{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T21:25:26Z","timestamp":1769376326776,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681533","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"2719-2728","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Knowledge-Aware Artifact Image Synthesis with LLM-Enhanced Prompting and Multi-Source Supervision"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2453-9901","authenticated-orcid":false,"given":"Shengguang","family":"Wu","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6902-1195","authenticated-orcid":false,"given":"Zhenglun","family":"Chen","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4769-2812","authenticated-orcid":false,"given":"Qi","family":"Su","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","unstructured":"Luigi Asprino Luana Bulla Ludovica Marinucci Misael Mongiov\u00ec and Valentina Presutti. 2022. A Large Visual Question Answering Dataset for Cultural Heritage. 193--197. https:\/\/doi.org\/10.1007\/978--3-030--95470--3_14","DOI":"10.1007\/978--3-030--95470--3_14"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Pietro Bongini Federico Becattini and Alberto Del Bimbo. 2023. Is GPT-3 all you need for Visual Question Answering in Cultural Heritage? arXiv:2207.12101 [cs.CV]","DOI":"10.1007\/978-3-031-25056-9_18"},{"key":"e_1_3_2_1_3_1","unstructured":"Tom B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell Sandhini Agarwal Ariel Herbert-Voss Gretchen Krueger Tom Henighan Rewon Child Aditya Ramesh Daniel M. Ziegler Jeffrey Wu Clemens Winter Christopher Hesse Mark Chen Eric Sigler Mateusz Litwin Scott Gray Benjamin Chess Jack Clark Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever and Dario Amodei. 2020. Language Models are Few-Shot Learners. arXiv:2005.14165 [cs.CL]"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547925"},{"key":"e_1_3_2_1_6_1","volume-title":"Wortman Vaughan (Eds.)","volume":"34","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion Models Beat GANs on Image Synthesis. In Advances in Neural Information Processing Systems, M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan (Eds.), Vol. 34. Curran Associates, Inc., 8780--8794. https:\/\/proceedings.neurips.cc\/ paper_files\/paper\/2021\/file\/49ad23d1ec9fa4bd8d77d02681df5cfa-Paper.pdf"},{"key":"e_1_3_2_1_7_1","volume-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618","author":"Gal Rinon","year":"2022","unstructured":"Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit H Bermano, Gal Chechik, and Daniel Cohen-Or. 2022. An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Noa Garcia Chentao Ye Zihua Liu Qingtao Hu Mayu Otani Chenhui Chu Yuta Nakashima and Teruko Mitamura. 2020. A Dataset and Baselines for Visual Question Answering on Art. arXiv:2008.12520 [cs.CV]","DOI":"10.1007\/978-3-030-66096-3_8"},{"key":"e_1_3_2_1_9_1","volume-title":"Weinberger (Eds.)","volume":"27","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. In Advances in Neural Information Processing Systems, Z. Ghahramani, M. Welling, C. Cortes, N. Lawrence, and K.Q. Weinberger (Eds.), Vol. 27. