{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:22:22Z","timestamp":1761895342305,"version":"build-2065373602"},"reference-count":27,"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"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","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\/icme59968.2025.11209139","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":["Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Bin","family":"Li","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,School of Automation,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dehong","family":"Gao","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Cybersecurity,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yeyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Automation,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linbo","family":"Jin","sequence":"additional","affiliation":[{"name":"Alibaba Group,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shanqing","family":"Yu","sequence":"additional","affiliation":[{"name":"Zhejiang University of Technology,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyan","family":"Cai","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Automation,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Libin","family":"Yang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Cybersecurity,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"Neural Information Processing Systems(NIPS)"},{"key":"ref2","article-title":"Instructblip: towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2024","journal-title":"Neural Information Processing Systems(NIPS)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889170"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01246"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.05.001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1394-4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.161"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.54254\/2755-2721\/2024.17851"},{"article-title":"A survey of hallucination in large visual language models","year":"2024","author":"Lan","key":"ref9"},{"article-title":"Mllms-augmented visual-language representation learning","year":"2023","author":"Liu","key":"ref10"},{"article-title":"Ciem: Contrastive instruction evaluation method for better instruction tuning","year":"2023","author":"Hu","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4251-x"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.99"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.439"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations(ICLR)","author":"Dosovitskiy","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3651510"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3161428"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401430"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0271-y"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32869"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.937"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01356"}],"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\/11209139.pdf?arnumber=11209139","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:48:02Z","timestamp":1761889682000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209139\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209139","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}