{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:26:24Z","timestamp":1780673184308,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":88,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62301316"],"award-info":[{"award-number":["No.62301316"]}],"id":[{"id":"10.13039\/501100001809","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\/3746027.3754731","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:51Z","timestamp":1761377211000},"page":"6771-6780","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Human-Activity AGV Quality Assessment: A Benchmark Dataset and an Objective Evaluation Metric"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1466-6383","authenticated-orcid":false,"given":"Zhichao","family":"Zhang","sequence":"first","affiliation":[{"name":"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":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7362-0532","authenticated-orcid":false,"given":"Xinyue","family":"Li","sequence":"additional","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\/0009-0003-2981-7460","authenticated-orcid":false,"given":"qihang","family":"ge","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5424-4284","authenticated-orcid":false,"given":"Jun","family":"Jia","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7247-7938","authenticated-orcid":false,"given":"Zicheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"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"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8258-8109","authenticated-orcid":false,"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":"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":"Stability AI. 2024a. StableVideo. https:\/\/www.stablevideo.com\/"},{"key":"e_1_3_2_1_2_1","unstructured":"Zhipu AI. 2024b. Ying. https:\/\/chatglm.cn\/video"},{"key":"e_1_3_2_1_3_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_4_1","unstructured":"ByteDance. 2024. Dreamina. https:\/\/jimeng.jianying.com\/"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_6_1","volume-title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models. arXiv","author":"Chen Haoxin","year":"2024","unstructured":"Haoxin Chen, Yong Zhang, Xiaodong Cun, Menghan Xia, Xintao Wang, Chao Weng, and Ying Shan. 2024a. VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models. arXiv (2024). showeprint2401.09047 [cs.CV]"},{"key":"e_1_3_2_1_7_1","volume-title":"Videocrafter2: Overcoming data limitations for high-quality video diffusion models. arXiv preprint arXiv:2401.09047","author":"Chen Haoxin","year":"2024","unstructured":"Haoxin Chen, Yong Zhang, Xiaodong Cun, Menghan Xia, Xintao Wang, Chao Weng, and Ying Shan. 2024b. Videocrafter2: Overcoming data limitations for high-quality video diffusion models. arXiv preprint arXiv:2401.09047 (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":"Sheng Zheng, Jingyao Zheng, Lik-Hang Lee, Tae-Ho Kim, Choong Seon Hong, and Chaoning Zhang.","author":"Cho Joseph","year":"2024","unstructured":"Joseph Cho, Fachrina Dewi Puspitasari, Sheng Zheng, Jingyao Zheng, Lik-Hang Lee, Tae-Ho Kim, Choong Seon Hong, and Chaoning Zhang. 2024. Sora as an agi world model? a complete survey on text-to-video generation. arXiv preprint arXiv:2403.05131 (2024)."},{"key":"e_1_3_2_1_10_1","unstructured":"Alibaba Cloud. 2025. Wanxiang. https:\/\/tongyi.aliyun.com\/wanxiang"},{"key":"e_1_3_2_1_11_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv:2010.11929 [cs.CV] https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00373"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"e_1_3_2_1_16_1","volume-title":"International Conference on Learning Representations","author":"Guo Yuwei","year":"2024","unstructured":"Yuwei Guo, Ceyuan Yang, Anyi Rao, Zhengyang Liang, Yaohui Wang, Yu Qiao, Maneesh Agrawala, Dahua Lin, and Bo Dai. 2024. AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning. International Conference on Learning Representations (2024)."},{"key":"e_1_3_2_1_17_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, Poriya Panet, Sapir Weissbuch, Victor Kulikov, Yaki Bitterman, Zeev Melumian, and Ofir Bibi. 2024. LTX-Video: Realtime Video Latent Diffusion. arXiv preprint arXiv:2501.00103 (2024)."