{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T16:19:58Z","timestamp":1782836398030,"version":"3.54.5"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["61902309"],"award-info":[{"award-number":["61902309"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["xxj022019003"],"award-info":[{"award-number":["xxj022019003"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["xzd012022006"],"award-info":[{"award-number":["xzd012022006"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2020M683496"],"award-info":[{"award-number":["2020M683496"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Postdoctoral Innovative Talents Support","award":["BX20190273"],"award-info":[{"award-number":["BX20190273"]}]},{"name":"Science and Technology Program of Xi&#x0027;an","award":["21RGZN0017"],"award-info":[{"award-number":["21RGZN0017"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3289729","type":"journal-article","created":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T18:42:05Z","timestamp":1687804925000},"page":"1790-1800","source":"Crossref","is-referenced-by-count":11,"title":["Resolving Zero-Shot and Fact-Based Visual Question Answering via Enhanced Fact Retrieval"],"prefix":"10.1109","volume":"26","author":[{"given":"Sen","family":"Wu","sequence":"first","affiliation":[{"name":"School of Software Engineering, Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4392-8450","authenticated-orcid":false,"given":"Guoshuai","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3173-6307","authenticated-orcid":false,"given":"Xueming","family":"Qian","sequence":"additional","affiliation":[{"name":"Ministry of Education Key Laboratory for Intelligent Networks and Network Security, School of Information and Communication Engineering, and SMILES LAB, Xi&#x0027;an Jiaotong University, Xi&#x0027;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.500"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref3","article-title":"Zero-shot visual question answering","author":"Teney","year":"2016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88361-4_9"},{"key":"ref6","first-page":"2296","article-title":"Are you talking to a machine? dataset and methods for multilingual image question","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Gao","year":"2015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10442"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref9","article-title":"Hadamard product for low-rank bilinear pooling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3026892"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2995278"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3048626"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3145048"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref17","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Lu","year":"2016"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475609"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref21","first-page":"1378","article-title":"Ask me anything: Dynamic memory networks for natural language processing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kumar","year":"2016"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120194"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/153"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/179"},{"key":"ref25","first-page":"2659","article-title":"Out of the box: Reasoning with graph convolution nets for factual visual question answering","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Narasimhan","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_28"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018876"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475234"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.44"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108153"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/597"},{"key":"ref33","article-title":"K-ZSL: Resources for knowledge-driven zero-shot learning","author":"Geng","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00558"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01039"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00569"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3173815"},{"key":"ref38","article-title":"A zero-shot learning framework via cluster-prototype matching","volume-title":"Pattern Recognit.","volume":"124","author":"Zhang","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3127346"},{"key":"ref40","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref43","first-page":"1571","article-title":"Bilinear attention networks","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Kim","year":"2018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00648"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10163831.pdf?arnumber=10163831","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:12:55Z","timestamp":1706757175000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10163831\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3289729","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}