{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:50:11Z","timestamp":1753602611762,"version":"3.28.0"},"reference-count":29,"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\/icip49359.2023.10222423","type":"proceedings-article","created":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T17:58:31Z","timestamp":1694455111000},"page":"2140-2144","source":"Crossref","is-referenced-by-count":2,"title":["Interpretable Visual Question Answering Referring to Outside Knowledge"],"prefix":"10.1109","author":[{"given":"He","family":"Zhu","sequence":"first","affiliation":[{"name":"Hokkaido University,Graduate School of Information Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ren","family":"Togo","sequence":"additional","affiliation":[{"name":"Hokkaido University,Faculty of Information Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takahiro","family":"Ogawa","sequence":"additional","affiliation":[{"name":"Hokkaido University,Faculty of Information Science and Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miki","family":"Haseyama","sequence":"additional","affiliation":[{"name":"Hokkaido University,Faculty of Information Science and Technology,Japan"}],"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":"10.3390\/s20051459"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102611"},{"volume-title":"Interpretable machine learning: A Guide for Making Black Box Models Explainable","year":"2020","author":"Molnar","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00915"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4812"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref7"},{"issue":"8","key":"ref8","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Radford"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00814"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.253"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00128"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/GCCE56475.2022.10014385"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2629489"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.70"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00360"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref18","article-title":"GIT: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref19","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Li"},{"key":"ref20","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"article-title":"Blip2: Bootstrapping language-image pre-training with frozen image encoders and large language models","year":"2023","author":"Li","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref25","first-page":"65","article-title":"METEOR: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the ACL workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization","author":"Banerjee"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/1073445.1073465"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"article-title":"Microsoft COCO captions: Data collection and evaluation server","year":"2015","author":"Chen","key":"ref29"}],"event":{"name":"2023 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2023,10,8]]},"location":"Kuala Lumpur, Malaysia","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\/10222423.pdf?arnumber=10222423","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T20:29:40Z","timestamp":1709324980000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10222423\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,8]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icip49359.2023.10222423","relation":{},"subject":[],"published":{"date-parts":[[2023,10,8]]}}}