{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T09:37:37Z","timestamp":1782812257883,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","funder":[{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["Grant 2023A1515030087"],"award-info":[{"award-number":["Grant 2023A1515030087"]}]},{"name":"Open Project Program of Guangxi Key Laboratory of Digital Infrastructure","award":["No. GXDIOP2024015"],"award-info":[{"award-number":["No. GXDIOP2024015"]}]},{"name":"Key Laboratory of Computing Power Network and Information Security, Ministry of Education","award":["No. 2023ZD011"],"award-info":[{"award-number":["No. 2023ZD011"]}]},{"name":"Guangdong Provincial Key Laboratory of Information Security Technology","award":["No. 2023B1212060026"],"award-info":[{"award-number":["No. 2023B1212060026"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["Grant W2512008, Grant 62272498"],"award-info":[{"award-number":["Grant W2512008, Grant 62272498"]}],"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\/3746027.3755251","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:38Z","timestamp":1761377198000},"page":"11434-11442","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Towards Culturally Fair Multimodal Generation: Quantifying and Mitigating Orientalist Biases in Text-to-Visual Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9936-8669","authenticated-orcid":false,"given":"Yifan","family":"Zeng","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7926-1663","authenticated-orcid":false,"given":"Fangzhou","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0764-5802","authenticated-orcid":false,"given":"Jian","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0979-8613","authenticated-orcid":false,"given":"Peijia","family":"Zheng","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Information Technology, Sun Yat-sen Univsersity, Guangzhou, Guangdong, China and Guangdong Province Key Laboratory of Information Security Technology, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5182-2798","authenticated-orcid":false,"given":"Jian","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Qilu University of Technology (Shandong Academy of Sciences), Jinan, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7715-8346","authenticated-orcid":false,"given":"Huiyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Guangxi Key Laboratory of Digital Infrastructure, Guangxi Zhuang Autonomous Region Information Center, Nanning, Guangxi, 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":"Modernity at Large: Cultural Dimensions of Globalization","author":"Appadurai Arjun","unstructured":"Arjun Appadurai. 1996. Modernity at Large: Cultural Dimensions of Globalization. University of Minnesota Press, Minneapolis."},{"key":"e_1_3_2_1_2_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et al. 2025. Qwen2.5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"e_1_3_2_1_4_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_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"e_1_3_2_1_6_1","unstructured":"James Betker Gabriel Goh Li Jing Tim Brooks Jianfeng Wang Linjie Li Long Ouyang Juntang Zhuang Joyce Lee Yufei Guo et al. 2023. Improving image generation with better captions. https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf (2023)."},{"key":"e_1_3_2_1_7_1","volume-title":"ICML 2024 Workshop on Foundation Models in the Wild.","author":"Chen Zhaorun","unstructured":"Zhaorun Chen, Yichao Du, Zichen Wen, Yiyang Zhou, Chenhang Cui, Zhenzhen Weng, Haoqin Tu, Chaoqi Wang, Zhengwei Tong, Leria HUANG, et al., [n.d.]. MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge?. In ICML 2024 Workshop on Foundation Models in the Wild."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00283"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"James Clifford. 1980. Orientalism.","DOI":"10.2307\/2504800"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 12225-12235","author":"D'Inc\u00e0 Marco","unstructured":"Marco D'Inc\u00e0, Emanuele Peruzzo, Marco Mancini, and et al., 2024. OpenBias: Open-set Bias Detection in Text-to-Image Generative Models. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 12225-12235."},{"key":"e_1_3_2_1_11_1","volume-title":"Translated by Richard Philcox","author":"Fanon Frantz","year":"2008","unstructured":"Frantz Fanon. 1952. Black Skin, White Masks. \u00c9ditions du Seuil, Paris. Translated by Richard Philcox (2008), Grove Press."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/MTS.2021.3056293"},{"key":"e_1_3_2_1_13_1","volume-title":"The order of things","author":"Foucault Michel","unstructured":"Michel Foucault. 2005. The order of things. Routledge."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1080\/15358590500296997"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society","volume":"7","author":"Sourojit","unstructured":"Sourojit Ghosh et al., 2024. Do Generative AI Models Output Harm while Representing Non-Western Cultures: Evidence from A Community-Centered Approach. In Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society, Vol. 7."},{"key":"e_1_3_2_1_16_1","unstructured":"Google. 2025. Gemini 2.5 Pro. https:\/\/deepmind.google\/models\/gemini\/. Accessed: 2025-07-07."},{"key":"e_1_3_2_1_17_1","volume-title":"Prison notebooks","author":"Gramsci Antonio","unstructured":"Antonio Gramsci. 2011. Prison notebooks. Vol. 2. Columbia University Press."},{"key":"e_1_3_2_1_18_1","volume-title":"Towards Geographic Inclusion in the Evaluation of Text-to-Image Models. In The 2024 ACM Conference on Fairness, Accountability, and Transparency. 585-601","author":"Hall Melissa","year":"2024","unstructured":"Melissa Hall, Samuel J Bell, Candace Ross, Adina Williams, Michal Drozdzal, and Adriana Romero Soriano. 2024. Towards Geographic Inclusion in the Evaluation of Text-to-Image Models. In The 2024 ACM Conference on Fairness, Accountability, and Transparency. 585-601."},{"key":"e_1_3_2_1_19_1","volume-title":"Lectures on the Philosophy of History. Duncker und Humblot","author":"Friedrich Hegel Georg Wilhelm","year":"1956","unstructured":"Georg Wilhelm Friedrich Hegel. 1837. Lectures on the Philosophy of History. Duncker und Humblot, Berlin. Translated by J. Sibree (1956), Dover Publications."