{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:25:21Z","timestamp":1783095921225,"version":"3.54.6"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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":["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":["62301316"],"award-info":[{"award-number":["62301316"]}],"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":["62225112"],"award-info":[{"award-number":["62225112"]}],"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"}]},{"DOI":"10.13039\/501100001809","name":"Oceanic Interdisciplinary Program of Shanghai Jiao Tong University","doi-asserted-by":"publisher","award":["SL2020ZD102"],"award-info":[{"award-number":["SL2020ZD102"]}],"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":[[2025,11]]},"DOI":"10.1109\/tcsvt.2025.3571788","type":"journal-article","created":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T13:17:05Z","timestamp":1747747025000},"page":"11083-11096","source":"Crossref","is-referenced-by-count":21,"title":["LMM-VQA: Advancing Video Quality Assessment With Large Multimodal Models"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2981-7460","authenticated-orcid":false,"given":"Qihang","family":"Ge","sequence":"first","affiliation":[{"name":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8162-1949","authenticated-orcid":false,"given":"Wei","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Communication and Electronic Engineering, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7337-1748","authenticated-orcid":false,"given":"Yunhao","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9532-7035","authenticated-orcid":false,"given":"Zhongpeng","family":"Ji","sequence":"additional","affiliation":[{"name":"Huawei Technologies, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengyu","family":"Sun","sequence":"additional","affiliation":[{"name":"Huawei Technologies, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1047-4264","authenticated-orcid":false,"given":"Shangling","family":"Jui","sequence":"additional","affiliation":[{"name":"Huawei Technologies, 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":"Institute of Image Communication and Information Processing, 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":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"OpenAI","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2868262"},{"key":"ref3","article-title":"X-IQE: EXplainable image quality evaluation for text-to-image generation with visual large language models","author":"Chen","year":"2023","journal-title":"arXiv:2305.10843"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1186\/s42492-024-00171-w"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2168411"},{"key":"ref6","article-title":"VideoLLaMA 2: Advancing spatial\u2013temporal modeling and audio understanding in video-LLMs","author":"Cheng","year":"2024","journal-title":"arXiv:2406.07476"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2053549"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00591"},{"key":"ref10","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023","journal-title":"arXiv:2305.06500"},{"key":"ref11","article-title":"GenzIQA: Generalized image quality assessment using prompt-guided latent diffusion models","author":"De","year":"2024","journal-title":"arXiv:2406.04654"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref13","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00373"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3485684"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2500021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2707479"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2401732"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2007.913755"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2017.7965673"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967829"},{"key":"ref24","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jaegle"},{"key":"ref25","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","journal-title":"arXiv:2001.08361"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2923051"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164467"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"ref29","article-title":"LLaVA-NeXT-interleave: Tackling multi-image, video, and 3D in large multimodal models","author":"Li","year":"2024","journal-title":"arXiv:2407.07895"},{"key":"ref30","article-title":"Videochat: Chat-centric video understanding","author":"Li","year":"2024","journal-title":"arXiv:2305.06355"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref32","article-title":"Video-LLaVA: Learning united visual representation by alignment before projection","author":"Lin","year":"2023","journal-title":"arXiv:2311.10122"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref35","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611795"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01296"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240643"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2548247"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4133-3"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2502725"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref46","first-page":"1143","article-title":"Im2Text: Describing images using 1 million captioned photographs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Ord\u00f3\u00f1ez"},{"key":"ref47","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ouyang"},{"key":"ref48","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2191563"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2299154"},{"key":"ref51","first-page":"5","article-title":"LAION-400M: Open dataset of CLIP-filtered 400 million image-text pairs","volume-title":"Proc. NeurIPS Workshop Datacentric AI, DCAI","author":"Schuhmann"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2836974"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2869673"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2214933"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548329"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW53276.2021.9455999"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3385364"},{"key":"ref59","article-title":"Enhancing blind video quality assessment with rich quality-aware features","author":"Sun","year":"2024","journal-title":"arXiv:2405.08745"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.5201\/ipol.2013.26"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072221"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2021.3090333"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2019.8901772"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01323"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249741"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref70","first-page":"10404","article-title":"Q-bench: A benchmark for general-purpose foundation models on low-level vision","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Wu"},{"key":"ref71","article-title":"Q-instruct: Improving low-level visual abilities for multi-modality foundation models","author":"Wu","year":"2023","journal-title":"arXiv:2311.06783"},{"key":"ref72","first-page":"54015","article-title":"Q-align: Teaching LMMs for visual scoring via discrete text-defined levels","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref73","article-title":"CLIPVQA: Video quality assessment via CLIP","author":"Xing","year":"2024","journal-title":"arXiv:2407.04928"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01239"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506420"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01380"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00363"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW54805.2022.00013"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00274"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref81","article-title":"InternLM-XComposer: A vision-language large model for advanced text-image comprehension and composition","author":"Zhang","year":"2023","journal-title":"arXiv:2309.15112"},{"key":"ref82","article-title":"LLaMA-adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2023","journal-title":"arXiv:2303.16199"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3061932"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3445770"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00174"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207148"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3434999"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2363737"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11223720\/11008449.pdf?arnumber=11008449","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:41:06Z","timestamp":1767638466000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11008449\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":88,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3571788","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}