{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T17:49:34Z","timestamp":1774892974905,"version":"3.50.1"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Meituan; National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976049,62072080"],"award-info":[{"award-number":["61976049,62072080"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/icme52920.2022.9859847","type":"proceedings-article","created":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T19:45:18Z","timestamp":1661543118000},"page":"1-6","source":"Crossref","is-referenced-by-count":10,"title":["GTLR: Graph-Based Transformer with Language Reconstruction for Video Paragraph Grounding"],"prefix":"10.1109","author":[{"given":"Xun","family":"Jiang","sequence":"first","affiliation":[{"name":"Center for Future Media & School of Computer Science and Engineering, University of Electronic Science and Technology of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xing","family":"Xu","sequence":"additional","affiliation":[{"name":"Center for Future Media & School of Computer Science and Engineering, University of Electronic Science and Technology of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingran","family":"Zhang","sequence":"additional","affiliation":[{"name":"Center for Future Media & School of Computer Science and Engineering, University of Electronic Science and Technology of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fumin","family":"Shen","sequence":"additional","affiliation":[{"name":"Center for Future Media & School of Computer Science and Engineering, University of Electronic Science and Technology of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zuo","family":"Cao","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xunliang","family":"Cai","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1654","article-title":"Radial graph convolutional network for visual question generation","volume":"32","author":"xu","year":"2020","journal-title":"TNNLS"},{"key":"ref11","article-title":"Activity graph transformer for temporal action localization","author":"nawhal","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref12","first-page":"1460","article-title":"Graph convolutional network hashing","volume":"50","author":"zhou","year":"2018","journal-title":"TCyb"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref17","first-page":"2986","article-title":"Boundary proposal network for two-stage natural language video localization","author":"xiao","year":"0","journal-title":"AAAI"},{"key":"ref4","first-page":"920","article-title":"Dense events grounding in video","author":"bao","year":"0","journal-title":"AAAI"},{"key":"ref3","first-page":"1","article-title":"Diving into the relations: Leveraging semantic and visual structures for video moment retrieval","author":"wu","year":"0","journal-title":"ICME"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6897"},{"key":"ref5","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"NeurIPS"},{"key":"ref8","first-page":"8445","article-title":"Embracing uncertainty: Decoupling and debias for robust temporal grounding","author":"zhou","year":"0","journal-title":"CVPR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00155"},{"key":"ref2","first-page":"1902","article-title":"Proposal-free video grounding with contextual pyramid network","author":"li","year":"0","journal-title":"AAAI"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref9","article-title":"Weakly supervised temporal adjacent network for language grounding","author":"wang","year":"2021","journal-title":"TMM"}],"event":{"name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","location":"Taipei, Taiwan","start":{"date-parts":[[2022,7,18]]},"end":{"date-parts":[[2022,7,22]]}},"container-title":["2022 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9859562\/9858923\/09859847.pdf?arnumber=9859847","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T20:25:04Z","timestamp":1663619104000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9859847\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icme52920.2022.9859847","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}