},{"key":"e_1_3_2_1_18_1","volume-title":"Transformer in transformer. Advances in neural information processing systems","author":"Han Kai","year":"2021","unstructured":"Kai Han, An Xiao, Enhua Wu, Jianyuan Guo, Chunjing Xu, and Yunhe Wang. 2021. Transformer in transformer. Advances in neural information processing systems, Vol. 34 (2021), 15908-15919."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_20_1","volume-title":"Consistent, Dynamic, and Extendable Long Video Generation from Text. arXiv preprint arXiv:2403.14773","author":"Henschel Roberto","year":"2024","unstructured":"Roberto Henschel, Levon Khachatryan, Daniil Hayrapetyan, Hayk Poghosyan, Vahram Tadevosyan, Zhangyang Wang, Shant Navasardyan, and Humphrey Shi. 2024. StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text. arXiv preprint arXiv:2403.14773 (2024)."},{"key":"e_1_3_2_1_21_1","volume-title":"Advances in Neural Information Processing Systems","author":"Heusel Martin","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc."},{"key":"e_1_3_2_1_22_1","first-page":"8633","article-title":"Video diffusion models","volume":"35","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho, Tim Salimans, Alexey Gritsenko, William Chan, Mohammad Norouzi, and David J Fleet. 2022. Video diffusion models. Advances in Neural Information Processing Systems, Vol. 35 (2022), 8633-8646.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Hong Wenyi","year":"2022","unstructured":"Wenyi Hong, Ming Ding, Wendi Zheng, Xinghan Liu, and Jie Tang. 2022. CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2017.7965673"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967829"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.224"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"e_1_3_2_1_29_1","volume-title":"Peter Selednik, Stuart Anderson, and Shunsuke Saito.","author":"Khirodkar Rawal","year":"2024","unstructured":"Rawal Khirodkar, Timur Bagautdinov, Julieta Martinez, Su Zhaoen, Austin James, Peter Selednik, Stuart Anderson, and Shunsuke Saito. 2024. Sapiens: Foundation for Human Vision Models. arXiv:2408.12569 [cs.CV]"},{"key":"e_1_3_2_1_30_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Kirstain Yuval","year":"2023","unstructured":"Yuval Kirstain, Adam Poliak, Uriel Singer, and Omer Levy. 2023. Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation. In Advances in Neural Information Processing Systems, Vol. 36."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2923051"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680868"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","unstructured":"PKU-Yuan Lab and Tuzhan AI etc. 2024. Open-Sora-Plan. https:\/\/doi.org\/10.5281\/zenodo.10948109","DOI":"10.5281\/zenodo.10948109"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164467"},{"key":"e_1_3_2_1_35_1","volume-title":"Llava-onevision: Easy visual task transfer. arXiv preprint arXiv:2408.03326","author":"Li Bo","year":"2024","unstructured":"Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Yanwei Li, Ziwei Liu, and Chunyuan Li. 2024a. Llava-onevision: Easy visual task transfer. arXiv preprint arXiv:2408.03326 (2024)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3319020"},{"key":"e_1_3_2_1_37_1","volume-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models. arXiv preprint arXiv:2407.07895","author":"Li Feng","year":"2024","unstructured":"Feng Li, Renrui Zhang, Hao Zhang, Yuanhan Zhang, Bo Li, Wei Li, Zejun Ma, and Chunyuan Li. 2024b. Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models. arXiv preprint arXiv:2407.07895 (2024)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"e_1_3_2_1_39_1","volume-title":"Computer Vision - ECCV","author":"Li Yanwei","year":"2024","unstructured":"Yanwei Li, Chengyao Wang, and Jiaya Jia. 2025. LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models. In Computer Vision - ECCV 2024, Ale\u0161 Leonardis, Elisa Ricci, Stefan Roth, Olga Russakovsky, Torsten Sattler, and G\u00fcl Varol (Eds.). Springer Nature Switzerland, Cham, 323-340."