{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:07:08Z","timestamp":1765310828679,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755102","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:30:51Z","timestamp":1761377451000},"page":"3517-3526","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FingER: Content Aware Fine-grained Evaluation with Reasoning for AI-Generated Videos"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6249-6780","authenticated-orcid":false,"given":"Rui","family":"Chen","sequence":"first","affiliation":[{"name":"AMAP, Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9550-8098","authenticated-orcid":false,"given":"Lei","family":"Sun","sequence":"additional","affiliation":[{"name":"AMAP, Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1739-1548","authenticated-orcid":false,"given":"Jing","family":"Tang","sequence":"additional","affiliation":[{"name":"AMAP, Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2289-5558","authenticated-orcid":false,"given":"Geng","family":"Li","sequence":"additional","affiliation":[{"name":"AMAP, Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2548-0605","authenticated-orcid":false,"given":"Xiangxiang","family":"Chu","sequence":"additional","affiliation":[{"name":"AMAP, Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et al. 2025a. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_1_2_1","volume-title":"Univg-r1: Reasoning guided universal visual grounding with reinforcement learning. arXiv preprint arXiv:2505.14231","author":"Bai Sule","year":"2025","unstructured":"Sule Bai, Mingxing Li, Yong Liu, Jing Tang, Haoji Zhang, Lei Sun, Xiangxiang Chu, and Yansong Tang. 2025b. Univg-r1: Reasoning guided universal visual grounding with reinforcement learning. arXiv preprint arXiv:2505.14231 (2025)."},{"key":"e_1_3_2_1_3_1","volume-title":"Vidu: a highly consistent, dynamic and skilled text-to-video generator with diffusion models. arXiv preprint arXiv:2405.04233","author":"Bao Fan","year":"2024","unstructured":"Fan Bao, Chendong Xiang, Gang Yue, Guande He, Hongzhou Zhu, Kaiwen Zheng, Min Zhao, Shilong Liu, Yaole Wang, and Jun Zhu. 2024. Vidu: a highly consistent, dynamic and skilled text-to-video generator with diffusion models. arXiv preprint arXiv:2405.04233 (2024)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29720"},{"key":"e_1_3_2_1_5_1","first-page":"1","article-title":"Video generation models as world simulators","volume":"1","author":"Brooks Tim","year":"2024","unstructured":"Tim Brooks, Bill Peebles, Connor Holmes, Will DePue, Yufei Guo, Li Jing, David Schnurr, Joe Taylor, Troy Luhman, Eric Luhman, et al., 2024. Video generation models as world simulators. OpenAI Blog, Vol. 1, 8 (2024), 1.","journal-title":"OpenAI Blog"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 24185-24198","author":"Chen Zhe","year":"2024","unstructured":"Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, et al., 2024. Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 24185-24198."},{"key":"e_1_3_2_1_7_1","unstructured":"Jaemin Cho Yushi Hu Jason M Baldridge Roopal Garg Peter Anderson Ranjay Krishna Mohit Bansal Jordi Pont-Tuset and Su Wang. 2024. Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation. In ICLR."},{"key":"e_1_3_2_1_8_1","volume-title":"Gpg: A simple and strong reinforcement learning baseline for model reasoning. arXiv preprint arXiv:2504.02546","author":"Chu Xiangxiang","year":"2025","unstructured":"Xiangxiang Chu, Hailang Huang, Xiao Zhang, Fei Wei, and Yong Wang. 2025. Gpg: A simple and strong reinforcement learning baseline for model reasoning. arXiv preprint arXiv:2504.02546 (2025)."