{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T16:39:21Z","timestamp":1792255161406,"version":"4.4.0"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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":["62522116"],"award-info":[{"award-number":["62522116"]}],"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":["62271312"],"award-info":[{"award-number":["62271312"]}],"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":["62132006"],"award-info":[{"award-number":["62132006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["22DZ2229005"],"award-info":[{"award-number":["22DZ2229005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tcsvt.2025.3619558","type":"journal-article","created":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:55:49Z","timestamp":1760032549000},"page":"3382-3396","source":"Crossref","is-referenced-by-count":2,"title":["Mitigating Low-Level Visual Hallucinations Requires Self-Awareness: Database, Model, and Training Strategy"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3054-4268","authenticated-orcid":false,"given":"Yinan","family":"Sun","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5693-0416","authenticated-orcid":false,"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7247-7938","authenticated-orcid":false,"given":"Zicheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6292-0529","authenticated-orcid":false,"given":"Yixuan","family":"Gao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqin","family":"Cao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-9322","authenticated-orcid":false,"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"71683","article-title":"OBELICS: An open Web-scale filtered dataset of interleaved image-text documents","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Lauren\u00e7on"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2729891"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3485684"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2902097"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967829"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3295375"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3544659"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3251695"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3616155"},{"key":"ref14","article-title":"AGAV-rater: Adapting large multimodal model for AI-generated audio-visual quality assessment","author":"Cao","year":"2025","journal-title":"arXiv:2501.18314"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3229839"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3282874"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3124322"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3393843"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4251-x"},{"key":"ref22","first-page":"53728","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Rafailov"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_22"},{"key":"ref24","article-title":"Improve vision language model chain-of-thought reasoning","author":"Zhang","year":"2024","journal-title":"arXiv:2410.16198"},{"key":"ref25","article-title":"Step-DPO: Step-wise preference optimization for long-chain reasoning of LLMs","author":"Lai","year":"2024","journal-title":"arXiv:2406.18629"},{"key":"ref26","article-title":"Secrets of RLHF in large language models Part I: PPO","author":"Zheng","year":"2023","journal-title":"arXiv:2307.04964"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01310"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00373"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.249"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611737"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_40"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3631357"},{"key":"ref34","first-page":"1","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"36","author":"Xu"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3319020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00211"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02408"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2019.8743252"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00363"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00070"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3445770"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_21"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_15"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680649"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"ref49","article-title":"Beyond hallucinations: Enhancing LVLMs through hallucination-aware direct preference optimization","author":"Zhao","year":"2023","journal-title":"arXiv:2311.16839"},{"key":"ref50","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2500021"},{"key":"ref52","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv:1504.00325"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2012.6489321"},{"key":"ref54","article-title":"MMBench: Is your multi-modal model an all-around player?","author":"Liu","year":"2023","journal-title":"arXiv:2307.06281"},{"key":"ref55","article-title":"Evaluation and enhancement of semantic grounding in large vision-language models","author":"Lu","year":"2023","journal-title":"arXiv:2309.04041"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3421895"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2875354"},{"key":"ref58","article-title":"LLaVA-OneVision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv:2408.03326"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3272224"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3437288"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref62","article-title":"Qwen2 technical report","volume-title":"arXiv:2407.10671","author":"Yang","year":"2024"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.89"},{"key":"ref64","first-page":"4299","article-title":"Deep reinforcement learning from human preferences","volume-title":"Proc. Adv. neural Inf. Process. Syst. (NIPS)","author":"Christiano"},{"key":"ref65","article-title":"Training a helpful and harmless assistant with reinforcement learning from human feedback","author":"Bai","year":"2022","journal-title":"arXiv:2204.05862"},{"key":"ref66","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Ouyang"},{"key":"ref67","first-page":"3008","article-title":"Learning to summarize with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"33","author":"Stiennon"},{"key":"ref68","article-title":"Camels in a changing climate: Enhancing LM adaptation with T\u00dcLU 2","author":"Ivison","year":"2023","journal-title":"arXiv:2311.10702"},{"key":"ref69","article-title":"Zephyr: Direct distillation of LM alignment","author":"Tunstall","year":"2023","journal-title":"arXiv:2310.16944"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.2307\/2346567"},{"key":"ref71","article-title":"Improved baselines with visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv:2310.03744"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01239"},{"key":"ref73","article-title":"MPLUG-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv:2304.14178"},{"key":"ref74","article-title":"InternLM-XComposer2: Mastering free-form text-image composition and comprehension in vision-language large model","author":"Dong","year":"2024","journal-title":"arXiv:2401.16420"},{"key":"ref75","article-title":"InternLM-XComposer-2.5: A versatile large vision language model supporting long-contextual input and output","author":"Zhang","year":"2024","journal-title":"arXiv:2407.03320"},{"key":"ref76","article-title":"InternLM-XComposer2-4KHD: A pioneering large vision-language model handling resolutions from 336 pixels to 4K HD","author":"Dong","year":"2024","journal-title":"arXiv:2404.06512"},{"key":"ref77","volume-title":"InfiMM: Advancing Multimodal Understanding From Flamingo\u2019s Legacy Through Diverse LLM Integration","author":"Team","year":"2024"},{"key":"ref78","volume-title":"Introducing Our Multimodal Models","author":"Bavishi et al","year":"2023"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"ref80","volume-title":"Gemini Pro","year":"2023"},{"key":"ref81","article-title":"UHD-IQA benchmark database: Pushing the boundaries of blind photo quality assessment","author":"Hosu","year":"2024","journal-title":"arXiv:2406.17472"},{"key":"ref82","article-title":"A note on DPO with noisy preferences & relationship to IPO","author":"Mitchell","year":"2023"},{"key":"ref83","first-page":"4447","article-title":"A general theoretical paradigm to understand learning from human preferences","volume-title":"Proc. Int. Conf. Artif. Intell. Statist. (AISTATS)","author":"Azar"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11424237\/11197535.pdf?arnumber=11197535","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:01:23Z","timestamp":1773086483000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11197535\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":83,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3619558","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}