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2014\/file\/ 5ca3e9b122f61f8f06494c97b1afccf3-Paper.pdf"},{"key":"e_1_3_2_1_10_1","unstructured":"Shuyang Gu Dong Chen Jianmin Bao Fang Wen Bo Zhang Dongdong Chen Lu Yuan and Baining Guo. 2022. Vector Quantized Diffusion Model for Text-to- Image Synthesis. arXiv:2111.14822 [cs.CV]"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00684"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"e_1_3_2_1_13_1","volume-title":"Denoising Diffusion Probabilistic Models. (June","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. (June 2020). arXiv:2006.11239 [cs.LG] https:\/\/arxiv.org\/pdf\/2006.11239. pdf"},{"key":"e_1_3_2_1_14_1","volume-title":"Perceptual losses for realtime style transfer and super-resolution. (March","author":"Johnson Justin","year":"2016","unstructured":"Justin Johnson, Alexandre Alahi, and Li Fei-Fei. 2016. Perceptual losses for realtime style transfer and super-resolution. (March 2016). arXiv:1603.08155 [cs.CV]"},{"key":"e_1_3_2_1_15_1","volume-title":"Scaling up GANs for text-to-image synthesis. (March","author":"Kang Minguk","year":"2023","unstructured":"Minguk Kang, Jun-Yan Zhu, Richard Zhang, Jaesik Park, Eli Shechtman, Sylvain Paris, and Taesung Park. 2023. Scaling up GANs for text-to-image synthesis. (March 2023). arXiv:2303.05511 [cs.CV]"},{"key":"e_1_3_2_1_16_1","volume-title":"Auto-Encoding Variational Bayes. (Dec","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma and Max Welling. 2013. Auto-Encoding Variational Bayes. (Dec. 2013). arXiv:1312.6114 [stat.ML]"},{"key":"e_1_3_2_1_17_1","volume-title":"Multi-Concept Customization of Text-to-Image Diffusion. arXiv preprint arXiv:2212.04488","author":"Kumari Nupur","year":"2022","unstructured":"Nupur Kumari, Bingliang Zhang, Richard Zhang, Eli Shechtman, and Jun-Yan Zhu. 2022. Multi-Concept Customization of Text-to-Image Diffusion. arXiv preprint arXiv:2212.04488 (2022)."},{"key":"e_1_3_2_1_18_1","volume-title":"Shibani Santurkar, Surya Ganguli, Tatsunori Hashimoto, Thomas Icard, Tianyi Zhang, Vishrav Chaudhary, William Wang, Xuechen Li, Yifan Mai, Yuhui Zhang, and Yuta Koreeda.","author":"Liang Percy","year":"2022","unstructured":"Percy Liang, Rishi Bommasani, Tony Lee, Dimitris Tsipras, Dilara Soylu, Michihiro Yasunaga, Yian Zhang, Deepak Narayanan, Yuhuai Wu, Ananya Kumar, Benjamin Newman, Binhang Yuan, Bobby Yan, Ce Zhang, Christian Cosgrove, Christopher D Manning, Christopher R\u00e9, Diana Acosta-Navas, Drew A Hudson, Eric Zelikman, Esin Durmus, Faisal Ladhak, Frieda Rong, Hongyu Ren, Huaxiu Yao, Jue Wang, Keshav Santhanam, Laurel Orr, Lucia Zheng, Mert Yuksekgonul, Mirac Suzgun, Nathan Kim, Neel Guha, Niladri Chatterji, Omar Khattab, Peter Henderson, Qian Huang, Ryan Chi, Sang Michael Xie, Shibani Santurkar, Surya Ganguli, Tatsunori Hashimoto, Thomas Icard, Tianyi Zhang, Vishrav Chaudhary, William Wang, Xuechen Li, Yifan Mai, Yuhui Zhang, and Yuta Koreeda. 2022. Holistic Evaluation of Language Models. (Nov. 2022). arXiv:2211.09110 [cs.CL]"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.225"},{"key":"e_1_3_2_1_20_1","unstructured":"Alex Nichol and Prafulla Dhariwal. 2021. Improved Denoising Diffusion Probabilistic Models. arXiv:2102.09672 [cs.LG]"},{"key":"e_1_3_2_1_21_1","volume-title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. arXiv:2112.10741 [cs.CV]","author":"Nichol Alex","year":"2022","unstructured":"Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2022. GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. arXiv:2112.10741 [cs.CV]"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_23_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_24_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever.","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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning transferable visual models from natural language supervision. (Feb. 2021). arXiv:2103.00020 [cs.CV]"},{"key":"e_1_3_2_1_25_1","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. 