{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:24:29Z","timestamp":1761895469093,"version":"build-2065373602"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209827","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["A Knowledge Noise Mitigation Framework for Knowledge-based Visual Question Answering"],"prefix":"10.1109","author":[{"given":"Zhiyue","family":"Liu","sequence":"first","affiliation":[{"name":"Guangxi University,School of Computer, Electronics and Information,Nanning,China"}]},{"given":"Sihang","family":"Liu","sequence":"additional","affiliation":[{"name":"Guangxi University,School of Computer, Electronics and Information,Nanning,China"}]},{"given":"Jinyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Guangxi University,School of Computer, Electronics and Information,Nanning,China"}]},{"given":"Xinru","family":"Zhang","sequence":"additional","affiliation":[{"name":"Guangxi University,School of Computer, Electronics and Information,Nanning,China"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/CVPR.2019.00331"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ICCV.2015.279"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/CVPR46437.2021.01389"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.18653\/v1\/2021.emnlp-main.517"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1023\/B:BTTJ.0000047600.45421.6d"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1145\/2629489"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1609\/aaai.v36i3.20215"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/ICCV51070.2023.00277"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/CVPR52729.2023.01438"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.18653\/v1\/2023.emnlp-main.919"},{"year":"2024","author":"An","article-title":"Knowledge acquisition disentanglement for knowledge-based visual question answering with large language models","key":"ref11"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.18653\/v1\/2022.emnlp-main.772"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.18653\/v1\/2024.emnlp-main.110"},{"key":"ref14","first-page":"146","article-title":"A-OK-VQA: A benchmark for visual question answering using world knowledge","volume-title":"ECCV","author":"Schwenk"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.18653\/v1\/2022.naacl-main.70"},{"key":"ref16","first-page":"10560","article-title":"Revive: regional visual representation matters in knowledge-based visual question answering","volume-title":"NeurIPS","author":"Lin"},{"key":"ref17","first-page":"22820","article-title":"Fine-grained late-interaction multi-modal retrieval for retrieval augmented visual question answering","volume-title":"NeurIPS","author":"Lin"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/CVPR.2019.00644"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.18653\/v1\/2022.findings-emnlp.67"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1007\/978-3-031-20059-5_38"},{"year":"2024","author":"Dubey","article-title":"The llama 3 herd of models","key":"ref21"},{"year":"2023","author":"Zhu","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","key":"ref22"},{"key":"ref23","first-page":"49250","article-title":"Instructblip: towards general-purpose vision-language models with instruction tuning","volume-title":"NeurIPS","author":"Dai"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209827.pdf?arnumber=11209827","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:51:16Z","timestamp":1761889876000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209827\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209827","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}