{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:08:38Z","timestamp":1781586518827,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Major Special Funds of the Changsha Scientific and Technological Project","award":["kh2202006"],"award-info":[{"award-number":["kh2202006"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,30]]},"DOI":"10.1145\/3652583.3658071","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T06:30:40Z","timestamp":1717741840000},"page":"239-247","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["ExpoGenius: Robust Personalized Human Image Generation using Diffusion Model for Exposure Variation and Pose Transfer"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2398-3096","authenticated-orcid":false,"given":"Depei","family":"Liu","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4872-8557","authenticated-orcid":false,"given":"Hongjie","family":"Fan","sequence":"additional","affiliation":[{"name":"China University of Political Science and Law, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4464-804X","authenticated-orcid":false,"given":"Junfei","family":"Liu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"e_1_3_2_1_2_1","volume-title":"CVPR","author":"Bhunia Ankan Kumar","year":"2023","unstructured":"Ankan Kumar Bhunia, Salman H. Khan, Hisham Cholakkal, Rao Muhammad Anwer, Jorma Laaksonen, Mubarak Shah, and Fahad Shahbaz Khan. [n.,d.]. Person Image Synthesis via Denoising Diffusion Model. In CVPR, 2023."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"e_1_3_2_1_4_1","volume-title":"Muse: Text-to-image generation via masked generative transformers. arXiv preprint arXiv:2301.00704","author":"Chang Huiwen","year":"2023","unstructured":"Huiwen Chang, Han Zhang, Jarred Barber, AJ Maschinot, Jose Lezama, Lu Jiang, Ming-Hsuan Yang, Kevin Murphy, William T Freeman, Michael Rubinstein, et al. 2023. Muse: Text-to-image generation via masked generative transformers. arXiv preprint arXiv:2301.00704 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"e_1_3_2_1_6_1","volume-title":"ICLR","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. [n.,d.]. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In ICLR, 2021."},{"key":"e_1_3_2_1_7_1","volume-title":"ICLR","author":"Gal Rinon","year":"2023","unstructured":"Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit Haim Bermano, Gal Chechik, and Daniel Cohen-Or. [n.,d.]. An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion. In ICLR, 2023."},{"key":"e_1_3_2_1_8_1","volume-title":"Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models. ACM TOG","author":"Gal Rinon","year":"2023","unstructured":"Rinon Gal, Moab Arar, Yuval Atzmon, Amit H. Bermano, Gal Chechik, and Daniel Cohen-Or. 2023. Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models. ACM TOG (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"Generative adversarial networks. Commun. ACM","author":"Goodfellow Ian J.","year":"2020","unstructured":"Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron C. Courville, and Yoshua Bengio. 2020. Generative adversarial networks. Commun. ACM (2020)."},{"key":"e_1_3_2_1_10_1","volume-title":"Masked Autoencoders Are Scalable Vision Learners. In CVPR","author":"He Kaiming","year":"2022","unstructured":"Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Doll\u00e1 r, and Ross B. Girshick. [n.,d.]. Masked Autoencoders Are Scalable Vision Learners. In CVPR, 2022."},{"key":"e_1_3_2_1_11_1","volume-title":"NeurIPS","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. [n.,d.]. Denoising Diffusion Probabilistic Models. In NeurIPS, 2020."},{"key":"e_1_3_2_1_12_1","volume-title":"Classifier-Free Diffusion Guidance. arXiv preprint arXiv:2207.12598","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-Free Diffusion Guidance. arXiv preprint arXiv:2207.12598 (2022)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"e_1_3_2_1_16_1","volume-title":"DiffFace: Diffusion-based Face Swapping with Facial Guidance. arXiv preprint arXiv:2212.13344","author":"Kim Kihong","year":"2022","unstructured":"Kihong Kim, Yunho Kim, Seokju Cho, Junyoung Seo, Jisu Nam, Kychul Lee, Seungryong Kim, and KwangHee Lee. 2022. DiffFace: Diffusion-based Face Swapping with Facial Guidance. arXiv preprint arXiv:2212.13344 (2022)."},{"key":"e_1_3_2_1_17_1","volume-title":"Adam: A Method for Stochastic Optimization. In ICLR","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. [n.,d.]. Adam: A Method for Stochastic Optimization. In ICLR, 2015."},{"key":"e_1_3_2_1_18_1","volume-title":"Auto-Encoding Variational Bayes. In ICLR","author":"Diederik","year":"2014","unstructured":"Diederik P. Kingma and Max Welling. [n.,d.]. Auto-Encoding Variational Bayes. In ICLR, 2014."},{"key":"e_1_3_2_1_19_1","volume-title":"Fusing Visual Information in Text-to-Image Generation. arXiv preprint arXiv:2303.01000","author":"Kirstain Yuval","year":"2023","unstructured":"Yuval Kirstain, Omer Levy, and Adam Polyak. 2023. X&Fuse: Fusing Visual Information in Text-to-Image Generation. arXiv preprint arXiv:2303.01000 (2023)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01765"},{"key":"e_1_3_2_1_22_1","volume-title":"Visual Instruction Tuning. arXiv preprint arXiv:2304.08485","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual Instruction Tuning. arXiv preprint arXiv:2304.08485 (2023)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.124"},{"key":"e_1_3_2_1_25_1","volume-title":"ICML","author":"Nichol Alexander Quinn","year":"2022","unstructured":"Alexander Quinn Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. [n.,d.]. GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. In ICML, 2022."},{"key":"e_1_3_2_1_26_1","volume-title":"ICML","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. [n.,d.]. Learning Transferable Visual Models From Natural Language Supervision. In ICML, 2021."},{"key":"e_1_3_2_1_27_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_28_1","volume-title":"ICML","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. [n.,d.]. Zero-Shot Text-to-Image Generation. In ICML, 2021."},{"key":"e_1_3_2_1_29_1","volume-title":"Pivotal Tuning for Latent-based Editing of Real Images. ACM TOG","author":"Roich Daniel","year":"2023","unstructured":"Daniel Roich, Ron Mokady, Amit H. Bermano, and Daniel Cohen-Or. 2023. Pivotal Tuning for Latent-based Editing of Real Images. ACM TOG (2023)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_31_1","volume-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv preprint arXiv:1505.04597","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv preprint arXiv:1505.04597 (2015)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_33_1","volume-title":"Raphael Gontijo Lopes, Burcu Karagol Ayan, 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 L. Denton, Seyed Kamyar Seyed Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, Jonathan Ho, David J. Fleet, and Mohammad Norouzi. 2022. Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding. In NeurIPS."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Shaw Peter","year":"2019","unstructured":"Peter Shaw, Jakob Uszkoreit, and Ashish Vaswani. [n.,d.]. Self-Attention with Relative Position Representations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019."},{"key":"e_1_3_2_1_36_1","volume-title":"InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning. arXiv preprint arXiv:2304.03411","author":"Shi Jing","year":"2023","unstructured":"Jing Shi, Wei Xiong, Zhe Lin, and Hyun Joon Jung. 2023. InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning. arXiv preprint arXiv:2304.03411 (2023)."},{"key":"e_1_3_2_1_37_1","volume-title":"Simoncelli","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C. Bovik, Hamid R. Sheikh, and Eero P. Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. TIP (2004)."},{"key":"e_1_3_2_1_38_1","volume-title":"ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation. arXiv preprint arXiv:2302.13848","author":"Wei Yuxiang","year":"2023","unstructured":"Yuxiang Wei, Yabo Zhang, Zhilong Ji, Jinfeng Bai, Lei Zhang, and Wangmeng 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_39_1","volume-title":"FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention. arXiv preprint arXiv:2305.10431","author":"Xiao Guangxuan","year":"2023","unstructured":"Guangxuan Xiao, Tianwei Yin, William T. Freeman, Fr\u00e9 do Durand, and Song Han. 2023. FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention. arXiv preprint arXiv:2305.10431 (2023)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"e_1_3_2_1_41_1","volume-title":"Thang Luong, Gunjan Baid, Zirui Wang, Vijay Vasudevan, Alexander Ku, Yinfei Yang, Burcu Karagol Ayan, et al.","author":"Yu Jiahui","year":"2022","unstructured":"Jiahui Yu, Yuanzhong Xu, Jing Yu Koh, Thang Luong, Gunjan Baid, Zirui Wang, Vijay Vasudevan, Alexander Ku, Yinfei Yang, Burcu Karagol Ayan, et al. 2022. Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint arXiv:2206.10789 (2022)."},{"key":"e_1_3_2_1_42_1","volume-title":"Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks. SPL","author":"Zhang Kaipeng","year":"2016","unstructured":"Kaipeng Zhang, Zhanpeng Zhang, Zhifeng Li, and Yu Qiao. 2016. Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks. SPL (2016)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_44_1","volume-title":"CVPR","author":"Zhang Richard","year":"2019","unstructured":"Richard Zhang, Phillip Isola, Alexei A. Efros, Eli Shechtman, and Oliver Wang. [n.,d.] a. The Unreasonable Effectiveness of Deep Features as a Perceptual Metric. In CVPR, 2019."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01814"},{"key":"e_1_3_2_1_46_1","volume-title":"Enhancing Detail Preservation for Customized Text-to-Image Generation: A Regularization-Free Approach. arXiv preprint arXiv:2305.13579","author":"Zhou Yufan","year":"2023","unstructured":"Yufan Zhou, Ruiyi Zhang, Tong Sun, and Jinhui Xu. 2023. Enhancing Detail Preservation for Customized Text-to-Image Generation: A Regularization-Free Approach. arXiv preprint arXiv:2305.13579 (2023)."}],"event":{"name":"ICMR '24: International Conference on Multimedia Retrieval","location":"Phuket Thailand","acronym":"ICMR '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 2024 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658071","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652583.3658071","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T08:52:35Z","timestamp":1755766355000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658071"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":46,"alternative-id":["10.1145\/3652583.3658071","10.1145\/3652583"],"URL":"https:\/\/doi.org\/10.1145\/3652583.3658071","relation":{},"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"2024-06-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}