{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T20:40:55Z","timestamp":1777322455400,"version":"3.51.4"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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","award":["62576200"],"award-info":[{"award-number":["62576200"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476161"],"award-info":[{"award-number":["62476161"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Language Processing Innovation Team"},{"name":"Science and Technology Cooperation and Exchange Special Project of ShanXi Province","award":["202204041101016"],"award-info":[{"award-number":["202204041101016"]}]},{"name":"Taiyuan City Key Core Technology Research and Development"},{"name":"List and Commander-in-Chief","award":["2024TYJB0137"],"award-info":[{"award-number":["2024TYJB0137"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3651099","type":"journal-article","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T18:36:32Z","timestamp":1767724592000},"page":"3242-3255","source":"Crossref","is-referenced-by-count":0,"title":["Mitigating Hallucinations in Large Vision-Language Models via Visual-Enhanced Contrastive Decoding"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3622-8769","authenticated-orcid":false,"given":"Pengpeng","family":"Qiang","sequence":"first","affiliation":[{"name":"Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5858-899X","authenticated-orcid":false,"given":"Hongye","family":"Tan","sequence":"additional","affiliation":[{"name":"Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0912-4870","authenticated-orcid":false,"given":"Hu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0762-6562","authenticated-orcid":false,"given":"Xiaoli","family":"Li","sequence":"additional","affiliation":[{"name":"Information Systems Technology and Design, Singapore University of Technology and Design, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1545-5553","authenticated-orcid":false,"given":"Ru","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5887-9327","authenticated-orcid":false,"given":"Jiye","family":"Liang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Shikra: Unleashing multimodal llms referential dialogue magic","author":"Chen","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01031"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01208"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1240"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291588"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521658"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.573"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.262"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"ref17","article-title":"The curious case of neural text degeneration","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Holtzman","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00502"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00971"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.937"},{"key":"ref22","first-page":"7824","article-title":"HALC: Object hallucination reduction via adaptive focal-contrast decoding","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Chen","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.387"},{"key":"ref24","first-page":"34586","article-title":"Factuality enhanced language models for open-ended text generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Lee","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00257"},{"key":"ref26","article-title":"Aligning large multi-modal model with robust instruction tuning","author":"Liu","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01310"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01230"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4251-x"},{"key":"ref30","article-title":"Analyzing and mitigating object hallucination in large vision-language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Zhou","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.557"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref33","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"202","author":"Li","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01356"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-short.69"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.687"},{"key":"ref37","article-title":"Intervening anchor token: Decoding strategy in alleviating hallucinations for MLLMs","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Tang","year":"2025"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01363"},{"key":"ref39","article-title":"MLLM can see? dynamic correction decoding for hallucination mitigation","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Wang","year":"2025"},{"key":"ref40","first-page":"13050","article-title":"Probing multimodal large language models for global and local semantic representations","volume-title":"Proc. Joint Int. Conf. Comput. Linguistics, Lang. Resour. Eval., LREC\/COLING 2024","author":"Tao","year":"2024"},{"key":"ref41","first-page":"4514","article-title":"Probing inter-modality: Visual parsing with self-attention for vision-and-language pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 34: Annu. Conf. Neural Inf. Process. Syst. 2021","author":"Xue","year":"2021"},{"key":"ref42","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Radford","year":"2021"},{"key":"ref43","first-page":"2292","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Cuturi","year":"2013"},{"key":"ref44","article-title":"Llava-next: Stronger LLMs supercharge multimodal capabilities in the wild","author":"Li","year":"2024"},{"key":"ref45","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90 chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref46","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref47","article-title":"Mitigating modality prior-induced hallucinations in multimodal large language models via deciphering attention causality","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Zhou","year":"2025"},{"key":"ref48","article-title":"Look twice before you answer: Memory-space visual retracing for hallucination mitigation in multimodal large language models","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","author":"Zou","year":"2025"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref54","article-title":"MME: A comprehensive evaluation benchmark for multimodal large language models","volume-title":"Proc. 39th Annu. Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Fu","year":"2025"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11329466.pdf?arnumber=11329466","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T19:50:18Z","timestamp":1777319418000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11329466\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3651099","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}