{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:26:21Z","timestamp":1780673181138,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":77,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62401365, 62225112, 62101326, 62132006, U24A20220"],"award-info":[{"award-number":["62401365, 62225112, 62101326, 62132006, U24A20220"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["BX20250411, 2025M773473"],"award-info":[{"award-number":["BX20250411, 2025M773473"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758299","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:55Z","timestamp":1761377215000},"page":"13376-13383","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["HVEval: Towards Unified Evaluation of Human-Centric Video Generation and Understanding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7753-1596","authenticated-orcid":false,"given":"Sijing","family":"Wu","sequence":"first","affiliation":[{"name":"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":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6519-4067","authenticated-orcid":false,"given":"Huiyu","family":"Duan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6700-8110","authenticated-orcid":false,"given":"Yanwei","family":"Jiang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3069-060X","authenticated-orcid":false,"given":"Yucheng","family":"Zhu","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":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katherine Millican Malcolm Reynolds et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems Vol. 35 (2022) 23716-23736."},{"key":"e_1_3_2_1_2_1","volume-title":"arXiv preprint arXiv:2502.13923","author":"Bai Shuai","year":"2025","unstructured":"Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, Humen Zhong, Yuanzhi Zhu, Mingkun Yang, Zhaohai Li, Jianqiang Wan, Pengfei Wang, Wei Ding, Zheren Fu, Yiheng Xu, Jiabo Ye, Xi Zhang, Tianbao Xie, Zesen Cheng, Hang Zhang, Zhibo Yang, Haiyang Xu, and Junyang Lin. 2025. Qwen2.5-VL Technical Report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_1_3_1","unstructured":"Capcut. 2025. Dreamina. https:\/\/dreamina.capcut.com\/ai-tool\/home."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3088505"},{"key":"e_1_3_2_1_5_1","unstructured":"Guibin Chen Dixuan Lin Jiangping Yang Chunze Lin Juncheng Zhu Mingyuan Fan Hao Zhang Sheng Chen Zheng Chen Chengchen Ma et al. 2025. Skyreels-v2: Infinite-length film generative model. arXiv preprint arXiv:2504.13074 (2025)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"e_1_3_2_1_7_1","unstructured":"Zhe Chen Weiyun Wang Yue Cao Yangzhou Liu Zhangwei Gao Erfei Cui Jinguo Zhu Shenglong Ye Hao Tian Zhaoyang Liu et al. 2024a. Expanding performance boundaries of open-source multimodal models with model data and test-time scaling. arXiv preprint arXiv:2412.05271 (2024)."},{"key":"e_1_3_2_1_8_1","unstructured":"Zesen Cheng Sicong Leng Hang Zhang Yifei Xin Xin Li Guanzheng Chen Yongxin Zhu Wenqi Zhang Ziyang Luo Deli Zhao et al. 2024. Videollama 2: Advancing spatial-temporal modeling and audio understanding in video-llms. arXiv preprint arXiv:2406.07476 (2024)."},{"key":"e_1_3_2_1_9_1","volume-title":"Measuring the quality of text-to-video model outputs: Metrics and dataset. arXiv preprint arXiv:2309.08009","author":"Chivileva Iya","year":"2023","unstructured":"Iya Chivileva, Philip Lynch, Tomas E Ward, and Alan F Smeaton. 2023. Measuring the quality of text-to-video model outputs: Metrics and dataset. arXiv preprint arXiv:2309.08009 (2023)."},{"key":"e_1_3_2_1_10_1","unstructured":"Gemini. 2025. ChatGPT-4o. https:\/\/gemini.google.com\/."