2022. Hierarchical Text-Conditional Image Generation with CLIP Latents. arXiv:2204.06125 [cs.CV]"},{"key":"e_1_3_2_1_26_1","volume-title":"High-resolution image synthesis with latent diffusion models. (Dec","author":"Rombach Robin","year":"2021","unstructured":"Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bj\u00f6rn Ommer. 2021. High-resolution image synthesis with latent diffusion models. (Dec. 2021). arXiv:2112.10752 [cs.CV]"},{"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":"U-Net: Convolutional Networks for Biomedical Image Segmentation. (May","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. (May 2015). arXiv:1505.04597 [cs.CV]"},{"key":"e_1_3_2_1_29_1","volume-title":"Burcu Karagol Ayan, S. Sara Mahdavi, Rapha Gontijo Lopes, Tim Salimans, Jonathan Ho, David J Fleet, and Mohammad Norouzi.","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily Denton, Seyed Kamyar Seyed Ghasemipour, Burcu Karagol Ayan, S. Sara Mahdavi, Rapha Gontijo Lopes, Tim Salimans, Jonathan Ho, David J Fleet, and Mohammad Norouzi. 2022. Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding. arXiv:2205.11487 [cs.CV]"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350972"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","unstructured":"Daqian Shi Xiaolei Diao Lida Shi Hao Tang Yang Chi Chuntao Li and Hao Xu. 2022. CharFormer: A Glyph Fusion based Attentive Framework for Highprecision Character Image Denoising. (2022). https:\/\/doi.org\/10.1145\/3503161. 3548208 arXiv:arXiv:2207.07798","DOI":"10.1145\/3503161"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548344"},{"key":"e_1_3_2_1_34_1","unstructured":"Jascha Sohl-Dickstein Eric A.Weiss Niru Maheswaranathan and Surya Ganguli. 2015. Deep Unsupervised Learning using Nonequilibrium Thermodynamics. arXiv:arXiv:1503.03585"},{"key":"e_1_3_2_1_35_1","unstructured":"Jiaming Song Chenlin Meng and Stefano Ermon. 2022. Denoising Diffusion Implicit Models. arXiv:2010.02502 [cs.LG]"},{"key":"e_1_3_2_1_36_1","unstructured":"Yang Song and Stefano Ermon. 2020. Generative Modeling by Estimating Gradients of the Data Distribution. arXiv:1907.05600 [cs.LG]"},{"key":"e_1_3_2_1_37_1","unstructured":"Yang Song Jascha Sohl-Dickstein Diederik P. Kingma Abhishek Kumar Stefano Ermon and Ben Poole. 2020. Score-Based Generative Modeling through Stochastic Differential Equations. arXiv:arXiv:2011.13456"},{"key":"e_1_3_2_1_38_1","unstructured":"Yang Song Jascha Sohl-Dickstein Diederik P. Kingma Abhishek Kumar Stefano Ermon and Ben Poole. 2021. Score-Based Generative Modeling through Stochastic Differential Equations. arXiv:2011.13456 [cs.LG]"},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the International Conference on Image Analysis and Processing.","author":"Stefanini Matteo","year":"2019","unstructured":"Matteo Stefanini, Marcella Cornia, Lorenzo Baraldi, Massimiliano Corsini, and Rita Cucchiara. 2019. Artpedia: A New Visual-Semantic Dataset with Visual and Contextual Sentences. In Proceedings of the International Conference on Image Analysis and Processing."},{"key":"e_1_3_2_1_40_1","unstructured":"Taipei National Palace Museum. 2019. National Palace Museum Open Data. data retrieved from National Palace Museum Open Data https:\/\/theme.npm.edu.tw\/ opendata\/index.aspx?lang=2."},{"key":"e_1_3_2_1_41_1","volume-title":"Representation learning with Contrastive Predictive Coding. (July","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with Contrastive Predictive Coding. (July 2018). arXiv:1807.03748 [cs.LG]"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"YizhongWang Yeganeh Kordi Swaroop Mishra Alisa Liu Noah A. Smith Daniel Khashabi and Hannaneh Hajishirzi. 