{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T07:59:04Z","timestamp":1772006344705,"version":"3.50.1"},"reference-count":76,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"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\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,1]]},"DOI":"10.1109\/vcip67698.2025.11396889","type":"proceedings-article","created":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T20:55:27Z","timestamp":1771966527000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["CVBench: Benchmarking and Comparing Video Generation with Large Multimodal Models"],"prefix":"10.1109","author":[{"given":"Jiarui","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiyu","family":"Duan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuke","family":"Xing","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Cardiff University,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref2","article-title":"Ltx-video: Realtime video latent diffusion","author":"HaCohen","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref4","article-title":"Wan: Open and advanced large-scale video generative models","author":"Wang","year":"2025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref6","article-title":"Videollama 3: Frontier multimodal foundation models for image and video understanding","author":"Zhang"},{"key":"ref7","article-title":"Internvideo2.5: Empowering video mllms with long and rich context modeling","author":"Wang","year":"2025"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01758"},{"key":"ref9","article-title":"Measuring the quality of text-to-video model outputs: Metrics and dataset","author":"Chivileva","year":"2023"},{"key":"ref10","article-title":"Gaia: Rethinking action quality assessment for aigenerated videos","volume-title":"NeurIPS","author":"Chen"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref12","article-title":"Love: Benchmarking and evaluating text-to-video generation and video-to-text interpretation","author":"Wang","year":"2025"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00538"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"ref15","article-title":"Benchmarking aigc video quality assessment: A dataset and unified model","author":"Zhang","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680868"},{"key":"ref17","first-page":"500","article-title":"Methodology for the subjective assessment of the quality of television pictures","author":"Series","year":"2012","journal-title":"Recommendation ITU-R BT"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3220404"},{"key":"ref19","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2018.2816783"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2017.2788206"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2585880"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.133"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164467"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548329"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref31","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML","author":"Li"},{"key":"ref32","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume-title":"NeurIPS","author":"Schuhmann"},{"key":"ref33","first-page":"15903","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume-title":"NeurIPS","author":"Xu"},{"key":"ref34","article-title":"Deepseek-vl2: Mixture-of-experts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024"},{"key":"ref35","article-title":"mplug-owl3: Towards long image-sequence understanding in multi-modal large language models","volume-title":"ICLR","author":"Ye"},{"key":"ref36","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref37","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025"},{"key":"ref38","first-page":"2024","article-title":"Llama 3.2: Revolutionizing edge ai and vision with open, customizable models","volume":"20","author":"Meta","year":"2024","journal-title":"Meta AI Blog"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"ref40","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling","author":"Chen","year":"2024"},{"key":"ref41","article-title":"Enhancing the reasoning ability of multimodal large language models via mixed preference optimization","author":"Wang"},{"key":"ref42","article-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models","author":"Li","year":"2024"},{"key":"ref43","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024"},{"key":"ref44","article-title":"Gemini1.5-pro","year":"2024"},{"key":"ref45","article-title":"Claude3.5","year":"2024"},{"key":"ref46","article-title":"Grok2 vision","year":"2024"},{"key":"ref47","article-title":"Chatgpt-4o","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2016.2637168"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2651374"},{"key":"ref50","article-title":"Jimeng ai","year":"2024"},{"key":"ref51","article-title":"Pixverse: Ai video creation platform","author":"AI","year":"2024"},{"key":"ref52","article-title":"Sora","year":"2024"},{"key":"ref53","article-title":"Wanxiang","author":"Cloud","year":"2024"},{"key":"ref54","article-title":"Hailuo ai","year":"2024"},{"key":"ref55","article-title":"Hunyuan-dit: A powerful multi-resolution diffusion transformer with fine-grained chinese understanding","author":"Li"},{"key":"ref56","article-title":"Kling ai","year":"2024"},{"key":"ref57","article-title":"Introducing gen-3 alpha: A new frontier for video generation","year":"2024"},{"key":"ref58","article-title":"Vidu ai","year":"2024"},{"key":"ref59","article-title":"Gemo","year":"2024"},{"key":"ref60","article-title":"Xunfei","year":"2024"},{"key":"ref61","article-title":"Chatglm: A family of large language models from glm-130b to glm-4 all tools","author":"GLM","year":"2024"},{"key":"ref62","article-title":"Pyramidal flow matching for efficient video generative modeling","author":"Jin","year":"2024"},{"key":"ref63","article-title":"Allegro: Open the black box of commercial-level video generation model","author":"Zhou","year":"2024"},{"key":"ref64","article-title":"Easyanimate: A high-performance long video generation method based on transformer architecture","author":"Xu","year":"2024"},{"key":"ref65","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref67","article-title":"Hotshot-XL","author":"Mullan"},{"key":"ref68","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2025","journal-title":"Transactions on Machine Learning Research"},{"key":"ref69","article-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1797"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref72","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023"},{"key":"ref73","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022"},{"key":"ref74","article-title":"Zeroscope","year":"2024"},{"key":"ref75","article-title":"World model on million-length video and language with blockwise ringattention","author":"Liu","year":"2024"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"}],"event":{"name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","location":"Klagenfurt, Austria","start":{"date-parts":[[2025,12,1]]},"end":{"date-parts":[[2025,12,4]]}},"container-title":["2025 International Conference on Visual Communications and Image Processing (VCIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11396756\/11396790\/11396889.pdf?arnumber=11396889","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T07:02:47Z","timestamp":1772002967000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11396889\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/vcip67698.2025.11396889","relation":{},"subject":[],"published":{"date-parts":[[2025,12,1]]}}}