},{"key":"e_1_3_2_1_11_1","volume-title":"Ltx-video: Realtime video latent diffusion. arXiv preprint arXiv:2501.00103","author":"HaCohen Yoav","year":"2024","unstructured":"Yoav HaCohen, Nisan Chiprut, Benny Brazowski, Daniel Shalem, Dudu Moshe, Eitan Richardson, Eran Levin, Guy Shiran, Nir Zabari, Ori Gordon, et al., 2024. Ltx-video: Realtime video latent diffusion. arXiv preprint arXiv:2501.00103 (2024)."},{"key":"e_1_3_2_1_12_1","volume-title":"Ronan Le Bras, and Yejin Choi","author":"Hessel Jack","year":"2021","unstructured":"Jack Hessel, Ari Holtzman, Maxwell Forbes, Ronan Le Bras, and Yejin Choi. 2021. Clipscore: A reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)."},{"key":"e_1_3_2_1_13_1","unstructured":"Wenyi Hong Weihan Wang Ming Ding Wenmeng Yu Qingsong Lv Yan Wang Yean Cheng Shiyu Huang Junhui Ji Zhao Xue et al. 2024a. Cogvlm2: Visual language models for image and video understanding. arXiv preprint arXiv:2408.16500 (2024)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"e_1_3_2_1_16_1","first-page":"36652","article-title":"Pick-a-pic: An open dataset of user preferences for text-to-image generation","volume":"36","author":"Kirstain Yuval","year":"2023","unstructured":"Yuval Kirstain, Adam Polyak, Uriel Singer, Shahbuland Matiana, Joe Penna, and Omer Levy. 2023. Pick-a-pic: An open dataset of user preferences for text-to-image generation. Advances in Neural Information Processing Systems, Vol. 36 (2023), 36652-36663.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_17_1","volume-title":"Hunyuanvideo: A systematic framework for large video generative models. arXiv preprint arXiv:2412.03603","author":"Kong Weijie","year":"2024","unstructured":"Weijie Kong, Qi Tian, Zijian Zhang, Rox Min, Zuozhuo Dai, Jin Zhou, Jiangfeng Xiong, Xin Li, Bo Wu, Jianwei Zhang, et al., 2024. Hunyuanvideo: A systematic framework for large video generative models. arXiv preprint arXiv:2412.03603 (2024)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680868"},{"key":"e_1_3_2_1_19_1","unstructured":"Kuaishou. 2024. KLING. https:\/\/kling.kuaishou.com\/."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00538"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00726"},{"key":"e_1_3_2_1_22_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_23_1","volume-title":"International conference on machine learning. PMLR, 12888-12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888-12900."},{"key":"e_1_3_2_1_24_1","volume-title":"T2v-turbo-v2: Enhancing video generation model post-training through data, reward, and conditional guidance design. arXiv preprint arXiv:2410.05677","author":"Li Jiachen","year":"2024","unstructured":"Jiachen Li, Qian Long, Jian Zheng, Xiaofeng Gao, Robinson Piramuthu, Wenhu Chen, and William Yang Wang. 2024b. T2v-turbo-v2: Enhancing video generation model post-training through data, reward, and conditional guidance design. arXiv preprint arXiv:2410.05677 (2024)."},{"key":"e_1_3_2_1_25_1","volume-title":"AGHI-QA: A Subjective-Aligned Dataset and Metric for AI-Generated Human Images. arXiv preprint arXiv:2504.21308","author":"Li Yunhao","year":"2025","unstructured":"Yunhao Li, Sijing Wu, Wei Sun, Zhichao Zhang, Yucheng Zhu, Zicheng Zhang, Huiyu Duan, Xiongkuo Min, and Guangtao Zhai. 2025a. AGHI-QA: A Subjective-Aligned Dataset and Metric for AI-Generated Human Images. arXiv preprint arXiv:2504.21308 (2025)."},{"key":"e_1_3_2_1_26_1","volume-title":"Video-llava: Learning united visual representation by alignment before projection. arXiv preprint arXiv:2311.10122","author":"Lin Bin","year":"2023","unstructured":"Bin Lin, Yang Ye, Bin Zhu, Jiaxi Cui, Munan Ning, Peng Jin, and Li Yuan. 2023. Video-llava: Learning united visual representation by alignment before projection. arXiv preprint arXiv:2311.10122 (2023)."