{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:05:04Z","timestamp":1776884704752,"version":"3.51.2"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890131","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Visual Entity-Centric Prompting for Knowledge Retrieval in Knowledge-based VQA"],"prefix":"10.1109","author":[{"given":"Jiaming","family":"Yang","sequence":"first","affiliation":[{"name":"Guangdong University of Technology,School of Computer Science,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiuxiang","family":"You","sequence":"additional","affiliation":[{"name":"Hiroshima University,Graduate School of Advanced Science and Engineering,Hiroshima,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyue","family":"Qiu","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology,School of Computer Science,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guobo","family":"Xie","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology,School of Computer Science,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yu","sequence":"additional","affiliation":[{"name":"Hiroshima University,Graduate School of Advanced Science and Engineering,Hiroshima,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenguo","family":"Yang","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology,School of Computer Science,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"19 730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00277"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01046"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.189"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00011"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00179"},{"key":"ref8","first-page":"2835","article-title":"Git: A generative image-to-text transformer for vision and language","volume-title":"Transactions on Machine Learning Research","author":"Wang","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref10","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume-title":"Journal of machine learning research","author":"Raffel","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413943"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448108"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547870"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00501"},{"key":"ref20","first-page":"23 716","article-title":"Flamingo: a visual language model for few-shot learning","author":"Alayrac","year":"2022","journal-title":"Advances in neural information processing systems, NeurIPS"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890131.pdf?arnumber=10890131","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:08Z","timestamp":1774416128000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890131\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890131","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}