{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T16:14:07Z","timestamp":1776096847528,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:00:00Z","timestamp":1715385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Guangzhou Basic and Applied Basic Research Foundation","award":["2023A03J0142"],"award-info":[{"award-number":["2023A03J0142"]}]},{"name":"Guangzhou Basic and Applied Basic Research Foundation","award":["2024A04J6462"],"award-info":[{"award-number":["2024A04J6462"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,11]]},"DOI":"10.1145\/3613904.3642165","type":"proceedings-article","created":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T08:39:12Z","timestamp":1715416752000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":22,"title":["IntentTuner: An Interactive Framework for Integrating Human Intentions in Fine-tuning Text-to-Image Generative Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1967-0595","authenticated-orcid":false,"given":"Xingchen","family":"Zeng","sequence":"first","affiliation":[{"name":"Thrust of Data Science and Analytics, Hong Kong University of Science and Technology (Guangzhou), China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2424-0796","authenticated-orcid":false,"given":"Ziyao","family":"Gao","sequence":"additional","affiliation":[{"name":"Thrust of Computational Media and Arts, Hong Kong University of Science and Technology (Guangzhou), China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8874-5928","authenticated-orcid":false,"given":"Yilin","family":"Ye","sequence":"additional","affiliation":[{"name":"Thrust of Computational Media and Arts, The Hong Kong University of Science and Technology (Guangzhou), China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5600-8824","authenticated-orcid":false,"given":"Wei","family":"Zeng","sequence":"additional","affiliation":[{"name":"Thrust of Computational Media and Arts, The Hong Kong University of Science and Technology (Guangzhou), China and Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, China"}]}],"member":"320","published-online":{"date-parts":[[2024,5,11]]},"reference":[{"key":"e_1_3_3_3_1_1","unstructured":"2022. Civitai. https:\/\/civitai.com"},{"key":"e_1_3_3_3_2_1","unstructured":"2022. Kohya\u2019s Stable Diffusion trainers. https:\/\/github.com\/bmaltais\/kohya_ss"},{"key":"e_1_3_3_3_3_1","unstructured":"2022. LibLibAI. https:\/\/www.liblibai.com\/"},{"key":"e_1_3_3_3_4_1","unstructured":"2022. Stable Diffusion Web UI. https:\/\/github.com\/AUTOMATIC1111\/stable-diffusion-webui"},{"key":"e_1_3_3_3_5_1","unstructured":"2023. Adobe Firefly. https:\/\/www.adobe.com\/sensei\/generative-ai\/firefly.html"},{"key":"e_1_3_3_3_6_1","unstructured":"2023. CLIP Interrogator. https:\/\/github.com\/pharmapsychotic\/clip-interrogator"},{"key":"e_1_3_3_3_7_1","unstructured":"2023. Midjourney. https:\/\/www.midjourney.com\/"},{"key":"e_1_3_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1906.02569"},{"key":"e_1_3_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00053"},{"key":"e_1_3_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-019-0149-9"},{"key":"e_1_3_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3495883"},{"key":"e_1_3_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1141933"},{"key":"e_1_3_3_3_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095167"},{"key":"e_1_3_3_3_15_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2110.02861"},{"key":"e_1_3_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_34"},{"key":"e_1_3_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3327168"},{"key":"e_1_3_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2208.01618"},{"key":"e_1_3_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530164"},{"key":"e_1_3_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295408"},{"key":"e_1_3_3_3_21_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Hu J","year":"2022","unstructured":"Edward\u00a0J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_3_3_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"e_1_3_3_3_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3526113.3545612"},{"key":"e_1_3_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.2991\/978-94-6463-200-2_143"},{"key":"e_1_3_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2307.04767"},{"key":"e_1_3_3_3_28_1","volume-title":"Proceedings of the International Conference on Machine Learning. 19730\u201319742","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In Proceedings of the International Conference on Machine Learning. 19730\u201319742."