{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T10:21:55Z","timestamp":1793701315745,"version":"4.5.1"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755259","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:38Z","timestamp":1761377198000},"page":"6654-6662","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["ArtFRD: A Fisher-Rao Mixture Metric for Generative Model Aesthetic Evaluation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6133-2073","authenticated-orcid":false,"given":"Chuanwei","family":"Huang","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5044-9987","authenticated-orcid":false,"given":"Zexi","family":"Jia","sequence":"additional","affiliation":[{"name":"WeChat AI, Tencent Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9820-9472","authenticated-orcid":false,"given":"Hongyan","family":"Fei","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7918-2962","authenticated-orcid":false,"given":"Yeshuang","family":"Zhu","sequence":"additional","affiliation":[{"name":"WeChat AI, Tencent Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2150-4067","authenticated-orcid":false,"given":"Zhiqiang","family":"Yuan","sequence":"additional","affiliation":[{"name":"WeChat AI, Tencent Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4611-9675","authenticated-orcid":false,"given":"Jinchao","family":"Zhang","sequence":"additional","affiliation":[{"name":"WeChat AI, Tencent Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5899-5165","authenticated-orcid":false,"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"WeChat AI, Tencent Inc., Beijing, 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":"Information geometry and its applications","unstructured":"Shun-ichi Amari. 2016. Information geometry and its applications. Vol. 194. Springer."},{"key":"e_1_3_2_1_2_1","volume-title":"Methods of information geometry","author":"Hiroshi Nagaoka Amari","unstructured":"Shun-ichi Amari and Hiroshi Nagaoka. 2000. Methods of information geometry. Vol. 191. American Mathematical Soc."},{"key":"e_1_3_2_1_3_1","volume-title":"A note on the inception score. arXiv preprint arXiv:1801.01973","author":"Barratt Shane","year":"2018","unstructured":"Shane Barratt and Rishi Sharma. 2018. A note on the inception score. arXiv preprint arXiv:1801.01973 (2018)."},{"key":"e_1_3_2_1_4_1","volume-title":"Demystifying mmd gans. arXiv preprint arXiv:1801.01401","author":"Bi\u0144kowski Miko\u0142aj","year":"2018","unstructured":"Miko\u0142aj Bi\u0144kowski, Danica J Sutherland, Michael Arbel, and Arthur Gretton. 2018. Demystifying mmd gans. arXiv preprint arXiv:1801.01401 (2018)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Jacob Burbea. 1984. Informative geometry of probability spaces. (1984).","DOI":"10.21236\/ADA150510"},{"key":"e_1_3_2_1_6_1","volume-title":"Geometric modeling in probability and statistics","author":"Calin Ovidiu","unstructured":"Ovidiu Calin and Constantin Udri\u015fte. 2014. Geometric modeling in probability and statistics. Vol. 121. Springer."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3475799"},{"key":"e_1_3_2_1_8_1","volume-title":"Pixart-alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis. arXiv preprint arXiv:2310.00426","author":"Chen Junsong","year":"2023","unstructured":"Junsong Chen, Jincheng Yu, Chongjian Ge, Lewei Yao, Enze Xie, Yue Wu, Zhongdao Wang, James Kwok, Ping Luo, Huchuan Lu, et al. 2023. Pixart-alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis. arXiv preprint arXiv:2310.00426 (2023)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00611"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1977.tb01600.x"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2696576"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/0047-259X(82)90077-X"},{"key":"e_1_3_2_1_13_1","volume-title":"Fortyfirst international conference on machine learning.","author":"Esser Patrick","year":"2024","unstructured":"Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas M\u00fcller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, et al. 2024. Scaling rectified flow transformers for high-resolution image synthesis. In Fortyfirst international conference on machine learning."},{"key":"e_1_3_2_1_14_1","first-page":"185","article-title":"The role of artificial intelligence and machine learning in preserving cultural heritage and artworks via virtual restoration. ISPRS Annals of the Photogrammetry","volume":"10","author":"Gaber Jomana Ahmed","year":"2023","unstructured":"Jomana Ahmed Gaber, Sherin Moustafa Youssef, and Karma Mohamed Fathalla. 2023. The role of artificial intelligence and machine learning in preserving cultural heritage and artworks via virtual restoration. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 10 (2023), 185-190.","journal-title":"Remote Sensing and Spatial Information Sciences"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00404"},{"key":"e_1_3_2_1_16_1","volume-title":"Generative adversarial nets. Advances in neural information processing systems 27","author":"Goodfellow Ian J","year":"2014","unstructured":"Ian J Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, DavidWarde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_2_1_17_1","volume-title":"A kernel method for the two-sample-problem. Advances in neural information processing systems 19","author":"Gretton Arthur","year":"2006","unstructured":"Arthur Gretton, Karsten Borgwardt, Malte Rasch, Bernhard Sch\u00f6lkopf, and Alex Smola. 