},{"key":"e_1_3_2_1_27_1","volume-title":"Animatediff-lightning: Cross-model diffusion distillation. arXiv preprint arXiv:2403.12706","author":"Lin Shanchuan","year":"2024","unstructured":"Shanchuan Lin and Xiao Yang. 2024. Animatediff-lightning: Cross-model diffusion distillation. arXiv preprint arXiv:2403.12706 (2024)."},{"key":"e_1_3_2_1_28_1","volume-title":"European Conference on Computer Vision. Springer, 366-384","author":"Lin Zhiqiu","year":"2024","unstructured":"Zhiqiu Lin, Deepak Pathak, Baiqi Li, Jiayao Li, Xide Xia, Graham Neubig, Pengchuan Zhang, and Deva Ramanan. 2024. Evaluating text-to-visual generation with image-to-text generation. In European Conference on Computer Vision. Springer, 366-384."},{"key":"e_1_3_2_1_29_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023b. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2023), 34892-34916."},{"key":"e_1_3_2_1_30_1","volume-title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration. arXiv preprint arXiv:2412.13155","author":"Liu Lu","year":"2024","unstructured":"Lu Liu, Huiyu Duan, Qiang Hu, Liu Yang, Chunlei Cai, Tianxiao Ye, Huayu Liu, Xiaoyun Zhang, and Guangtao Zhai. 2024b. F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration. arXiv preprint arXiv:2412.13155 (2024)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02090"},{"key":"e_1_3_2_1_32_1","first-page":"62352","article-title":"Fetv: A benchmark for fine-grained evaluation of open-domain text-to-video generation","volume":"36","author":"Liu Yuanxin","year":"2023","unstructured":"Yuanxin Liu, Lei Li, Shuhuai Ren, Rundong Gao, Shicheng Li, Sishuo Chen, Xu Sun, and Lu Hou. 2023a. Fetv: A benchmark for fine-grained evaluation of open-domain text-to-video generation. Advances in Neural Information Processing Systems, Vol. 36 (2023), 62352-62387.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_33_1","unstructured":"Haoyu Lu Wen Liu Bo Zhang Bingxuan Wang Kai Dong Bo Liu Jingxiang Sun Tongzheng Ren Zhuoshu Li Hao Yang et al. 2024b. Deepseek-vl: towards real-world vision-language understanding. arXiv preprint arXiv:2403.05525 (2024)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02453"},{"key":"e_1_3_2_1_35_1","unstructured":"Guoqing Ma Haoyang Huang Kun Yan Liangyu Chen Nan Duan Shengming Yin Changyi Wan Ranchen Ming Xiaoniu Song Xing Chen et al. 2025. Step-video-t2v technical report: The practice challenges and future of video foundation model. arXiv preprint arXiv:2502.10248 (2025)."},{"key":"e_1_3_2_1_36_1","volume-title":"Latte: Latent diffusion transformer for video generation. arXiv preprint arXiv:2401.03048","author":"Ma Xin","year":"2024","unstructured":"Xin Ma, Yaohui Wang, Gengyun Jia, Xinyuan Chen, Ziwei Liu, Yuan-Fang Li, Cunjian Chen, and Yu Qiao. 2024. Latte: Latent diffusion transformer for video generation. arXiv preprint arXiv:2401.03048 (2024)."},{"key":"e_1_3_2_1_37_1","volume-title":"Video-chatgpt: Towards detailed video understanding via large vision and language models. arXiv preprint arXiv:2306.05424","author":"Maaz Muhammad","year":"2023","unstructured":"Muhammad Maaz, Hanoona Rasheed, Salman Khan, and Fahad Shahbaz Khan. 2023. Video-chatgpt: Towards detailed video understanding via large vision and language models. arXiv preprint arXiv:2306.05424 (2023)."},{"key":"e_1_3_2_1_38_1","unstructured":"OpenAI. 2025. ChatGPT-4o. https:\/\/openai.com."},{"key":"e_1_3_2_1_39_1","volume-title":"Dreambench: A human-aligned benchmark for personalized image generation. arXiv preprint arXiv:2406.16855","author":"Peng Yuang","year":"2024","unstructured":"Yuang Peng, Yuxin Cui, Haomiao Tang, Zekun Qi, Runpei Dong, Jing Bai, Chunrui Han, Zheng Ge, Xiangyu Zhang, and Shu-Tao Xia. 2024. Dreambench: A human-aligned benchmark for personalized image generation. arXiv preprint arXiv:2406.16855 (2024)."},{"key":"e_1_3_2_1_40_1","unstructured":"Pika. 2025. Pika. https:\/\/www.pika.art."},{"key":"e_1_3_2_1_41_1","unstructured":"PixVerse. 