{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:10:12Z","timestamp":1765339812026,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476134"],"award-info":[{"award-number":["62476134"]}],"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\/3746027.3755280","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:51Z","timestamp":1761377211000},"page":"9978-9986","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MPPR: Memory-Prior-based Prompt Refinement in Continuous Space for Advanced Text-to-Image Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9558-4917","authenticated-orcid":false,"given":"Zhibing","family":"Zhang","sequence":"first","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5705-2299","authenticated-orcid":false,"given":"Jiantao","family":"Lin","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0528-8202","authenticated-orcid":false,"given":"Cangqi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0621-1058","authenticated-orcid":false,"given":"Rui","family":"Xia","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"volume-title":"Chatgpt stable diffusion prompts generator. https:\/\/gist.github.com\/bluelovers\/92dac6fe7dcbafd7b5ae0557e638e6ef Retrieved","year":"2024","key":"e_1_3_2_1_1_1","unstructured":"Bluelovers. 2023. Chatgpt stable diffusion prompts generator. https:\/\/gist.github.com\/bluelovers\/92dac6fe7dcbafd7b5ae0557e638e6ef Retrieved September 9, 2024 from"},{"key":"e_1_3_2_1_2_1","volume-title":"Language models are few-shot learners. arXiv preprint arXiv:2005.14165","author":"Brown Tom B","year":"2020","unstructured":"Tom B Brown. 2020. Language models are few-shot learners. arXiv preprint arXiv:2005.14165 (2020)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"e_1_3_2_1_4_1","volume-title":"What's in a text-to-image prompt? The potential of stable diffusion in visual arts education. Heliyon","author":"Dehouche Nassim","year":"2023","unstructured":"Nassim Dehouche and Kullathida Dehouche. 2023. What's in a text-to-image prompt? The potential of stable diffusion in visual arts education. Heliyon (2023)."},{"key":"e_1_3_2_1_5_1","volume-title":"Evaluating the robustness of text-to-image diffusion models against real-world attacks. arXiv preprint arXiv:2306.13103","author":"Gao Hongcheng","year":"2023","unstructured":"Hongcheng Gao, Hao Zhang, Yinpeng Dong, and Zhijie Deng. 2023. Evaluating the robustness of text-to-image diffusion models against real-world attacks. arXiv preprint arXiv:2306.13103 (2023)."},{"key":"e_1_3_2_1_6_1","volume-title":"Optimizing prompts for text-to-image generation. Advances in Neural Information Processing Systems","author":"Hao Yaru","year":"2024","unstructured":"Yaru Hao, Zewen Chi, Li Dong, and Furu Wei. 2024. Optimizing prompts for text-to-image generation. Advances in Neural Information Processing Systems (2024)."},{"key":"e_1_3_2_1_7_1","volume-title":"Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626","author":"Hertz Amir","year":"2022","unstructured":"Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, and Daniel Cohen-Or. 2022. Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)."},{"key":"e_1_3_2_1_8_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 (2020)."},{"key":"e_1_3_2_1_9_1","volume-title":"Cascaded diffusion models for high fidelity image generation. Journal of Machine Learning Research","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho, Chitwan Saharia, William Chan, David J Fleet, Mohammad Norouzi, and Tim Salimans. 2022. Cascaded diffusion models for high fidelity image generation. Journal of Machine Learning Research (2022)."},{"key":"e_1_3_2_1_10_1","volume-title":"Pick-a-pic: An open dataset of user preferences for text-to-image generation. Advances in Neural Information Processing Systems","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 (2023)."},{"key":"e_1_3_2_1_11_1","volume-title":"International conference on machine learning. PMLR.","author":"Kumar Ankit","year":"2016","unstructured":"Ankit Kumar, Ozan Irsoy, Peter Ondruska, Mohit Iyyer, James Bradbury, Ishaan Gulrajani, Victor Zhong, Romain Paulus, and Richard Socher. 2016. Ask me anything: Dynamic memory networks for natural language processing. In International conference on machine learning. PMLR."},{"key":"e_1_3_2_1_12_1","volume-title":"GenAI-Bench: A Holistic Benchmark for Compositional Text-to-Visual Generation. In 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_13_1","volume-title":"International conference on machine learning. PMLR.","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR."},{"key":"e_1_3_2_1_14_1","volume-title":"Geometry-Editable and Appearance-Preserving Object Compositon. arXiv preprint arXiv:2505.20914","author":"Lin Jianman","year":"2025","unstructured":"Jianman Lin, Haojie Li, Chunmei Qing, Zhijing Yang, Liang Lin, and Tianshui Chen. 2025. Geometry-Editable and Appearance-Preserving Object Compositon. arXiv preprint arXiv:2505.20914 (2025)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_16_1","volume-title":"prompt, and predict: A systematic survey of prompting methods in natural language processing. Comput. Surveys","author":"Liu Pengfei","year":"2023","unstructured":"Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. 2023a. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. Comput. Surveys (2023)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501825"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501825"},{"key":"e_1_3_2_1_19_1","volume-title":"GPT understands, too. AI Open","author":"Liu Xiao","year":"2023","unstructured":"Xiao Liu, Yanan Zheng, Zhengxiao Du, Ming Ding, Yujie Qian, Zhilin Yang, and Jie Tang. 2023b. GPT understands, too. AI Open (2023)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01371"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02514"},{"key":"e_1_3_2_1_22_1","volume-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741","author":"Nichol Alex","year":"2021","unstructured":"Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2021. