{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T14:46:12Z","timestamp":1774968372335,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0111902"],"award-info":[{"award-number":["2021ZD0111902"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92370102"],"award-info":[{"award-number":["92370102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272015"],"award-info":[{"award-number":["62272015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2038"],"award-info":[{"award-number":["U21B2038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tnnls.2024.3370925","type":"journal-article","created":{"date-parts":[[2024,3,6]],"date-time":"2024-03-06T13:58:44Z","timestamp":1709733524000},"page":"4519-4531","source":"Crossref","is-referenced-by-count":8,"title":["Bridging the Cross-Modality Semantic Gap in Visual Question Answering"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2677-8342","authenticated-orcid":false,"given":"Boyue","family":"Wang","sequence":"first","affiliation":[{"name":"Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, Faculty of Information Technology, Beijing University of Technology, Beijing, China"}]},{"given":"Yujian","family":"Ma","sequence":"additional","affiliation":[{"name":"Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, Faculty of Information Technology, Beijing University of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1536-4264","authenticated-orcid":false,"given":"Xiaoyan","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, Faculty of Information Technology, Beijing University of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9803-0256","authenticated-orcid":false,"given":"Junbin","family":"Gao","sequence":"additional","affiliation":[{"name":"Discipline of Business Analytics, The University of Sydney Business School, The University of Sydney, Sydney, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0440-438X","authenticated-orcid":false,"given":"Yongli","family":"Hu","sequence":"additional","affiliation":[{"name":"Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, Faculty of Information Technology, Beijing University of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3121-1823","authenticated-orcid":false,"given":"Baocai","family":"Yin","sequence":"additional","affiliation":[{"name":"Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, Faculty of Information Technology, Beijing University of Technology, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2956975"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2624140"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132068"},{"key":"ref9","article-title":"Google\u2019s neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016","journal-title":"arXiv:1609.08144"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3331121"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref13","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00444"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3104937"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref18","first-page":"1","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413223"},{"key":"ref22","first-page":"1575","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref23","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Li"},{"key":"ref24","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105284"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859591"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3017530"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00504"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.188"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13214290"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17034"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00351"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3487042"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3253548"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3235704"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"ref40","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00148"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3141051"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3140070"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01081"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00163"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1045"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475609"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3135655"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859639"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9891887"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3216770"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ISCMI53840.2021.9654812"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/4378553"},{"key":"ref58","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. for Learn. Represent.","author":"Kingma"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10908444\/10461046.pdf?arnumber=10461046","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:15Z","timestamp":1764959955000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10461046\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":59,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3370925","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}