2025. PixVerse. https:\/\/app.pixverse.ai."},{"key":"e_1_3_2_1_42_1","unstructured":"Yujia Qin Yining Ye Junjie Fang Haoming Wang Shihao Liang Shizuo Tian Junda Zhang Jiahao Li Yunxin Li Shijue Huang et al. 2025. UI-TARS: Pioneering Automated GUI Interaction with Native Agents. arXiv preprint arXiv:2501.12326 (2025)."},{"key":"e_1_3_2_1_43_1","volume-title":"International conference on machine learning. PmLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748-8763."},{"key":"e_1_3_2_1_44_1","unstructured":"Runway. 2024. Introducing Gen-3 Alpha: A New Frontier for Video Generation. https:\/\/runwayml.com\/blog\/introducing-gen-3-alpha\/."},{"key":"e_1_3_2_1_45_1","unstructured":"Christoph Schuhmann Romain Beaumont Richard Vencu Cade Gordon Ross Wightman Mehdi Cherti Theo Coombes Aarush Katta Clayton Mullis Mitchell Wortsman et al. 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in neural information processing systems Vol. 35 (2022) 25278-25294."},{"key":"e_1_3_2_1_46_1","volume-title":"Recommendation ITU-R BT","volume":"500","author":"Series B","year":"2012","unstructured":"B Series. 2012. Methodology for the subjective assessment of the quality of television pictures. Recommendation ITU-R BT, Vol. 500, 13 (2012)."},{"key":"e_1_3_2_1_47_1","unstructured":"Spencer Sterling. 2023. ZeroScope. https:\/\/huggingface.co\/cerspense\/zeroscope_v2_576w."},{"key":"e_1_3_2_1_48_1","volume-title":"T2v-compbench: A comprehensive benchmark for compositional text-to-video generation. arXiv preprint arXiv:2407.14505","author":"Sun Kaiyue","year":"2024","unstructured":"Kaiyue Sun, Kaiyi Huang, Xian Liu, Yue Wu, Zihan Xu, Zhenguo Li, and Xihui Liu. 2024a. T2v-compbench: A comprehensive benchmark for compositional text-to-video generation. arXiv preprint arXiv:2407.14505 (2024)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548329"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3385364"},{"key":"e_1_3_2_1_51_1","unstructured":"Genmo Team. 2024. Mochi 1. https:\/\/github.com\/genmoai\/models."},{"key":"e_1_3_2_1_52_1","unstructured":"OpenAI Team. 2025. Sora. https:\/\/openai.com\/sora\/."},{"key":"e_1_3_2_1_53_1","unstructured":"Hansi Teng Hongyu Jia Lei Sun Lingzhi Li Maolin Li Mingqiu Tang Shuai Han Tianning Zhang WQ Zhang Weifeng Luo et al. 2025. MAGI-1: Autoregressive Video Generation at Scale. arXiv preprint arXiv:2505.13211 (2025)."},{"key":"e_1_3_2_1_54_1","volume-title":"Wan: Open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314","author":"Wan Team","year":"2025","unstructured":"Team Wan, Ang Wang, Baole Ai, Bin Wen, Chaojie Mao, Chen-Wei Xie, Di Chen, Feiwu Yu, Haiming Zhao, Jianxiao Yang, et al., 2025. Wan: Open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)."},{"key":"e_1_3_2_1_55_1","volume-title":"Animatelcm: Computation-efficient personalized style video generation without personalized video data. In SIGGRAPH Asia 2024 Technical Communications. 1-5.","author":"Wang Fu-Yun","year":"2024","unstructured":"Fu-Yun Wang, Zhaoyang Huang, Weikang Bian, Xiaoyu Shi, Keqiang Sun, Guanglu Song, Yu Liu, and Hongsheng Li. 2024b. Animatelcm: Computation-efficient personalized style video generation without personalized video data. In SIGGRAPH Asia 2024 Technical Communications. 1-5."},{"key":"e_1_3_2_1_56_1","volume-title":"Modelscope text-to-video technical report. arXiv preprint arXiv:2308.06571","author":"Wang Jiuniu","year":"2023","unstructured":"Jiuniu Wang, Hangjie Yuan, Dayou Chen, Yingya Zhang, Xiang Wang, and Shiwei Zhang. 2023. Modelscope text-to-video technical report. arXiv preprint arXiv:2308.06571 (2023)."},{"key":"e_1_3_2_1_57_1","volume-title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. arXiv preprint arXiv:2409.12191","author":"Wang Peng","year":"2024","unstructured":"Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, and Junyang Lin. 2024a. Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_58_1","volume-title":"Is this Generated Person Existed in Real-world? Fine-grained Detecting and Calibrating Abnormal Human-body. arXiv preprint arXiv:2411.14205","author":"Wang Zeqing","year":"2024","unstructured":"Zeqing Wang, Qingyang Ma, Wentao Wan, Haojie Li, Keze Wang, and Yonghong Tian. 2024c. Is this Generated Person Existed in Real-world? Fine-grained Detecting and Calibrating Abnormal Human-body. arXiv preprint arXiv:2411.14205 (2024)."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"e_1_3_2_1_61_1","volume-title":"Q-align: Teaching lmms for visual scoring via discrete text-defined levels. arXiv preprint arXiv:2312.17090","author":"Wu Haoning","year":"2023","unstructured":"Haoning Wu, Zicheng Zhang, Weixia Zhang, Chaofeng Chen, Liang Liao, Chunyi Li, Yixuan Gao, Annan Wang, Erli Zhang, Wenxiu Sun, et al., 2023b. Q-align: Teaching lmms for visual scoring via discrete text-defined levels. arXiv preprint arXiv:2312.17090 (2023)."},{"key":"e_1_3_2_1_62_1","volume-title":"FVQ: A Large-Scale Dataset and A LMM-based Method for Face Video Quality Assessment. arXiv preprint arXiv:2504.09255","author":"Wu Sijing","year":"2025","unstructured":"Sijing Wu, Yunhao Li, Ziwen Xu, Yixuan Gao, Huiyu Duan, Wei Sun, and Guangtao Zhai. 2025. FVQ: A Large-Scale Dataset and A LMM-based Method for Face Video Quality Assessment. arXiv preprint arXiv:2504.09255 (2025)."},{"key":"e_1_3_2_1_63_1","unstructured":"Zhiyu Wu Xiaokang Chen Zizheng Pan Xingchao Liu Wen Liu Damai Dai Huazuo Gao Yiyang Ma Chengyue Wu Bingxuan Wang et al. 2024. Deepseek-vl2: Mixture-of-experts vision-language models for advanced multimodal understanding. arXiv preprint arXiv:2412.10302 (2024)."},{"key":"e_1_3_2_1_64_1","volume-title":"Videoclip: Contrastive pre-training for zero-shot video-text understanding. arXiv preprint arXiv:2109.14084","author":"Xu Hu","year":"2021","unstructured":"Hu Xu, Gargi Ghosh, Po-Yao Huang, Dmytro Okhonko, Armen Aghajanyan, Florian Metze, Luke Zettlemoyer, and Christoph Feichtenhofer. 2021. Videoclip: Contrastive pre-training for zero-shot video-text understanding. arXiv preprint arXiv:2109.14084 (2021)."},{"key":"e_1_3_2_1_65_1","first-page":"15903","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume":"36","author":"Xu Jiazheng","year":"2023","unstructured":"Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, and Yuxiao Dong. 2023. Imagereward: Learning and evaluating human preferences for text-to-image generation. Advances in Neural Information Processing Systems, Vol. 36 (2023), 15903-15935.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_66_1","volume-title":"Lmme3dhf: Benchmarking and evaluating multimodal 3d human face generation with lmms. arXiv preprint arXiv:2504.20466","author":"Yang Woo Yi","year":"2025","unstructured":"Woo Yi Yang, Jiarui Wang, Sijing Wu, Huiyu Duan, Yuxin Zhu, Liu Yang, Kang Fu, Guangtao Zhai, and Xiongkuo Min. 2025. Lmme3dhf: Benchmarking and evaluating multimodal 3d human face generation with lmms. arXiv preprint arXiv:2504.20466 (2025)."},{"key":"e_1_3_2_1_67_1","volume-title":"Cogvideox: Text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072","author":"Yang Zhuoyi","year":"2024","unstructured":"Zhuoyi Yang, Jiayan Teng, Wendi Zheng, Ming Ding, Shiyu Huang, Jiazheng Xu, Yuanming Yang, Wenyi Hong, Xiaohan Zhang, Guanyu Feng, et al., 2024. Cogvideox: Text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072 (2024)."},{"key":"e_1_3_2_1_68_1","volume-title":"mplug-owl3: Towards long image-sequence understanding in multi-modal large language models. arXiv preprint arXiv:2408.04840","author":"Ye Jiabo","year":"2024","unstructured":"Jiabo Ye, Haiyang Xu, Haowei Liu, Anwen Hu, Ming Yan, Qi Qian, Ji Zhang, Fei Huang, and Jingren Zhou. 2024. mplug-owl3: Towards long image-sequence understanding in multi-modal large language models. arXiv preprint arXiv:2408.04840 (2024)."