{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T15:37:03Z","timestamp":1788968223267,"version":"build-2803163510"},"reference-count":35,"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\/100009950","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009950","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002766","name":"Beijing University of Posts and Telecommunications","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002766","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\/icme59968.2025.11209127","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":2,"title":["Mitigating Object Hallucination in Large Vision-Language Models via Visual Attention Direct Preference Optimization"],"prefix":"10.1109","author":[{"given":"Yixiao","family":"He","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haifeng","family":"Sun","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Qi","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zirui","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfei","family":"Ren","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huazheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yafeng","family":"Nan","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref2","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2024","journal-title":"ICLR"},{"key":"ref3","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"issue":"2","key":"ref4","first-page":"3","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","volume":"1","author":"Bai","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref6","article-title":"Llava-next: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref9","article-title":"An llm-free multi-dimensional benchmark for mllms hallucination evaluation","author":"Wang","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"ref11","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov","year":"2024","journal-title":"NeurIPS"},{"key":"ref12","article-title":"Beyond hallucinations: Enhancing lvlms through hallucination-aware direct preference optimization","author":"Zhao","year":"2023"},{"key":"ref13","article-title":"Aligning modalities in vision large language models via preference fine-tuning","author":"Zhou","year":"2024"},{"key":"ref14","article-title":"Mitigating object hallucination via data augmented contrastive tuning","author":"Sarkar","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.358"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_22"},{"key":"ref17","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01310"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.460"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.775"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73404-5_15"},{"key":"ref23","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"NeurIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref25","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.633"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref29","article-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2019"},{"key":"ref30","article-title":"Multi-object hallucination in vision language models","author":"Chen","year":"2024","journal-title":"NeurIPS"},{"key":"ref31","article-title":"Are we on the right way for evaluating large vision-language models?","author":"Chen","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"ref33","article-title":"Analyzing and mitigating object hallucination in large vision-language models","author":"Zhou","year":"2024","journal-title":"ICLR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.414"},{"key":"ref35","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","author":"Liu","year":"2024","journal-title":"ICLR"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"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\/11209127.pdf?arnumber=11209127","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:30:35Z","timestamp":1761888635000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209127\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209127","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}