{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T14:05:53Z","timestamp":1784556353984,"version":"3.55.0"},"reference-count":91,"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":[{"name":"National Key Research and Development Program of China","award":["2023YFC2508704"],"award-info":[{"award-number":["2023YFC2508704"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62236008"],"award-info":[{"award-number":["62236008"]}],"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":["62441232"],"award-info":[{"award-number":["62441232"]}],"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":["U21B2038"],"award-info":[{"award-number":["U21B2038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","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.2025.3618949","type":"journal-article","created":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T17:53:08Z","timestamp":1759859588000},"page":"3497-3512","source":"Crossref","is-referenced-by-count":2,"title":["Asking Questions to Alleviate Object Hallucination in Large Vision-Language Models"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5895-1202","authenticated-orcid":false,"given":"Chao","family":"Bi","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiantian","family":"Dang","sequence":"additional","affiliation":[{"name":"School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5931-0527","authenticated-orcid":false,"given":"Shuhui","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Intelligent Manufacturing and Control Engineering, Qilu Institute of Technology, Jinan, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-296X","authenticated-orcid":false,"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref2","article-title":"Gpt-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref3","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref6","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref7","article-title":"MultiModal-GPT: A vision and language model for dialogue with humans","author":"Gong","year":"2023","journal-title":"arXiv:2305.04790"},{"key":"ref8","article-title":"MPLUG-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv:2304.14178"},{"key":"ref9","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv:2306.14565"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.397"},{"key":"ref11","article-title":"Evaluation and analysis of hallucination in large vision-language models","author":"Wang","year":"2023","journal-title":"arXiv:2308.15126"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00971"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1203"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00502"},{"key":"ref17","article-title":"Visual perturbation-aware collaborative learning for overcoming the language prior problem","author":"Han","year":"2022","journal-title":"arXiv:2207.11850"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"ref19","first-page":"5721","article-title":"Overcoming language priors in visual question answering via distinguishing superficially similar instances","volume-title":"Proc. 29th Int. Conf. Comput. Linguistics","author":"Wu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-14167-2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-6207-5_4"},{"key":"ref22","first-page":"1","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28338"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2965966"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4251-x"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref28","article-title":"Mitigating object hallucinations in large vision-language models with assembly of global and local attention","author":"An","year":"2024","journal-title":"arXiv:2406.12718"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/coli.a.16"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.173"},{"key":"ref33","first-page":"1","article-title":"Wizard of wikipedia: Knowledge-powered conversational agents","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dinan"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.200"},{"key":"ref35","first-page":"2206","article-title":"Improving language models by retrieving from trillions of tokens","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Borgeaud"},{"key":"ref36","article-title":"Check your facts and try again: Improving large language models with external knowledge and automated feedback","author":"Peng","year":"2023","journal-title":"arXiv:2302.12813"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.463"},{"key":"ref38","article-title":"The web is your oyster\u2013knowledge-intensive NLP against a very large web corpus","author":"Piktus","year":"2021","journal-title":"arXiv:2112.09924"},{"key":"ref39","article-title":"BlenderBot 3: A deployed conversational agent that continually learns to responsibly engage","author":"Shuster","year":"2022","journal-title":"arXiv:2208.03188"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.741"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07421-0"},{"key":"ref43","first-page":"34586","article-title":"Factuality enhanced language models for open-ended text generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.311"},{"key":"ref45","article-title":"Self-contradictory hallucinations of large language models: Evaluation, detection and mitigation","author":"M\u00fcndler","year":"2023","journal-title":"arXiv:2305.15852"},{"key":"ref46","article-title":"PURR: Efficiently editing language model hallucinations by denoising language model corruptions","author":"Chen","year":"2023","journal-title":"arXiv:2305.14908"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3294261"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3338459"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014775"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3349567"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3319020"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3341840"},{"key":"ref53","article-title":"A survey on hallucination in large vision-language models","author":"Liu","year":"2024","journal-title":"arXiv:2402.00253"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.262"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.60"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref59","article-title":"Towards language models that can see: Computer vision through the LENS of natural language","author":"Berrios","year":"2023","journal-title":"arXiv:2306.16410"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.200"},{"key":"ref61","article-title":"ChatGPT asks, BLIP-2 answers: Automatic questioning towards enriched visual descriptions","author":"Zhu","year":"2023","journal-title":"arXiv:2303.06594"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.755"},{"key":"ref63","article-title":"Visual ChatGPT: Talking, drawing and editing with visual foundation models","author":"Wu","year":"2023","journal-title":"arXiv:2303.04671"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01460"},{"key":"ref65","article-title":"Caption anything: Interactive image description with diverse multimodal controls","author":"Wang","year":"2023","journal-title":"arXiv:2305.02677"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00249"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"ref68","first-page":"38154","article-title":"HuggingGPT: Solving AI tasks with ChatGPT and its friends in hugging face","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Shen"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3149"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3315133"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3040900"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3253210"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3326373"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2975798"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3404374"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3067449"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3468872"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3472810"},{"issue":"6","key":"ref79","first-page":"1111","article-title":"Review of omnimedia content quality evaluation","volume":"38","author":"Yan","year":"2022","journal-title":"J. Signal Process."},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680777"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3350695"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01224"},{"key":"ref83","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Human Lang. Technol.","author":"Devlin"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2124"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.841"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i22.34512"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11424237\/11195828.pdf?arnumber=11195828","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:00:42Z","timestamp":1773086442000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11195828\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":91,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3618949","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}