{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:26:25Z","timestamp":1780673185036,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":90,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271312,62132006"],"award-info":[{"award-number":["62271312,62132006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["22DZ2229005"],"award-info":[{"award-number":["22DZ2229005"]}],"id":[{"id":"10.13039\/501100003399","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\/3746027.3755700","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"8825-8834","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["LMME3DHF: Benchmarking and Evaluating Multimodal 3D Human Face Generation with LMMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1171-2929","authenticated-orcid":false,"given":"Woo Yi","family":"Yang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9890-2698","authenticated-orcid":false,"given":"Jiarui","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7753-1596","authenticated-orcid":false,"given":"Sijing","family":"Wu","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\/0009-0006-0542-578X","authenticated-orcid":false,"given":"Yuxin","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1300-7401","authenticated-orcid":false,"given":"Liu","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6916-5821","authenticated-orcid":false,"given":"Kang","family":"Fu","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"}]},{"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"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 20950-20959","author":"An Sizhe","year":"2023","unstructured":"Sizhe An, Hongyi Xu, Yichun Shi, Guoxian Song, Umit Y Ogras, and Linjie Luo. 2023. Panohead: Geometry-aware 3d full-head synthesis in 360deg. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 20950-20959."},{"key":"e_1_3_2_1_2_1","volume-title":"Saliency based on information maximization. Advances in neural information processing systems","author":"Bruce Neil","year":"2005","unstructured":"Neil Bruce and John Tsotsos. 2005. Saliency based on information maximization. Advances in neural information processing systems, Vol. 18 (2005)."},{"key":"e_1_3_2_1_3_1","volume-title":"Predicting human gaze using low-level saliency combined with face detection. Advances in neural information processing systems","author":"Cerf Moran","year":"2007","unstructured":"Moran Cerf, Jonathan Harel, Wolfgang Einh\u00e4user, and Christof Koch. 2007. Predicting human gaze using low-level saliency combined with face detection. Advances in neural information processing systems, Vol. 20 (2007)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2945857"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1267"},{"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. 2024b. 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","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00680"},{"key":"e_1_3_2_1_11_1","volume-title":"European Conference on Computer Vision. Springer, 316-333","author":"Deng Yu","year":"2024","unstructured":"Yu Deng, Duomin Wang, and Baoyuan Wang. 2024a. Portrait4d-v2: Pseudo multi-view data creates better 4d head synthesizer. In European Conference on Computer Vision. Springer, 316-333."},{"key":"e_1_3_2_1_12_1","volume-title":"Diffusion models beat gans on image synthesis. Advances in neural information processing systems","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in neural information processing systems, Vol. 34 (2021), 8780-8794."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00305"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995676"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1167\/13.4.11"},{"key":"e_1_3_2_1_16_1","volume-title":"Context-aware saliency detection","author":"Goferman Stas","year":"2011","unstructured":"Stas Goferman, Lihi Zelnik-Manor, and Ayellet Tal. 2011. Context-aware saliency detection. IEEE transactions on pattern analysis and machine intelligence, Vol. 34, 10 (2011), 1915-1926."},{"key":"e_1_3_2_1_17_1","volume-title":"2008 IEEE conference on computer vision and pattern recognition. IEEE, 1-8.","author":"Guo Chenlei","year":"2008","unstructured":"Chenlei Guo, Qi Ma, and Liming Zhang. 2008. Spatio-temporal saliency detection using phase spectrum of quaternion fourier transform. In 2008 IEEE conference on computer vision and pattern recognition. IEEE, 1-8."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.143.1.7063747"},{"key":"e_1_3_2_1_19_1","volume-title":"Graph-based visual saliency. Advances in neural information processing systems","author":"Harel Jonathan","year":"2006","unstructured":"Jonathan Harel, Christof Koch, and Pietro Perona. 2006. Graph-based visual saliency. Advances in neural information processing systems, Vol. 19 (2006)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_21_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems","author":"Heusel Martin","year":"2017","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. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383267"},{"key":"e_1_3_2_1_23_1","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2022. Lora: Low-rank adaptation of large language models. ICLR, Vol. 1, 2 (2022), 3.","journal-title":"ICLR"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00437"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.38"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00589"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3527850"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.224"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/30.1-2.81"},{"key":"e_1_3_2_1_33_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_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680868"},{"key":"e_1_3_2_1_35_1","volume-title":"On information and sufficiency. The annals of mathematical statistics","author":"Kullback Solomon","year":"1951","unstructured":"Solomon Kullback and Richard A Leibler. 1951. On information and sufficiency. The annals of mathematical statistics, Vol. 22, 1 (1951), 79-86."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3164467"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3319020"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351028"},{"key":"e_1_3_2_1_39_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. 2024. 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_40_1","volume-title":"Visual saliency based on scale-space analysis in the frequency domain","author":"Li Jian","year":"2012","unstructured":"Jian Li, Martin D Levine, Xiangjing An, Xin Xu, and Hangen He. 2012. Visual saliency based on scale-space analysis in the frequency domain. IEEE transactions on pattern analysis and machine intelligence, Vol. 35, 4 (2012), 996-1010."