{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:22:20Z","timestamp":1778048540881,"version":"3.51.4"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00127","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1242-1251","source":"Crossref","is-referenced-by-count":0,"title":["CAAC: Confidence-Aware Attention Calibration to Reduce Hallucinations in Large Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Mehrdad","family":"Fazli","sequence":"first","affiliation":[{"name":"George Mason University,Department of Computer Science,Fairfax,VA,USA,22030"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bowen","family":"Wei","sequence":"additional","affiliation":[{"name":"George Mason University,Department of Computer Science,Fairfax,VA,USA,22030"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmet","family":"Sari","sequence":"additional","affiliation":[{"name":"George Mason University,Department of Computer Science,Fairfax,VA,USA,22030"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziwei","family":"Zhu","sequence":"additional","affiliation":[{"name":"George Mason University,Department of Computer Science,Fairfax,VA,USA,22030"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Bai","year":"2023","journal-title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond"},{"key":"ref2","author":"Bai","year":"2025","journal-title":"Hallucination of Multimodal Large Language Models: A Survey"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"ref4","article-title":"Shikra: Unleashing Multimodal LLM\u2019s Referential Dialogue Magic","author":"Chen","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01356"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.439"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2024.1430984"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02553"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW65960.2025.00115"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00257"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.687"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref21","author":"Liu","year":"2024","journal-title":"Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref23","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.54254\/2755-2721\/2024.17851"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1111\/jels.12413"},{"key":"ref27","author":"Radford","year":"2021","journal-title":"Learning Transferable Visual Models From Natural Language Supervision"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1437"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.489"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02783"},{"key":"ref31","author":"Touvron","year":"2023","journal-title":"LLaMA: Open and Efficient Foundation Language Models"},{"key":"ref32","author":"Wang","year":"2024","journal-title":"AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.99"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3507000"},{"key":"ref35","author":"Ye","year":"2024","journal-title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality"},{"key":"ref36","author":"Yin","year":"2023","journal-title":"Woodpecker: Hallucination Correction for Multimodal Large Language Models"},{"key":"ref37","author":"Zhang","year":"2024","journal-title":"Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref39","author":"Zhou","year":"2024","journal-title":"Analyzing and Mitigating Object Hallucination in Large Vision-Language Models"},{"key":"ref40","author":"Zhu","year":"2023","journal-title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models"},{"key":"ref41","author":"Zhu","year":"2025","journal-title":"Mitigating Object Hallucinations in Large Vision-Language Models via Attention Calibration"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492278.pdf?arnumber=11492278","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:09:14Z","timestamp":1778047754000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492278\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00127","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}