{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T01:21:11Z","timestamp":1773105671150,"version":"3.50.1"},"reference-count":22,"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\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2019B1515120049,2020Blll1340056"],"award-info":[{"award-number":["2019B1515120049,2020Blll1340056"]}],"id":[{"id":"10.13039\/501100003453","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\/icme52920.2022.9859766","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":18,"title":["Joint Learning of Object Graph and Relation Graph for Visual Question Answering"],"prefix":"10.1109","author":[{"given":"Hao","family":"Li","sequence":"first","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Li","sequence":"additional","affiliation":[{"name":"Baidu Research,Cognitive Computing Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Belhal","family":"Karimi","sequence":"additional","affiliation":[{"name":"Baidu Research,Cognitive Computing Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingming","family":"Sun","sequence":"additional","affiliation":[{"name":"Baidu Research,Cognitive Computing Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00801"},{"key":"ref11","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"NIPS"},{"key":"ref12","article-title":"Compositional attention networks for machine reasoning","author":"hudson","year":"2018","journal-title":"ICLRE"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.08.002"},{"key":"ref15","article-title":"Un-biased scene graph generation from biased training","author":"tang","year":"2020","journal-title":"CVPR"},{"key":"ref16","article-title":"Graphvqa: Language-guided graph neural networks for scene graph question answering","author":"liange","year":"2021","journal-title":"NAACL"},{"key":"ref17","article-title":"Gated graph sequence neural networks","author":"li","year":"2016","journal-title":"ICLRE"},{"key":"ref18","author":"velickovic","year":"0","journal-title":"Graph attention networks"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-47674-2_2"},{"key":"ref4","article-title":"Learning by abstraction: The neural state machine","author":"hudson","year":"0","journal-title":"NeurIPS 2019"},{"key":"ref3","article-title":"An empirical study on leveraging scene graphs for visual question answering","author":"zhang","year":"0","journal-title":"BMVC 2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref5","author":"singh","year":"0","journal-title":"From strings to things Knowledge-enabled vqa model that can read and reason"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00952"},{"key":"ref7","article-title":"Prior visual re-lationship reasoning for visual question answering","author":"yang","year":"2020","journal-title":"ICIP"},{"key":"ref2","article-title":"Understanding the role of scene graphs in visual question answering","volume":"abs 2101 5479","author":"damodaran","year":"2021","journal-title":"CoRR"},{"key":"ref1","article-title":"Scene graph reasoning for visual question answering","author":"hildebrandt","year":"2020","journal-title":"CoRR"},{"key":"ref9","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref20","article-title":"A neu-ral transition-based approach for semantic dependency graph parsing","author":"wang","year":"0","journal-title":"AAAI 2018"},{"key":"ref22","article-title":"GloVe: Global vec-tors for word representation","author":"p","year":"0","journal-title":"EMNLP 2014"},{"key":"ref21","author":"tang","year":"2020","journal-title":"Sgg codebase in pytorch"}],"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\/09859766.pdf?arnumber=9859766","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T20:23:42Z","timestamp":1663619022000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9859766\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icme52920.2022.9859766","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}