},{"key":"e_1_3_2_1_41_1","volume-title":"Videochat: Chat-centric video understanding. arXiv preprint arXiv:2305.06355","author":"Li KunChang","year":"2023","unstructured":"KunChang Li, Yinan He, Yi Wang, Yizhuo Li, Wenhai Wang, Ping Luo, Yali Wang, Limin Wang, and Yu Qiao. 2023a. Videochat: Chat-centric video understanding. arXiv preprint arXiv:2305.06355 (2023)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01835"},{"key":"e_1_3_2_1_43_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_44_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_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02090"},{"key":"e_1_3_2_1_46_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_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.080"},{"key":"e_1_3_2_1_50_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_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2788206"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2018.2816783"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2902097"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"e_1_3_2_1_55_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_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995506"},{"key":"e_1_3_2_1_57_1","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 13503-13513","author":"Or-El Roy","year":"2022","unstructured":"Roy Or-El, Xuan Luo, Mengyi Shan, Eli Shechtman, Jeong Joon Park, and Ira Kemelmacher-Shlizerman. 2022. Stylesdf: High-resolution 3d-consistent image and geometry generation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 13503-13513."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"crossref","unstructured":"Karl Pearson. 1896. VII. Mathematical contributions to the theory of evolution.-III. Regression heredity and panmixia. Philosophical Transactions of the Royal Society of London. Series A containing papers of a mathematical or physical character 187 ( 1896) 253-318.","DOI":"10.1098\/rsta.1896.0007"},{"key":"e_1_3_2_1_59_1","volume-title":"Components of bottom-up gaze allocation in natural images. Vision research","author":"Peters Robert J","year":"2005","unstructured":"Robert J Peters, Asha Iyer, Laurent Itti, and Christof Koch. 2005. Components of bottom-up gaze allocation in natural images. Vision research, Vol. 45, 18 (2005), 2397-2416."},{"key":"e_1_3_2_1_60_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_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_62_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_63_1","first-page":"33999","article-title":"Voxgraf: Fast 3d-aware image synthesis with sparse voxel grids","volume":"35","author":"Schwarz Katja","year":"2022","unstructured":"Katja Schwarz, Axel Sauer, Michael Niemeyer, Yiyi Liao, and Andreas Geiger. 2022. Voxgraf: Fast 3d-aware image synthesis with sparse voxel grids. Advances in Neural Information Processing Systems, Vol. 35 (2022), 33999-34011.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_64_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_65_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_66_1","first-page":"24487","article-title":"Epigraf: Rethinking training of 3d gans","volume":"35","author":"Skorokhodov Ivan","year":"2022","unstructured":"Ivan Skorokhodov, Sergey Tulyakov, Yiqun Wang, and Peter Wonka. 2022. Epigraf: Rethinking training of 3d gans. Advances in Neural Information Processing Systems, Vol. 35 (2022), 24487-24501.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.2307\/1412159"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00502"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02011"},{"key":"e_1_3_2_1_71_1","first-page":"16331","article-title":"Controllable 3d face synthesis with conditional generative occupancy fields","volume":"35","author":"Sun Keqiang","year":"2022","unstructured":"Keqiang Sun, Shangzhe Wu, Zhaoyang Huang, Ning Zhang, Quan Wang, and HongSheng Li. 2022b. Controllable 3d face synthesis with conditional generative occupancy fields. Advances in Neural Information Processing Systems, Vol. 35 (2022), 16331-16343.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548329"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2023.3270621"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00130487"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"e_1_3_2_1_76_1","volume-title":"CAAI International Conference on Artificial Intelligence. Springer, 46-57","author":"Wang Jiarui","year":"2023","unstructured":"Jiarui Wang, Huiyu Duan, Jing Liu, Shi Chen, Xiongkuo Min, and Guangtao Zhai. 2023. Aigciqa2023: A large-scale image quality assessment database for ai generated images: from the perspectives of quality, authenticity and correspondence. In CAAI International Conference on Artificial Intelligence. Springer, 46-57."},{"key":"e_1_3_2_1_77_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 2024. 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_78_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"e_1_3_2_1_80_1","volume-title":"Better aligning text-to-image models with human preference. arXiv preprint arXiv:2303.14420","author":"Wu Xiaoshi","year":"2023","unstructured":"Xiaoshi Wu, Keqiang Sun, Feng Zhu, Rui Zhao, and Hongsheng Li. 2023a. Better aligning text-to-image models with human preference. arXiv preprint arXiv:2303.14420, Vol. 1, 3 (2023)."},{"key":"e_1_3_2_1_81_1","first-page":"36188","article-title":"Anifacegan: Animatable 3d-aware face image generation for video avatars","volume":"35","author":"Wu Yue","year":"2022","unstructured":"Yue Wu, Yu Deng, Jiaolong Yang, Fangyun Wei, Qifeng Chen, and Xin Tong. 2022b. Anifacegan: Animatable 3d-aware face image generation for video avatars. Advances in Neural Information Processing Systems, Vol. 35 (2022), 36188-36201.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618164"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2585880"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.133"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647885"},{"key":"e_1_3_2_1_86_1","volume-title":"Minicpm-v: A gpt-4v level mllm on your phone. arXiv preprint arXiv:2408.01800","author":"Yao Yuan","year":"2024","unstructured":"Yuan Yao, Tianyu Yu, Ao Zhang, Chongyi Wang, Junbo Cui, Hongji Zhu, Tianchi Cai, Haoyu Li, Weilin Zhao, Zhihui He, et al., 2024. Minicpm-v: A gpt-4v level mllm on your phone. arXiv preprint arXiv:2408.01800 (2024)."},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-019-2757-1"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1167\/8.7.32"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01790"},{"key":"e_1_3_2_1_90_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\/3746027.3755700","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:36:59Z","timestamp":1765309019000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755700"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":90,"alternative-id":["10.1145\/3746027.3755700","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755700","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"}}]}}