2022. Self-Instruct: Aligning Language Model with Self Generated Instructions. arXiv:2212.10560 [cs.CL]","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_2_1_45_1","volume-title":"andWangmeng Zuo","author":"Zhang Yabo","year":"2023","unstructured":"YuxiangWei, Yabo Zhang, Zhilong Ji, Jinfeng Bai, Lei Zhang, andWangmeng Zuo. 2023. Elite: Encoding visual concepts into textual embeddings for customized text-to-image generation. arXiv preprint arXiv:2302.13848 (2023)."},{"key":"e_1_3_2_1_46_1","volume-title":"AttnGAN: Fine-grained text to image generation with attentional generative adversarial networks. (Nov","author":"Xu Tao","year":"2017","unstructured":"Tao Xu, Pengchuan Zhang, Qiuyuan Huang, Han Zhang, Zhe Gan, Xiaolei Huang, and Xiaodong He. 2017. AttnGAN: Fine-grained text to image generation with attentional generative adversarial networks. (Nov. 2017). arXiv:1711.10485 [cs.CV]"},{"key":"e_1_3_2_1_47_1","volume-title":"Diffusion models: A comprehensive survey of methods and applications. (Sept","author":"Yang Ling","year":"2022","unstructured":"Ling Yang, Zhilong Zhang, Yang Song, Shenda Hong, Runsheng Xu, Yue Zhao, Wentao Zhang, Bin Cui, and Ming-Hsuan Yang. 2022. Diffusion models: A comprehensive survey of methods and applications. (Sept. 2022). arXiv:2209.00796 [cs.LG]"},{"key":"e_1_3_2_1_48_1","volume-title":"StackGAN: Text to photo-realistic image synthesis with Stacked Generative Adversarial Networks. (Dec","author":"Zhang Han","year":"2016","unstructured":"Han Zhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaogang Wang, Xiaolei Huang, and Dimitris Metaxas. 2016. StackGAN: Text to photo-realistic image synthesis with Stacked Generative Adversarial Networks. (Dec. 2016). arXiv:1612.03242 [cs.CV]"},{"key":"e_1_3_2_1_49_1","unstructured":"Jiaxing Zhang Ruyi Gan Junjie Wang Yuxiang Zhang Lin Zhang Ping Yang Xinyu Gao Ziwei Wu Xiaoqun Dong Junqing He Jianheng Zhuo Qi Yang Yongfeng Huang Xiayu Li Yanghan Wu Junyu Lu Xinyu Zhu Weifeng Chen Ting Han Kunhao Pan Rui Wang Hao Wang Xiaojun Wu Zhongshen Zeng and Chongpei Chen. 2022. Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence. arXiv:arXiv:2209.02970"},{"key":"e_1_3_2_1_50_1","volume-title":"Being the Foundation of Chinese Cognitive Intelligence. CoRR abs\/2209.02970","author":"Zhang Jiaxing","year":"2022","unstructured":"Jiaxing Zhang, Ruyi Gan, Junjie Wang, Yuxiang Zhang, Lin Zhang, Ping Yang, Xinyu Gao, Ziwei Wu, Xiaoqun Dong, Junqing He, Jianheng Zhuo, Qi Yang, Yongfeng Huang, Xiayu Li, Yanghan Wu, Junyu Lu, Xinyu Zhu, Weifeng Chen, Ting Han, Kunhao Pan, Rui Wang, Hao Wang, Xiaojun Wu, Zhongshen Zeng, and Chongpei Chen. 2022. Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence. CoRR abs\/2209.02970 (2022)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"crossref","unstructured":"Richard Zhang Phillip Isola Alexei A. Efros Eli Shechtman and Oliver Wang. 2018. The Unreasonable Effectiveness of Deep Features as a Perceptual Metric. arXiv:arXiv:1801.03924","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467285"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681533","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681533","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:48Z","timestamp":1750294668000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681533"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":52,"alternative-id":["10.1145\/3664647.3681533","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681533","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}