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00945"},{"key":"e_1_3_2_1_41_1","first-page":"15420","article-title":"Nuwa-infinity: Autoregressive over autoregressive generation for infinite visual synthesis","volume":"35","author":"Liang Jian","year":"2022","unstructured":"Jian Liang, Chenfei Wu, Xiaowei Hu, Zhe Gan, Jianfeng Wang, Lijuan Wang, Zicheng Liu, Yuejian Fang, and Nan Duan. 2022. Nuwa-infinity: Autoregressive over autoregressive generation for infinite visual synthesis. Advances in Neural Information Processing Systems, Vol. 35 (2022), 15420-15432.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"e_1_3_2_1_43_1","volume-title":"A Survey of AI-Generated Video Evaluation. arXiv preprint arXiv:2410.19884","author":"Liu Xiao","year":"2024","unstructured":"Xiao Liu, Xinhao Xiang, Zizhong Li, Yongheng Wang, Zhuoheng Li, Zhuosheng Liu, Weidi Zhang, Weiqi Ye, and Jiawei Zhang. 2024b. A Survey of AI-Generated Video Evaluation. arXiv preprint arXiv:2410.19884 (2024)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02090"},{"key":"e_1_3_2_1_45_1","volume-title":"FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation. arXiv preprint arXiv: 2311.01813","author":"Liu Yuanxin","year":"2023","unstructured":"Yuanxin Liu, Lei Li, Shuhuai Ren, Rundong Gao, Shicheng Li, Sishuo Chen, Xu Sun, and Lu Hou. 2023. FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation. arXiv preprint arXiv: 2311.01813 (2023)."},{"key":"e_1_3_2_1_46_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_47_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_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"e_1_3_2_1_49_1","volume-title":"Making a ''completely blind'' image quality analyzer","author":"Mittal Anish","year":"2012","unstructured":"Anish Mittal, Rajiv Soundararajan, and Alan C Bovik. 2012b. Making a ''completely blind'' image quality analyzer. IEEE Signal processing letters, Vol. 20, 3 (2012), 209-212."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","unstructured":"Alejandro Newell Kaiyu Yang and Jia Deng. 2016. Stacked Hourglass Networks for Human Pose Estimation. arXiv:1603.06937 [cs.CV] https:\/\/arxiv.org\/abs\/1603.06937","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"e_1_3_2_1_51_1","unstructured":"OpenAI. 2024a. ChatGPT (Version 4). https:\/\/openai.com\/chatgpt"},{"key":"e_1_3_2_1_52_1","unstructured":"OpenAI. 2024b. Sora. https:\/\/sora.com\/"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3127905"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"crossref","unstructured":"Nikolay Ponomarenko Lina Jin Oleg Ieremeiev Vladimir Lukin Karen Egiazarian Jaakko Astola Benoit Vozel Kacem Chehdi Marco Carli Federica Battisti et al. 2015. Image database TID2013: Peculiarities results and perspectives. Signal processing: Image communication Vol. 30 (2015) 57-77.","DOI":"10.1016\/j.image.2014.10.009"},{"key":"e_1_3_2_1_55_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_56_1","volume-title":"Self-attention with relative position representations. arXiv preprint arXiv:1803.02155","author":"Shaw Peter","year":"2018","unstructured":"Peter Shaw, Jakob Uszkoreit, and Ashish Vaswani. 2018. Self-attention with relative position representations. arXiv preprint arXiv:1803.02155 (2018)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"e_1_3_2_1_58_1","unstructured":"Rui Sun Yumin Zhang Tejal Shah Jiaohao Sun Shuoying Zhang Wenqi Li Haoran Duan and Bo Wei. [n.d.]. From Sora What We Can See: A Survey of Text-to-Video Generation. ([n.d.])."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548329"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2023.3270621"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3385364"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00986"},{"key":"e_1_3_2_1_63_1","unstructured":"Kuaishou Technology. 2024. Kling. https:\/\/klingai.kuaishou.com\/"},{"key":"e_1_3_2_1_64_1","volume-title":"Raft: Recurrent all-pairs field transforms for optical flow. In Computer Vision-ECCV 2020: 16th European Conference","author":"Teed Zachary","year":"2020","unstructured":"Zachary Teed and Jia Deng. 2020. Raft: Recurrent all-pairs field transforms for optical flow. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part II 16. Springer, 402-419."