{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T07:40:23Z","timestamp":1780386023882,"version":"3.54.1"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,8]]},"DOI":"10.1109\/icip49359.2023.10223156","type":"proceedings-article","created":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T13:58:31Z","timestamp":1694440711000},"page":"2525-2529","source":"Crossref","is-referenced-by-count":6,"title":["Interpretable Visual Question Answering Via Reasoning Supervision"],"prefix":"10.1109","author":[{"given":"Maria","family":"Parelli","sequence":"first","affiliation":[{"name":"DeepLab,Athens,Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimitrios","family":"Mallis","sequence":"additional","affiliation":[{"name":"DeepLab,Athens,Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Markos","family":"Diomataris","sequence":"additional","affiliation":[{"name":"DeepLab,Athens,Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vassilis","family":"Pitsikalis","sequence":"additional","affiliation":[{"name":"DeepLab,Athens,Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01851"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00268"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12272"},{"key":"ref20","article-title":"Merlot: Multimodal neural script knowledge models","author":"zellers","year":"2021","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00502"},{"key":"ref10","article-title":"A case study of the shortcut effects in visual commonsense reasoning","author":"ye","year":"2019","journal-title":"AAAI"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01002"},{"key":"ref2","article-title":"Vl-bert: Pre-training of generic visual-linguistic representations","author":"su","year":"2020","journal-title":"ICLRE"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00160"},{"key":"ref16","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00043"},{"key":"ref8","article-title":"Making the v in vqa matter: Elevating the role of image understanding in visual question answering","author":"goyal","year":"2016","journal-title":"IJCV"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.495"},{"key":"ref9","first-page":"4971","article-title":"Don’t just assume; look and answer: Overcoming priors for visual question answering","author":"agrawal","year":"2017","journal-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref4","article-title":"Vinvl: Making visual representations matter in vision-language models","author":"zhang","year":"2021","journal-title":"CVPR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.63"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"}],"event":{"name":"2023 IEEE International Conference on Image Processing (ICIP)","location":"Kuala Lumpur, Malaysia","start":{"date-parts":[[2023,10,8]]},"end":{"date-parts":[[2023,10,11]]}},"container-title":["2023 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10221937\/10221892\/10223156.pdf?arnumber=10223156","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T10:50:02Z","timestamp":1701255002000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10223156\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,8]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icip49359.2023.10223156","relation":{},"subject":[],"published":{"date-parts":[[2023,10,8]]}}}