},{"key":"e_1_3_2_1_9_1","unstructured":"Xiangxiang Chu Limeng Qiao Xinyu Zhang Shuang Xu Fei Wei Yang Yang Xiaofei Sun Yiming Hu Xinyang Lin Bo Zhang et al. 2024. Mobilevlm v2: Faster and stronger baseline for vision language model. arXiv preprint arXiv:2402.03766 (2024)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.798"},{"key":"e_1_3_2_1_11_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.127"},{"key":"e_1_3_2_1_13_1","volume-title":"MMGenBench: Fully Automatically Evaluating LMMs from the Text-to-Image Generation Perspective. arXiv preprint arXiv:2411.14062","author":"Huang Hailang","year":"2024","unstructured":"Hailang Huang, Yong Wang, Zixuan Huang, Huaqiu Li, Tongwen Huang, Xiangxiang Chu, and Richong Zhang. 2024b. MMGenBench: Fully Automatically Evaluating LMMs from the Text-to-Image Generation Perspective. arXiv preprint arXiv:2411.14062 (2024)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"e_1_3_2_1_15_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680868"},{"key":"e_1_3_2_1_17_1","unstructured":"Solomon Kullback. 1951. Kullback-leibler divergence. Tech. Rep. (1951)."},{"key":"e_1_3_2_1_18_1","volume-title":"Step-dpo: Step-wise preference optimization for long-chain reasoning of llms. arXiv preprint arXiv:2406.18629","author":"Lai Xin","year":"2024","unstructured":"Xin Lai, Zhuotao Tian, Yukang Chen, Senqiao Yang, Xiangru Peng, and Jiaya Jia. 2024. Step-dpo: Step-wise preference optimization for long-chain reasoning of llms. arXiv preprint arXiv:2406.18629 (2024)."},{"key":"e_1_3_2_1_19_1","volume-title":"Synthetic Data for Computer Vision Workshop@ CVPR","author":"Li Baiqi","year":"2024","unstructured":"Baiqi Li, Zhiqiu Lin, Deepak Pathak, Jiayao Emily Li, Xide Xia, Graham Neubig, Pengchuan Zhang, and Deva Ramanan. 2024. Genai-bench: A holistic benchmark for compositional text-to-visual generation. In Synthetic Data for Computer Vision Workshop@ CVPR 2024."},{"key":"e_1_3_2_1_20_1","volume-title":"Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Model. arXiv preprint arXiv:2503.06141","author":"Li Mingxing","year":"2025","unstructured":"Mingxing Li, Rui Wang, Lei Sun, Yancheng Bai, and Xiangxiang Chu. 2025. Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Model. arXiv preprint arXiv:2503.06141 (2025)."},{"key":"e_1_3_2_1_21_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_22_1","volume-title":"VMBench: A Benchmark for Perception-Aligned Video Motion Generation. arXiv preprint arXiv:2503.10076","author":"Ling Xinran","year":"2025","unstructured":"Xinran Ling, Chen Zhu, Meiqi Wu, Hangyu Li, Xiaokun Feng, Cundian Yang, Aiming Hao, Jiashu Zhu, Jiahong Wu, and Xiangxiang Chu. 2025. VMBench: A Benchmark for Perception-Aligned Video Motion Generation. arXiv preprint arXiv:2503.10076 (2025)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02090"},{"key":"e_1_3_2_1_24_1","volume-title":"Wee Sun Lee, and Min Lin","author":"Liu Zichen","year":"2025","unstructured":"Zichen Liu, Changyu Chen, Wenjun Li, Penghui Qi, Tianyu Pang, Chao Du, Wee Sun Lee, and Min Lin. 2025a. Understanding r1-zero-like training: A critical perspective. arXiv preprint arXiv:2503.20783 (2025)."},{"key":"e_1_3_2_1_25_1","volume-title":"Visual-rft: Visual reinforcement fine-tuning. arXiv preprint arXiv:2503.01785","author":"Liu Ziyu","year":"2025","unstructured":"Ziyu Liu, Zeyi Sun, Yuhang Zang, Xiaoyi Dong, Yuhang Cao, Haodong Duan, Dahua Lin, and Jiaqi Wang. 2025b. Visual-rft: Visual reinforcement fine-tuning. arXiv preprint arXiv:2503.01785 (2025)."