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072221"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2021.3090333"},{"key":"e_1_3_2_1_67_1","unstructured":"Thomas Unterthiner Sjoerd van Steenkiste Karol Kurach Raphael Marinier Marcin Michalski and Sylvain Gelly. 2018. Towards Accurate Generative Models of Video: A New Metric Challenges. arXiv:1812.01717 [cs.CV]"},{"key":"e_1_3_2_1_68_1","volume-title":"International Conference on Learning Representations.","author":"Villegas Ruben","year":"2022","unstructured":"Ruben Villegas, Mohammad Babaeizadeh, Pieter-Jan Kindermans, Hernan Moraldo, Han Zhang, Mohammad Taghi Saffar, Santiago Castro, Julius Kunze, and Dumitru Erhan. 2022. Phenaki: Variable length video generation from open domain textual descriptions. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"e_1_3_2_1_71_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 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_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681471"},{"key":"e_1_3_2_1_73_1","volume-title":"A strong baseline for image and video quality assessment. arXiv preprint arXiv:2111.07104","author":"Wen Shaoguo","year":"2021","unstructured":"Shaoguo Wen and Junle Wang. 2021. A strong baseline for image and video quality assessment. arXiv preprint arXiv:2111.07104 (2021)."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"e_1_3_2_1_76_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_77_1","unstructured":"Zhiyu Wu Xiaokang Chen Zizheng Pan Xingchao Liu Wen Liu Damai Dai Huazuo Gao Yiyang Ma Chengyue Wu Bingxuan Wang Zhenda Xie Yu Wu Kai Hu Jiawei Wang Yaofeng Sun Yukun Li Yishi Piao Kang Guan Aixin Liu Xin Xie Yuxiang You Kai Dong Xingkai Yu Haowei Zhang Liang Zhao Yisong Wang and Chong Ruan. 2024. DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding. arXiv:2412.10302 [cs.CV] https:\/\/arxiv.org\/abs\/2412.10302"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00296"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01380"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00363"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00782"},{"key":"e_1_3_2_1_82_1","volume-title":"MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators. arXiv preprint arXiv:2404.05014","author":"Yuan Shenghai","year":"2024","unstructured":"Shenghai Yuan, Jinfa Huang, Yujun Shi, Yongqi Xu, Ruijie Zhu, Bin Lin, Xinhua Cheng, Li Yuan, and Jiebo Luo. 2024. MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators. arXiv preprint arXiv:2404.05014 (2024)."},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413560"},{"key":"e_1_3_2_1_84_1","volume-title":"Make pixels dance: High-dynamic video generation. arXiv preprint arXiv:2311.10982","author":"Zeng Yan","year":"2023","unstructured":"Yan Zeng, Guoqiang Wei, Jiani Zheng, Jiaxin Zou, Yang Wei, Yuchen Zhang, and Hang Li. 2023. Make pixels dance: High-dynamic video generation. arXiv preprint arXiv:2311.10982 (2023)."},{"key":"e_1_3_2_1_85_1","volume-title":"Jia-Wei Liu, Rui Zhao, Lingmin Ran, Yuchao Gu, Difei Gao, and Mike Zheng Shou.","author":"Zhang David Junhao","year":"2023","unstructured":"David Junhao Zhang, Jay Zhangjie Wu, Jia-Wei Liu, Rui Zhao, Lingmin Ran, Yuchao Gu, Difei Gao, and Mike Zheng Shou. 2023a. Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation. arXiv preprint arXiv:2309.15818 (2023)."},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3061932"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"},{"key":"e_1_3_2_1_88_1","unstructured":"Zhichao Zhang Xinyue Li Wei Sun Jun Jia Xiongkuo Min Zicheng Zhang Chunyi Li Zijian Chen Puyi Wang Zhongpeng Ji et al. 2024. Benchmarking AIGC Video Quality Assessment: A Dataset and Unified Model. arXiv preprint arXiv:2407.21408 (2024)."}],"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\/3746027.3754731","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:05:51Z","timestamp":1765339551000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754731"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":88,"alternative-id":["10.1145\/3746027.3754731","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754731","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"}}]}}