{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T05:35:28Z","timestamp":1771047328000,"version":"3.50.1"},"reference-count":27,"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\/icme57554.2024.10687844","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":5,"title":["Multi-Modal Fusion and Query Refinement Network for Video Moment Retrieval and Highlight Detection"],"prefix":"10.1109","author":[{"given":"Yifang","family":"Xu","sequence":"first","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunzhuo","family":"Sun","sequence":"additional","affiliation":[{"name":"Hubei Normal University,School of Physics and Electronics,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benxiang","family":"Zhai","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zien","family":"Xie","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youyao","family":"Jia","sequence":"additional","affiliation":[{"name":"Gosuncn Chuanglian Technology Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sidan","family":"Du","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Electronic Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00135"},{"key":"ref3","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":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"ref5","author":"Li","year":"2023","journal-title":"MomentDiff: Generative Video Moment Retrieval from Random to Real"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00795"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897762"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428446"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1098\/rspb.2012.1741"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2013.00071"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3340103"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn60899.2024.10650814"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02193"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01506"},{"key":"ref16","first-page":"3611","article-title":"Re-thinking transformer-based set prediction for object detection","author":"Sun","year":"2021","journal-title":"ICCV"},{"key":"ref17","article-title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","author":"Bhat","year":"2023"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML.","author":"Radford","year":"2021"},{"key":"ref19","author":"Jing","year":"2019","journal-title":"Recognizing american sign language manual signs from rgb-d videos"},{"key":"ref20","author":"Ba","year":"2016","journal-title":"Layer normalization"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/163788"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3250471"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref25","author":"Loshchilov","year":"2017","journal-title":"Decoupled weight decay regularization"},{"key":"ref26","author":"Yu","year":"2023","journal-title":"Self-Chained Image-Language Model for Video Localization and Question Answering"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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 (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687844.pdf?arnumber=10687844","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:35:20Z","timestamp":1727764520000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687844\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687844","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}