},{"key":"e_1_3_2_1_26_1","volume-title":"Improved techniques for training gans. Advances in neural information processing systems","author":"Salimans Tim","year":"2016","unstructured":"Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen. 2016. Improved techniques for training gans. Advances in neural information processing systems, Vol. 29 (2016)."},{"key":"e_1_3_2_1_27_1","volume-title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300","author":"Shao Zhihong","year":"2024","unstructured":"Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Yang Wu, et al., 2024. Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)."},{"key":"e_1_3_2_1_28_1","unstructured":"Genmo Team. 2024. Mochi 1. https:\/\/github.com\/genmoai\/models."},{"key":"e_1_3_2_1_29_1","volume-title":"Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al.","author":"Team Gemini","year":"2024","unstructured":"Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al., 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"e_1_3_2_1_31_1","volume-title":"ICLR 2019 Workshop DeepGenStruct","author":"Unterthiner Thomas","year":"2019","unstructured":"Thomas Unterthiner, Sjoerd Van Steenkiste, Karol Kurach, Rapha\u00ebl Marinier, Marcin Michalski, and Sylvain Gelly. 2019. FVD: A new metric for video generation. ICLR 2019 Workshop DeepGenStruct (2019)."},{"key":"e_1_3_2_1_32_1","volume-title":"TRL: Transformer Reinforcement Learning. https:\/\/github.com\/huggingface\/trl.","author":"von Werra Leandro","year":"2020","unstructured":"Leandro von Werra, Younes Belkada, Lewis Tunstall, Edward Beeching, Tristan Thrush, Nathan Lambert, Shengyi Huang, Kashif Rasul, and Quentin Gallou\u00e9dec. 2020. TRL: Transformer Reinforcement Learning. https:\/\/github.com\/huggingface\/trl."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"e_1_3_2_1_34_1","volume-title":"Unified multimodal chain-of-thought reward model through reinforcement fine-tuning. arXiv preprint arXiv:2505.03318","author":"Wang Yibin","year":"2025","unstructured":"Yibin Wang, Zhimin Li, Yuhang Zang, Chunyu Wang, Qinglin Lu, Cheng Jin, and Jiaqi Wang. 2025a. Unified multimodal chain-of-thought reward model through reinforcement fine-tuning. arXiv preprint arXiv:2505.03318 (2025)."},{"key":"e_1_3_2_1_35_1","volume-title":"Lift: Leveraging human feedback for text-to-video model alignment. arXiv preprint arXiv:2412.04814","author":"Wang Yibin","year":"2024","unstructured":"Yibin Wang, Zhiyu Tan, Junyan Wang, Xiaomeng Yang, Cheng Jin, and Hao Li. 2024. Lift: Leveraging human feedback for text-to-video model alignment. arXiv preprint arXiv:2412.04814 (2024)."},{"key":"e_1_3_2_1_36_1","volume-title":"Unified reward model for multimodal understanding and generation. arXiv preprint arXiv:2503.05236","author":"Wang Yibin","year":"2025","unstructured":"Yibin Wang, Yuhang Zang, Hao Li, Cheng Jin, and Jiaqi Wang. 2025b. Unified reward model for multimodal understanding and generation. arXiv preprint arXiv:2503.05236 (2025)."},{"key":"e_1_3_2_1_37_1","volume-title":"Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al., 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, Vol. 35 (2022), 24824-24837."},{"key":"e_1_3_2_1_38_1","volume-title":"Godiva: Generating open-domain videos from natural descriptions. arXiv preprint arXiv:2104.14806","author":"Wu Chenfei","year":"2021","unstructured":"Chenfei Wu, Lun Huang, Qianxi Zhang, Binyang Li, Lei Ji, Fan Yang, Guillermo Sapiro, and Nan Duan. 2021. Godiva: Generating open-domain videos from natural descriptions. arXiv preprint arXiv:2104.14806 (2021)."