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)."},{"key":"e_1_3_2_1_23_1","volume-title":"A taxonomy of prompt modifiers for text-to-image generation. Behaviour & Information Technology","author":"Oppenlaender Jonas","year":"2023","unstructured":"Jonas Oppenlaender. 2023. A taxonomy of prompt modifiers for text-to-image generation. Behaviour & Information Technology (2023)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592000"},{"key":"e_1_3_2_1_25_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125","author":"Ramesh Aditya","year":"2022","unstructured":"Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_28_1","volume-title":"The butterfly effect of altering prompts: How small changes and jailbreaks affect large language model performance. arXiv preprint arXiv:2401.03729","author":"Salinas Abel","year":"2024","unstructured":"Abel Salinas and Fred Morstatter. 2024. The butterfly effect of altering prompts: How small changes and jailbreaks affect large language model performance. arXiv preprint arXiv:2401.03729 (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"The role of attitudes in memory-based decision making. Journal of Personality and social Psychology","author":"Sanbonmatsu David M","year":"1990","unstructured":"David M Sanbonmatsu and Russell H Fazio. 1990. The role of attitudes in memory-based decision making. Journal of Personality and social Psychology (1990)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.3115\/991146.991190"},{"key":"e_1_3_2_1_31_1","volume-title":"Toward memory-based reasoning. Commun. ACM","author":"Stanfill Craig","year":"1986","unstructured":"Craig Stanfill and David Waltz. 1986. Toward memory-based reasoning. Commun. ACM (1986)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.486"},{"key":"e_1_3_2_1_33_1","volume-title":"What the daam: Interpreting stable diffusion using cross attention. arXiv preprint arXiv:2210.04885","author":"Tang Raphael","year":"2022","unstructured":"Raphael Tang, Linqing Liu, Akshat Pandey, Zhiying Jiang, Gefei Yang, Karun Kumar, Pontus Stenetorp, Jimmy Lin, and Ferhan Ture. 2022. What the daam: Interpreting stable diffusion using cross attention. arXiv preprint arXiv:2210.04885 (2022)."},{"key":"e_1_3_2_1_34_1","unstructured":"Aaron Van Den Oord Oriol Vinyals et al. 2017. Neural discrete representation learning. Advances in neural information processing systems Vol. 30 (2017)."},{"key":"e_1_3_2_1_35_1","volume-title":"Diffusiondb: A large-scale prompt gallery dataset for text-to-image generative models. arXiv preprint arXiv:2210.14896","author":"Wang Zijie J","year":"2022","unstructured":"Zijie J Wang, Evan Montoya, David Munechika, Haoyang Yang, Benjamin Hoover, and Duen Horng Chau. 2022. Diffusiondb: A large-scale prompt gallery dataset for text-to-image generative models. arXiv preprint arXiv:2210.14896 (2022)."},{"key":"e_1_3_2_1_36_1","volume-title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis. arXiv preprint arXiv:2306.09341","author":"Wu Xiaoshi","year":"2023","unstructured":"Xiaoshi Wu, Yiming Hao, Keqiang Sun, Yixiong Chen, Feng Zhu, Rui Zhao, and Hongsheng Li. 2023. Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis. arXiv preprint arXiv:2306.09341 (2023)."},{"key":"e_1_3_2_1_37_1","volume-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation. Advances in Neural Information Processing Systems","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 (2024)."},{"key":"e_1_3_2_1_38_1","volume-title":"High-quality Dataset for Image Restoration. arXiv preprint arXiv:2306.05390","author":"Yang Qinhong","year":"2023","unstructured":"Qinhong Yang, Dongdong Chen, Zhentao Tan, Qiankun Liu, Qi Chu, Jianmin Bao, Lu Yuan, Gang Hua, and Nenghai Yu. 2023. HQ-50K: A Large-scale, High-quality Dataset for Image Restoration. arXiv preprint arXiv:2306.05390 (2023)."},{"key":"e_1_3_2_1_39_1","volume-title":"Prompt Refinement with Image Pivot for Text-to-Image Generation. arXiv preprint arXiv:2407.00247","author":"Zhan Jingtao","year":"2024","unstructured":"Jingtao Zhan, Qingyao Ai, Yiqun Liu, Yingwei Pan, Ting Yao, Jiaxin Mao, Shaoping Ma, and Tao Mei. 2024a. Prompt Refinement with Image Pivot for Text-to-Image Generation. arXiv preprint arXiv:2407.00247 (2024)."},{"key":"e_1_3_2_1_40_1","volume-title":"Prompt Refinement with Image Pivot for Text-to-Image Generation. arXiv preprint arXiv:2407.00247","author":"Zhan Jingtao","year":"2024","unstructured":"Jingtao Zhan, Qingyao Ai, Yiqun Liu, Yingwei Pan, Ting Yao, Jiaxin Mao, Shaoping Ma, and Tao Mei. 2024b. Prompt Refinement with Image Pivot for Text-to-Image Generation. arXiv preprint arXiv:2407.00247 (2024)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00828"},{"key":"e_1_3_2_1_42_1","volume-title":"Miguel Eckstein, and William Yang Wang.","author":"Zhu Wanrong","year":"2023","unstructured":"Wanrong Zhu, Xinyi Wang, Yujie Lu, Tsu-Jui Fu, Xin Eric Wang, Miguel Eckstein, and William Yang Wang. 2023. Collaborative generative ai: Integrating gpt-k for efficient editing in text-to-image generation. arXiv preprint arXiv:2305.11317 (2023)."}],"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\/3746027.3755280","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:07:47Z","timestamp":1765339667000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755280"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":42,"alternative-id":["10.1145\/3746027.3755280","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755280","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"}}]}}