"},"reference-count":16,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,15]]},"DOI":"10.1109\/icmew63481.2024.10645365","type":"proceedings-article","created":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T17:43:36Z","timestamp":1724953416000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing Video Grounding with Dual-Path Modality Fusion on Animal Kingdom Datasets"],"prefix":"10.1109","author":[{"given":"Chengpeng","family":"Xiong","sequence":"first","affiliation":[{"name":"Macao Polytechnic University,Macao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengxuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Macao Polytechnic University,Macao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nuoer","family":"Long","sequence":"additional","affiliation":[{"name":"Macao Polytechnic University,Macao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kin-Seong","family":"Un","sequence":"additional","affiliation":[{"name":"Macao Polytechnic University,Macao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuolin","family":"Li","sequence":"additional","affiliation":[{"name":"Macao Polytechnic University,Macao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaobin","family":"Chen","sequence":"additional","affiliation":[{"name":"Macao Polytechnic University,Macao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Tan","sequence":"additional","affiliation":[{"name":"Macao Polytechnic University,Macao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chan-Tong","family":"Lam","sequence":"additional","affiliation":[{"name":"Macao Polytechnic University,Macao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Sun","sequence":"additional","affiliation":[{"name":"Macao Polytechnic University,Macao,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_44"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.01186"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref5","author":"Lei","year":"2021","journal-title":"Qvhigh-lights: Detecting moments and highlights in videos via natural language queries"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.530"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.445"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00262"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01844"},{"key":"ref16","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"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\/10645365.pdf?arnumber=10645365","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T04:30:20Z","timestamp":1725251420000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10645365\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/icmew63481.2024.10645365","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}