},{"key":"e_1_3_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.16434"},{"key":"e_1_3_3_3_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-35891-3_37"},{"key":"e_1_3_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.05499"},{"key":"e_1_3_3_3_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501825"},{"key":"e_1_3_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3526113.3545621"},{"key":"e_1_3_3_3_34_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1608.03983"},{"key":"e_1_3_3_3_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"e_1_3_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1"},{"key":"e_1_3_3_3_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"e_1_3_3_3_38_1","volume-title":"Proceedings of the International Conference on Machine Learning. 8748\u20138763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, 2021. Learning transferable visual models from natural language supervision. In Proceedings of the International Conference on Machine Learning. 8748\u20138763."},{"key":"e_1_3_3_3_39_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2204.06125"},{"key":"e_1_3_3_3_40_1","volume-title":"Proceedings of the International Conference on Machine Learning. 8821\u20138831","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In Proceedings of the International Conference on Machine Learning. 8821\u20138831."},{"key":"e_1_3_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_3_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581641.3584037"},{"key":"e_1_3_3_3_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_3_3_44_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems. 36479\u201336494","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily\u00a0L Denton, Kamyar Ghasemipour, Raphael Gontijo\u00a0Lopes, Burcu Karagol\u00a0Ayan, Tim Salimans, 2022. Photorealistic text-to-image diffusion models with deep language understanding. In Proceedings of the Advances in Neural Information Processing Systems. 36479\u201336494."},{"key":"e_1_3_3_3_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157346"},{"key":"e_1_3_3_3_46_1","doi-asserted-by":"publisher","DOI":"10.5555\/3620237.3620360"},{"key":"e_1_3_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.17580"},{"key":"e_1_3_3_3_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00586"},{"key":"e_1_3_3_3_49_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.13971"},{"key":"e_1_3_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544549.3585680"},{"key":"e_1_3_3_3_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618315"},{"key":"e_1_3_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V37I2.25353"},{"key":"e_1_3_3_3_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581402"},{"key":"e_1_3_3_3_54_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems. 24824\u201324837","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc\u00a0V Le, Denny Zhou, 2022. Chain-of-thought prompting elicits reasoning in large language models. In Proceedings of the Advances in Neural Information Processing Systems. 24824\u201324837."},{"key":"e_1_3_3_3_55_1","doi-asserted-by":"publisher","DOI":"10.22215\/timreview\/1282"},{"key":"e_1_3_3_3_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581377"},{"key":"e_1_3_3_3_57_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.05.001"},{"key":"e_1_3_3_3_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"e_1_3_3_3_59_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.05977"},{"key":"e_1_3_3_3_60_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2306.04121"},{"key":"e_1_3_3_3_61_1","volume-title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation. Transactions on Machine Learning Research","author":"Yu Jiahui","year":"2022","unstructured":"Jiahui Yu, Yuanzhong Xu, Jing\u00a0Yu Koh, Thang Luong, Gunjan Baid, Zirui Wang, Vijay Vasudevan, Alexander Ku, Yinfei Yang, Burcu\u00a0Karagol Ayan, 2022. Scaling Autoregressive Models for Content-Rich Text-to-Image Generation. Transactions on Machine Learning Research (2022)."},{"key":"e_1_3_3_3_62_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.06790"},{"key":"e_1_3_3_3_63_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2305.08196"},{"key":"e_1_3_3_3_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_3_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"e_1_3_3_3_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591532"}],"event":{"name":"CHI '24: CHI Conference on Human Factors in Computing Systems","location":"Honolulu HI USA","acronym":"CHI '24","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGACCESS ACM Special Interest Group on Accessible Computing"]},"container-title":["Proceedings of the CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613904.3642165","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3613904.3642165","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:56:42Z","timestamp":1750291002000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613904.3642165"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,11]]},"references-count":66,"alternative-id":["10.1145\/3613904.3642165","10.1145\/3613904"],"URL":"https:\/\/doi.org\/10.1145\/3613904.3642165","relation":{},"subject":[],"published":{"date-parts":[[2024,5,11]]},"assertion":[{"value":"2024-05-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}