{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T15:51:22Z","timestamp":1787673082669,"version":"build-2736575974"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["JQ23018"],"award-info":[{"award-number":["JQ23018"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["JQ24019"],"award-info":[{"award-number":["JQ24019"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036012"],"award-info":[{"award-number":["62036012"]}],"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":["61936005"],"award-info":[{"award-number":["61936005"]}],"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":["62276257"],"award-info":[{"award-number":["62276257"]}],"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":["62072456"],"award-info":[{"award-number":["62072456"]}],"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":["62106262"],"award-info":[{"award-number":["62106262"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"SMP-IDATA Open Youth Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2024.3521709","type":"journal-article","created":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T19:21:58Z","timestamp":1735068118000},"page":"16-27","source":"Crossref","is-referenced-by-count":13,"title":["LININ: Logic Integrated Neural Inference Network for Explanatory Visual Question Answering"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0173-1556","authenticated-orcid":false,"given":"Dizhan","family":"Xue","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9488-2208","authenticated-orcid":false,"given":"Shengsheng","family":"Qian","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4190-1529","authenticated-orcid":false,"given":"Quan","family":"Fang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10648-007-9047-2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2738401"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00502"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3101642"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00979"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3188547"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01514"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28954-6_7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/make3040048"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00181"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1644"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2995278"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972830"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097502"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00441"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_25"},{"key":"ref28","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren","year":"2015"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00050-1"},{"key":"ref33","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref34","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Su","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref36","first-page":"1571","article-title":"Bilinear attention networks","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","volume":"31","author":"Kim","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.683"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3026892"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3173131"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3190686"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3216770"},{"key":"ref42","first-page":"279","article-title":"Neuro-symbolic visual reasoning: Disentangling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amizadeh","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_23"},{"key":"ref44","article-title":"A survey on interpretable cross-modal reasoning","author":"Xue","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00238"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3398012"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00915"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4812"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_34"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00178"},{"key":"ref51","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref52","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00280"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref56","first-page":"228","article-title":"Meteor: An automatic metric for MT evaluation with high levels of correlation with human judgments","volume-title":"Proc. 2nd Workshop Stat. Mach. Transl.","author":"Agarwal","year":"2007"},{"key":"ref57","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref60","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/453"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10814657.pdf?arnumber=10814657","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:58:29Z","timestamp":1737399509000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10814657\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3521709","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}