2006. A kernel method for the two-sample-problem. Advances in neural information processing systems 19 (2006)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/2503308.2188410"},{"key":"e_1_3_2_1_19_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30","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 30 (2017)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888100"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00889"},{"key":"e_1_3_2_1_22_1","volume-title":"A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets. arXiv preprint arXiv:2507.04699","author":"Jia Zexi","year":"2025","unstructured":"Zexi Jia, Chuanwei Huang, Hongyan Fei, Yeshuang Zhu, Zhiqiang Yuan, Ying Deng, Jiapei Zhang, Jinchao Zhang, and Jie Zhou. 2025. A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets. arXiv preprint arXiv:2507.04699 (2025)."},{"key":"e_1_3_2_1_23_1","volume-title":"Control-CLIP: Decoupling Category and Style Guidance in CLIP for Specific-Domain Generation. arXiv preprint arXiv:2502.11532","author":"Jia Zexi","year":"2025","unstructured":"Zexi Jia, Chuanwei Huang, Hongyan Fei, Yeshuang Zhu, Zhiqiang Yuan, Jinchao Zhang, and Jie Zhou. 2025. Control-CLIP: Decoupling Category and Style Guidance in CLIP for Specific-Domain Generation. arXiv preprint arXiv:2502.11532 (2025)."},{"key":"e_1_3_2_1_24_1","volume-title":"From Imitation to Innovation: The Emergence of AI Unique Artistic Styles and the Challenge of Copyright Protection. arXiv preprint arXiv:2507.04769","author":"Jia Zexi","year":"2025","unstructured":"Zexi Jia, Chuanwei Huang, Yeshuang Zhu, Hongyan Fei, Ying Deng, Zhiqiang Yuan, Jiapei Zhang, Jinchao Zhang, and Jie Zhou. 2025. From Imitation to Innovation: The Emergence of AI Unique Artistic Styles and the Challenge of Copyright Protection. arXiv preprint arXiv:2507.04769 (2025)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00968"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_40"},{"key":"e_1_3_2_1_28_1","unstructured":"Black Forest Labs. 2024. FLUX. https:\/\/github.com\/black-forest-labs\/flux."},{"key":"e_1_3_2_1_29_1","volume-title":"Transforming Information Into Knowledge: How Computational Methods Reshape Art History. DHQ: Digital Humanities Quarterly 15, 3","author":"Lang Sabine","year":"2021","unstructured":"Sabine Lang and Bj\u00f6rn Ommer. 2021. Transforming Information Into Knowledge: How Computational Methods Reshape Art History. DHQ: Digital Humanities Quarterly 15, 3 (2021)."},{"key":"e_1_3_2_1_30_1","volume-title":"Playground v2. 5: Three insights towards enhancing aesthetic quality in text-to-image generation. arXiv preprint arXiv:2402.17245","author":"Li Daiqing","year":"2024","unstructured":"Daiqing Li, Aleks Kamko, Ehsan Akhgari, Ali Sabet, Linmiao Xu, and Suhail Doshi. 2024. Playground v2. 5: Three insights towards enhancing aesthetic quality in text-to-image generation. arXiv preprint arXiv:2402.17245 (2024)."},{"key":"e_1_3_2_1_31_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_32_1","volume-title":"2011 international conference on computer vision. IEEE, 2206-2213","author":"Luo Wei","year":"2011","unstructured":"Wei Luo, Xiaogang Wang, and Xiaoou Tang. 2011. Content-based photo quality assessment. In 2011 international conference on computer vision. IEEE, 2206-2213."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.2307\/1403358"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41884-024-00143-2"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"e_1_3_2_1_36_1","series-title":"Series A","volume-title":"Rao's distance for negative multinomial distributions. Sankhy\u00afa: The Indian Journal of Statistics","author":"Cuadras Oller","year":"1985","unstructured":"JoseMOller and CarlesMCuadras. 1985. Rao's distance for negative multinomial distributions. Sankhy\u00afa: The Indian Journal of Statistics, Series A (1985), 75-83."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01112"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.1894.0003"},{"key":"e_1_3_2_1_39_1","volume-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952","author":"Podell Dustin","year":"2023","unstructured":"Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M\u00fcller, Joe Penna, and Robin Rombach. 2023. Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)."},{"key":"e_1_3_2_1_40_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_41_1","first-page":"1867","article-title":"Uber die Hypothesen, welche der Geometrie zu Grunde liegen","volume":"13","author":"Riemann Bernhard","year":"1854","unstructured":"Bernhard Riemann. 1854. Uber die Hypothesen, welche der Geometrie zu Grunde liegen. K\u00f6nigliche Gesellschaft der Wissenschaften und der Georg-Augustus- Universit\u00e4t G\u00f6ttingen 13, 133 (1854), 1867.","journal-title":"K\u00f6nigliche Gesellschaft der Wissenschaften und der Georg-Augustus- Universit\u00e4t G\u00f6ttingen"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_43_1","volume-title":"Improved techniques for training gans. Advances in neural information processing systems 29","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 29 (2016)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Charles Spearman. 1961. The proof and measurement of association between two things. (1961).","DOI":"10.1037\/11491-005"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIS46139.2019.8940355"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02144"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"}],"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\/3746027.3755259","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:48:50Z","timestamp":1765309730000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755259"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":48,"alternative-id":["10.1145\/3746027.3755259","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755259","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"}}]}}