},{"key":"e_1_3_2_1_20_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_21_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Andreas Mayr, 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","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840-6851."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00836"},{"key":"e_1_3_2_1_24_1","volume-title":"KLING AI: Next-generation AI creative studio. https:\/\/klingai.com\/.","author":"KLING","year":"2024","unstructured":"KLING AI. 2024. KLING AI: Next-generation AI creative studio. https:\/\/klingai.com\/."},{"key":"e_1_3_2_1_25_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_26_1","volume-title":"The question of Orientalism. Orientalism: A reader","author":"Lewis Bernard","year":"2000","unstructured":"Bernard Lewis. 2000. The question of Orientalism. Orientalism: A reader, Vol. 25 (2000)."},{"key":"e_1_3_2_1_27_1","volume-title":"Benchmark, Evaluations and Challenges. arXiv preprint arXiv:2501.02189","author":"Li Zongxia","year":"2025","unstructured":"Zongxia Li, Xiyang Wu, Hongyang Du, Huy Nghiem, and Guangyao Shi. 2025. A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges. arXiv preprint arXiv:2501.02189 (2025)."},{"key":"e_1_3_2_1_28_1","unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et al. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437 (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"A survey on bias and fairness in machine learning. ACM computing surveys (CSUR)","author":"Mehrabi Ninareh","year":"2021","unstructured":"Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, and Aram Galstyan. 2021. A survey on bias and fairness in machine learning. ACM computing surveys (CSUR), Vol. 54, 6 (2021), 1-35."},{"key":"e_1_3_2_1_30_1","unstructured":"Midjourney. 2024. Midjourney. https:\/\/www.midjourney. com."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"e_1_3_2_1_32_1","article-title":"Reading Orientalism: A Postcolonial Perspective","volume":"2","author":"Nagar Neha","year":"2013","unstructured":"Neha Nagar. 2013. Reading Orientalism: A Postcolonial Perspective. Galaxy: International Multidisciplinary Research Journal, Vol. 2, 5 (2013).","journal-title":"Galaxy: International Multidisciplinary Research Journal"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600211.3604711"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_35_1","unstructured":"Edward W. Said. 1978. Orientalism. Pantheon Books New York."},{"key":"e_1_3_2_1_36_1","volume-title":"Towards a standard for identifying and managing bias in artificial intelligence","author":"Schwartz Reva","unstructured":"Reva Schwartz, Reva Schwartz, Apostol Vassilev, Kristen Greene, Lori Perine, Andrew Burt, and Patrick Hall. 2022. Towards a standard for identifying and managing bias in artificial intelligence. Vol. 3. US Department of Commerce, National Institute of Standards and Technology."},{"key":"e_1_3_2_1_37_1","volume-title":"Postcolonial criticism","author":"Spivak Gayatri C","unstructured":"Gayatri C Spivak. 2014. Three women's texts and a critique of imperialism. In Postcolonial criticism. Routledge, 145-165."},{"key":"e_1_3_2_1_38_1","first-page":"29489","article-title":"Videotetris: Towards compositional text-to-video generation","volume":"37","author":"Tian Ye","year":"2024","unstructured":"Ye Tian, Ling Yang, Haotian Yang, Yuan Gao, Yufan Deng, Xintao Wang, Zhaochen Yu, Xin Tao, Pengfei Wan, Di ZHANG, et al., 2024. Videotetris: Towards compositional text-to-video generation. Advances in Neural Information Processing Systems, Vol. 37 (2024), 29489-29513.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_39_1","volume-title":"Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation. arXiv preprint arXiv:2404.01030","author":"Wan Yixin","year":"2024","unstructured":"Yixin Wan, Arjun Subramonian, Anaelia Ovalle, Zongyu Lin, Ashima Suvarna, Christina Chance, Hritik Bansal, Rebecca Pattichis, and Kai-Wei Chang. 2024. Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation. arXiv preprint arXiv:2404.01030 (2024)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1353\/nlh.1997.0013"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681433"},{"key":"e_1_3_2_1_42_1","volume-title":"Words: Understanding and Mitigating Bias in Vision-Language Model from a Causal Mediation Perspective. arXiv preprint arXiv:2407.02814","author":"Weng Z","year":"2024","unstructured":"Z Weng, Z Gao, J Andrews, and et al., 2024. Images Speak Louder than Words: Understanding and Mitigating Bias in Vision-Language Model from a Causal Mediation Perspective. arXiv preprint arXiv:2407.02814 (2024)."},{"key":"e_1_3_2_1_43_1","unstructured":"Alan Wheeler. 2024. Orientalism in Ancient Literature and its Transmission into Modern Popular Culture. (2024)."},{"key":"e_1_3_2_1_44_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Xu Jiazheng","year":"2024","unstructured":"Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, and Yuxiao Dong. 2024. Imagereward: Learning and evaluating human preferences for text-to-image generation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3554729"},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings of the Annual Meeting of the Cognitive Science Society","volume":"47","author":"Zeng Yifan","year":"2025","unstructured":"Yifan Zeng, Liang Kairong, Fangzhou Dong, and Peijia Zheng. 2025. Quantifying Risk Propensities of Large Language Models: Ethical Focus and Bias Detection through Role-Play. In Proceedings of the Annual Meeting of the Cognitive Science Society, Vol. 47. https:\/\/escholarship.org\/uc\/item\/97c1h4j6"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642877"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00766"}],"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\/3746027.3755251","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:48:07Z","timestamp":1765309687000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755251"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":48,"alternative-id":["10.1145\/3746027.3755251","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755251","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"}}]}}