{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T02:39:36Z","timestamp":1783564776904,"version":"3.55.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002573","name":"Yonsei University","doi-asserted-by":"publisher","award":["RS-2021-II212068"],"award-info":[{"award-number":["RS-2021-II212068"]}],"id":[{"id":"10.13039\/501100002573","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01913","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20572-20581","source":"Crossref","is-referenced-by-count":1,"title":["Fuzzy Contrastive Decoding to Alleviate Object Hallucination in Large Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Jieun","family":"Kim","sequence":"first","affiliation":[{"name":"Yonsei University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinmyeong","family":"Kim","sequence":"additional","affiliation":[{"name":"Yonsei University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoonji","family":"Kim","sequence":"additional","affiliation":[{"name":"Yonsei University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sung-Bae","family":"Cho","sequence":"additional","affiliation":[{"name":"Yonsei University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1203"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2003.817053"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.fss.2025.109474"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1409"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614905"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/72.363487"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.46"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00847"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01356"},{"key":"ref10","volume":"abs\/2306.13394","author":"Fu","year":"2023","journal-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.75"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02553"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.290"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.397"},{"key":"ref19","first-page":"1973019742","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","year":"2023"},{"key":"ref20","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","volume-title":"The Twelfth International Conference on Learning Representations","author":"Liu","year":"2023"},{"key":"ref21","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3902"},{"key":"ref23","article-title":"Llms know more than they show: On the intrinsic representation of 11 m hallucinations","volume-title":"ICLR","author":"Orgad","year":"2025"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.551"},{"key":"ref25","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-short.4"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.220"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1985.6313399"},{"key":"ref32","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.937"},{"key":"ref34","article-title":"Evaluating object hallucination in large vision-language models","volume-title":"The 2023 Conference on Empirical Methods in Natural Language Processing","author":"Zhou","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.394"},{"key":"ref36","author":"Zhang","year":"2024","journal-title":"Debiasing multimodal large language models"},{"key":"ref37","first-page":"600","article-title":"Overcoming language priors with counterfactual inference for visual question answering","volume-title":"Proceedings of the 22nd Chinese National Conference on Computational Linguistics","author":"Zhibo","year":"2023"},{"key":"ref38","article-title":"Analyzing and mitigating object hallucination in large vision-language models","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Zhou"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.294"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/151"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444364.pdf?arnumber=11444364","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:11:12Z","timestamp":1777612272000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444364\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01913","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}