},{"key":"e_1_3_2_1_39_1","volume-title":"International Conference on Machine Learning. PMLR, 54015-54029","author":"Wu Haoning","year":"2024","unstructured":"Haoning Wu, Zicheng Zhang, Weixia Zhang, Chaofeng Chen, Liang Liao, Chunyi Li, Yixuan Gao, Annan Wang, Erli Zhang, Wenxiu Sun, et al., 2024b. Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels. In International Conference on Machine Learning. PMLR, 54015-54029."},{"key":"e_1_3_2_1_40_1","volume-title":"Jia-Wei Liu, Yuchao Gu, Rui Zhao, et al.","author":"Wu Jay Zhangjie","year":"2024","unstructured":"Jay Zhangjie Wu, Guian Fang, Haoning Wu, Xintao Wang, Yixiao Ge, Xiaodong Cun, David Junhao Zhang, Jia-Wei Liu, Yuchao Gu, Rui Zhao, et al., 2024a. Towards a better metric for text-to-video generation. arXiv preprint arXiv:2401.07781 (2024)."},{"key":"e_1_3_2_1_41_1","volume-title":"Visionreward: Fine-grained multi-dimensional human preference learning for image and video generation. arXiv preprint arXiv:2412.21059","author":"Xu Jiazheng","year":"2024","unstructured":"Jiazheng Xu, Yu Huang, Jiale Cheng, Yuanming Yang, Jiajun Xu, Yuan Wang, Wenbo Duan, Shen Yang, Qunlin Jin, Shurun Li, et al., 2024. Visionreward: Fine-grained multi-dimensional human preference learning for image and video generation. arXiv preprint arXiv:2412.21059 (2024)."},{"key":"e_1_3_2_1_42_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_43_1","volume-title":"Tree of thoughts: Deliberate problem solving with large language models. Advances in neural information processing systems","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. Advances in neural information processing systems, Vol. 36 (2023), 11809-11822."},{"key":"e_1_3_2_1_44_1","volume-title":"Limo: Less is more for reasoning. arXiv preprint arXiv:2502.03387","author":"Ye Yixin","year":"2025","unstructured":"Yixin Ye, Zhen Huang, Yang Xiao, Ethan Chern, Shijie Xia, and Pengfei Liu. 2025. Limo: Less is more for reasoning. arXiv preprint arXiv:2502.03387 (2025)."},{"key":"e_1_3_2_1_45_1","volume-title":"The dawn of video generation: Preliminary explorations with sora-like models. arXiv preprint arXiv:2410.05227","author":"Zeng Ailing","year":"2024","unstructured":"Ailing Zeng, Yuhang Yang, Weidong Chen, and Wei Liu. 2024. The dawn of video generation: Preliminary explorations with sora-like models. arXiv preprint arXiv:2410.05227 (2024)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"e_1_3_2_1_47_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_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-demos.38"},{"key":"e_1_3_2_1_49_1","volume-title":"Open-sora: Democratizing efficient video production for all. arXiv preprint arXiv:2412.20404","author":"Zheng Zangwei","year":"2024","unstructured":"Zangwei Zheng, Xiangyu Peng, Tianji Yang, Chenhui Shen, Shenggui Li, Hongxin Liu, Yukun Zhou, Tianyi Li, and Yang You. 2024a. Open-sora: Democratizing efficient video production for all. arXiv preprint arXiv:2412.20404 (2024)."},{"key":"e_1_3_2_1_50_1","volume-title":"R1-Zero's'' Aha Moment'' in Visual Reasoning on a 2B Non-SFT Model. arXiv preprint arXiv:2503.05132","author":"Zhou Hengguang","year":"2025","unstructured":"Hengguang Zhou, Xirui Li, Ruochen Wang, Minhao Cheng, Tianyi Zhou, and Cho-Jui Hsieh. 2025. R1-Zero's'' Aha Moment'' in Visual Reasoning on a 2B Non-SFT Model. arXiv preprint arXiv:2503.05132 (2025)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:04:07Z","timestamp":1765310647000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755102"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":50,"alternative-id":["10.1145\/3746027.3755102","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755102","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"}}]}}