{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:30:05Z","timestamp":1761895805967,"version":"build-2065373602"},"reference-count":24,"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\/icme59968.2025.11210062","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":["Multi-Passage Retrieval-Augmented Multimodal Language Generation Model for Knowledge-Based Visual Question Answering"],"prefix":"10.1109","author":[{"given":"Siyu","family":"Cheng","sequence":"first","affiliation":[{"name":"Hunan University,College of Computer Science and Electronic Engineering,Changsha,China"}]},{"given":"Chao","family":"Yang","sequence":"additional","affiliation":[{"name":"Hunan University,College of Computer Science and Electronic Engineering,Changsha,China"}]},{"given":"Bin","family":"Jiang","sequence":"additional","affiliation":[{"name":"Hunan University,College of Computer Science and Electronic Engineering,Changsha,China"}]}],"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.2019.00331"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.772"},{"article-title":"Fine-grained late-interaction multi-modal retrieval for retrieval augmented visual question answering","volume-title":"NeurIPS","author":"Lin","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.614"},{"article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","year":"2023","author":"Li","key":"ref8"},{"key":"ref9","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"NeurIPS","volume":"36","author":"Liu"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1171"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.44"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01389"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00501"},{"key":"ref15","first-page":"10560","article-title":"Revive: Regional visual representation matters in knowledge-based visual question answering","volume-title":"NeurIPS","volume":"35","author":"Lin"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591687"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20174"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547870"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.517"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.70"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01438"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.478"}],"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\/11210062.pdf?arnumber=11210062","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:59:37Z","timestamp":1761890377000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210062\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210062","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}