{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:02:43Z","timestamp":1761897763268,"version":"3.37.3"},"reference-count":19,"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":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972047"],"award-info":[{"award-number":["61972047"]}],"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\/icme52920.2022.9859784","type":"proceedings-article","created":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T19:45:18Z","timestamp":1661543118000},"page":"01-06","source":"Crossref","is-referenced-by-count":3,"title":["FHGN: Frame-Level Heterogeneous Graph Networks for Video Question Answering"],"prefix":"10.1109","author":[{"given":"Jinsheng","family":"Qi","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangtao","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Bai","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyu","family":"Cao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Song","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yibo","family":"Hu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"iqiyi-vid: A large dataset for multi-modal person identification","author":"liu","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3058626"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413097"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref15","first-page":"4171","article-title":"Bert: Pre-training of deep bidi-rectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL"},{"key":"ref16","first-page":"413","article-title":"Videos as space-time region graphs","author":"wang","year":"2018","journal-title":"ECCV"},{"key":"ref17","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"ICLRE"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463635"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/88"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.481"},{"key":"ref8","article-title":"Merlot: Multimodal neural script knowledge models","author":"zellers","year":"2021","journal-title":"NeurIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01527"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.730"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2969791"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987728"}],"event":{"name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2022,7,18]]},"location":"Taipei, Taiwan","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\/09859784.pdf?arnumber=9859784","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T20:24:52Z","timestamp":1663619092000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9859784\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icme52920.2022.9859784","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}