{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T20:36:16Z","timestamp":1778877376449,"version":"3.51.4"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62276283"],"award-info":[{"award-number":["62276283"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"China Meteorological Administration’s Science and Technology Project","award":["CMAJBGS202517"],"award-info":[{"award-number":["CMAJBGS202517"]}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515012985"],"award-info":[{"award-number":["2023A1515012985"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong-Hong Kong-Macao Greater Bay Area Meteorological Technology Collaborative Research Project","award":["GHMA2024Z04"],"award-info":[{"award-number":["GHMA2024Z04"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002402","name":"Sun Yat-sen University","doi-asserted-by":"publisher","award":["23hytd006"],"award-info":[{"award-number":["23hytd006"]}],"id":[{"id":"10.13039\/501100002402","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3651096","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:01:52Z","timestamp":1768255312000},"page":"3081-3096","source":"Crossref","is-referenced-by-count":1,"title":["Toward Top-Down Reasoning: An Explainable Multi-Agent Approach for Visual Question Answering"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6389-6678","authenticated-orcid":false,"given":"Zeqing","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2063-4382","authenticated-orcid":false,"given":"Wentao","family":"Wan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiqing","family":"Lao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Runmeng","family":"Chen","sequence":"additional","affiliation":[{"name":"South China Normal University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minjie","family":"Lang","sequence":"additional","affiliation":[{"name":"Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0008-0659","authenticated-orcid":false,"given":"Xiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Anhui University, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1843-3180","authenticated-orcid":false,"given":"Feng","family":"Gao","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7817-8306","authenticated-orcid":false,"given":"Keze","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2248-3755","authenticated-orcid":false,"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00502"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1116-0"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612222"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120194"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3216770"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.11"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01002"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.755"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612389"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2024.01.012"},{"key":"ref14","first-page":"56615","article-title":"Exploring question decomposition for zero-shot VQA","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Khan","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_16"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448321"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.144"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.107"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01046"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01441"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3380259"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2455415"},{"key":"ref23","article-title":"Mm-react: Prompting ChatGPT for multimodal reasoning and action","author":"Yang","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01259"},{"key":"ref27","first-page":"11733","article-title":"Improving factuality and reasoning in language models through multiagent debate","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Du","year":"2024"},{"key":"ref28","article-title":"More agents is all you need","author":"Li","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.26599\/CVM.2025.9450460"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3275853"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475350"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475609"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547870"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.44"},{"key":"ref36","first-page":"2659","article-title":"Out of the box: Reasoning with graph convolution nets for factual visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Narasimhan","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01389"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548387"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3289729"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2629489"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380107"},{"key":"ref42","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref43","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref44","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref45","article-title":"AssistGPT: A general multi-modal assistant that can plan, execute, inspect, and learn","author":"Gao","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4251-x"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"ref48","article-title":"Promptcap: Prompt-guided task-aware image captioning","author":"Hu","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref50","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref51","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27999"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3860"},{"key":"ref56","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Schuhmann","year":"2022"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.conll-1.14"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321501"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1240"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00246"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref62","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613848"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547776"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40231-1"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.15"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_29"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i6.16716"},{"key":"ref70","article-title":"Self-consistency improves chain of thought reasoning in language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2023"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0517"},{"issue":"3","key":"ref77","volume":"2","author":"Team","year":"2024","journal-title":""},{"issue":"3","key":"ref78","volume":"2","author":"Team","year":"2024","journal-title":""},{"key":"ref79","year":"2024","journal-title":""}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11329464.pdf?arnumber=11329464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T19:36:38Z","timestamp":1777923398000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11329464\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3651096","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}