{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:34:51Z","timestamp":1763202891864},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447275","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11616-11620","source":"Crossref","is-referenced-by-count":1,"title":["Semantic Enrichment for Video Question Answering with Gated Graph Neural Networks"],"prefix":"10.1109","author":[{"given":"Chenyang","family":"Lyu","sequence":"first","affiliation":[{"name":"Dublin City University,Dublin,Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxi","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianbo","family":"Ji","sequence":"additional","affiliation":[{"name":"Nantong University,Nantong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yu","sequence":"additional","affiliation":[{"name":"National Institute of Informatics,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longyue","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3010650"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548291"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00774"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350971"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00204"},{"year":"2023","key":"ref8","article-title":"GPT-4 Technical Report"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1561\/9781638281436"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01852"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"journal-title":"Robust speech recognition via large-scale weak supervision","year":"2022","author":"Radford","key":"ref12"},{"article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML","author":"Li","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-2812"},{"article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1044"},{"article-title":"Decoupled weight decay regularization","volume-title":"ICLR","author":"Loshchilov","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2020.3048440"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"article-title":"Graph-based video-language learning with multi-grained audiovisual alignment","volume-title":"ACMMM","author":"Lyu","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1024"},{"article-title":"Hierarchical question-image co-attention for visual question answering","year":"2016","author":"Lu","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447275.pdf?arnumber=10447275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:34:02Z","timestamp":1722576842000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447275\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447275","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}