},{"key":"e_1_3_2_1_69_1","volume-title":"Magictime: Time-lapse video generation models as metamorphic simulators","author":"Yuan Shenghai","year":"2025","unstructured":"Shenghai Yuan, Jinfa Huang, Yujun Shi, Yongqi Xu, Ruijie Zhu, Bin Lin, Xinhua Cheng, Li Yuan, and Jiebo Luo. 2025. Magictime: Time-lapse video generation models as metamorphic simulators. IEEE Transactions on Pattern Analysis and Machine Intelligence (2025)."},{"key":"e_1_3_2_1_70_1","unstructured":"Boqiang Zhang Kehan Li Zesen Cheng Zhiqiang Hu Yuqian Yuan Guanzheng Chen Sicong Leng Yuming Jiang Hang Zhang Xin Li et al. 2025. VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding. arXiv preprint arXiv:2501.13106 (2025)."},{"key":"e_1_3_2_1_71_1","volume-title":"Jia-Wei Liu, Rui Zhao, Lingmin Ran, Yuchao Gu, Difei Gao, and Mike Zheng Shou.","author":"Zhang David Junhao","year":"2024","unstructured":"David Junhao Zhang, Jay Zhangjie Wu, Jia-Wei Liu, Rui Zhao, Lingmin Ran, Yuchao Gu, Difei Gao, and Mike Zheng Shou. 2024d. Show-1: Marrying pixel and latent diffusion models for text-to-video generation. International Journal of Computer Vision (2024), 1-15."},{"key":"e_1_3_2_1_72_1","volume-title":"Video instruction tuning with synthetic data. arXiv preprint arXiv:2410.02713","author":"Zhang Yuanhan","year":"2024","unstructured":"Yuanhan Zhang, Jinming Wu, Wei Li, Bo Li, Zejun Ma, Ziwei Liu, and Chunyuan Li. 2024c. Video instruction tuning with synthetic data. arXiv preprint arXiv:2410.02713 (2024)."},{"key":"e_1_3_2_1_73_1","unstructured":"Zhichao Zhang Xinyue Li Wei Sun Jun Jia Xiongkuo Min Zicheng Zhang Chunyi Li Zijian Chen Puyi Wang Zhongpeng Ji et al. 2024a. Benchmarking AIGC Video Quality Assessment: A Dataset and Unified Model. arXiv preprint arXiv:2407.21408 (2024)."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"crossref","unstructured":"Zhichao Zhang Wei Sun Xinyue Li Yunhao Li Qihang Ge Jun Jia Zicheng Zhang Zhongpeng Ji Fengyu Sun Shangling Jui et al. 2024b. Human-Activity AGV Quality Assessment: A Benchmark Dataset and an Objective Evaluation Metric. arXiv preprint arXiv:2411.16619 (2024).","DOI":"10.1145\/3746027.3754731"},{"key":"e_1_3_2_1_75_1","volume-title":"Humanomni: A large vision-speech language model for human-centric video understanding. arXiv preprint arXiv:2501.15111","author":"Zhao Jiaxing","year":"2025","unstructured":"Jiaxing Zhao, Qize Yang, Yixing Peng, Detao Bai, Shimin Yao, Boyuan Sun, Xiang Chen, Shenghao Fu, Xihan Wei, Liefeng Bo, et al., 2025. Humanomni: A large vision-speech language model for human-centric video understanding. arXiv preprint arXiv:2501.15111 (2025)."},{"key":"e_1_3_2_1_76_1","unstructured":"Dian Zheng Ziqi Huang Hongbo Liu Kai Zou Yinan He Fan Zhang Yuanhan Zhang Jingwen He Wei-Shi Zheng Yu Qiao et al. 2025. Vbench-2.0: Advancing video generation benchmark suite for intrinsic faithfulness. arXiv preprint arXiv:2503.21755 (2025)."},{"key":"e_1_3_2_1_77_1","unstructured":"Jinguo Zhu Weiyun Wang Zhe Chen Zhaoyang Liu Shenglong Ye Lixin Gu Yuchen Duan Hao Tian Weijie Su Jie Shao et al. 2025. InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models. arXiv preprint arXiv:2504.10479 (2025)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3758299","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:07:09Z","timestamp":1765343229000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758299"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":77,"alternative-id":["10.1145\/3746027.3758299","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758299","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}