{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T04:55:00Z","timestamp":1782795300360,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":40,"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"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100002855","name":"Ministry of Science and Technology of the People's Republic of China","doi-asserted-by":"publisher","award":["No. 2021ZD0111700"],"award-info":[{"award-number":["No. 2021ZD0111700"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680734","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"11013-11021","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["DreamBooth++: Boosting Subject-Driven Generation via Region-Level References Packing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7053-1438","authenticated-orcid":false,"given":"Zhongyi","family":"Fan","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2129-9182","authenticated-orcid":false,"given":"Zixin","family":"Yin","sequence":"additional","affiliation":[{"name":"State Key Lab of Software Development Environment, Beihang University, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9520-0141","authenticated-orcid":false,"given":"Gang","family":"Li","sequence":"additional","affiliation":[{"name":"University of the Chinese Academy of Sciences & Institute of Software, Chinese Academy of Sciences, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3180-0484","authenticated-orcid":false,"given":"Yibing","family":"Zhan","sequence":"additional","affiliation":[{"name":"JD Explore Academy, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2220-3880","authenticated-orcid":false,"given":"Heliang","family":"Zheng","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"SIGGRAPH Asia 2023 Conference Papers. 1--10","author":"Arar Moab","unstructured":"Moab Arar, Rinon Gal, Yuval Atzmon, Gal Chechik, Daniel Cohen-Or, Ariel Shamir, and Amit H. Bermano. 2023. Domain-agnostic tuning-encoder for fast personalization of text-to-image models. In SIGGRAPH Asia 2023 Conference Papers. 1--10."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"e_1_3_2_1_4_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Chen Wenhu","year":"2024","unstructured":"Wenhu Chen, Hexiang Hu, Yandong Li, Nataniel Ruiz, Xuhui Jia, Ming-Wei Chang, and William W Cohen. 2024. Subject-driven text-to-image generation via apprenticeship learning. Advances in Neural Information Processing Systems, Vol. 36."},{"key":"e_1_3_2_1_5_1","volume-title":"Anydoor: Zero-shot object-level image customization.","author":"Chen Xi","year":"2024","unstructured":"Xi Chen, Lianghua Huang, Yu Liu, Yujun Shen, Deli Zhao, and Hengshuang Zhao. 2024. Anydoor: Zero-shot object-level image customization. (2024), 6593--6602."},{"key":"e_1_3_2_1_6_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Dehghani Mostafa","year":"2024","unstructured":"Mostafa Dehghani, Basil Mustafa, Josip Djolonga, Jonathan Heek, Matthias Minderer, Mathilde Caron, Andreas Steiner, Joan Puigcerver, Robert Geirhos, Ibrahim M Alabdulmohsin, et al. 2024. Patch n'pack: Navit, a vision transformer for any aspect ratio and resolution. Advances in Neural Information Processing Systems, Vol. 36."},{"key":"e_1_3_2_1_7_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805."},{"key":"e_1_3_2_1_8_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929."},{"key":"e_1_3_2_1_9_1","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."},{"key":"e_1_3_2_1_10_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33, 6840--6851."},{"key":"e_1_3_2_1_11_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685.","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685."},{"key":"e_1_3_2_1_12_1","volume-title":"Dreamtuner: Single image is enough for subject-driven generation. arXiv preprint arXiv:2312.13691","author":"Hua Miao","year":"2023","unstructured":"Miao Hua, Jiawei Liu, Fei Ding, Wei Liu, Jie Wu, and Qian He. 2023. Dreamtuner: Single image is enough for subject-driven generation. arXiv preprint arXiv:2312.13691 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"Yandong Li, Han Zhang, Boqing Gong, Tingbo Hou, Huisheng Wang, and Yu-Chuan Su.","author":"Jia Xuhui","year":"2023","unstructured":"Xuhui Jia, Yang Zhao, Kelvin CK Chan, Yandong Li, Han Zhang, Boqing Gong, Tingbo Hou, Huisheng Wang, and Yu-Chuan Su. 2023. Taming encoder for zero fine-tuning image customization with text-to-image diffusion models. arXiv preprint arXiv:2304.02642 (2023)."},{"key":"e_1_3_2_1_14_1","unstructured":"Mario Michael Krell Matej Kosec Sergio P. Perez and Andrew Fitzgibbon. 2022. Efficient Sequence Packing without Cross-contamination: Accelerating Large Language Models without Impacting Performance. arxiv: 2107.02027 [cs.CL]"},{"key":"e_1_3_2_1_15_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Li Dongxu","year":"2024","unstructured":"Dongxu Li, Junnan Li, and Steven Hoi. 2024. Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing. Advances in Neural Information Processing Systems, Vol. 36."},{"key":"e_1_3_2_1_16_1","volume-title":"Beyond Inserting: Learning Identity Embedding for Semantic-Fidelity Personalized Diffusion Generation.","author":"Li Yang","year":"2024","unstructured":"Yang Li, Songlin Yang, Wei Wang, and Jing Dong. 2024. Beyond Inserting: Learning Identity Embedding for Semantic-Fidelity Personalized Diffusion Generation."},{"key":"e_1_3_2_1_17_1","unstructured":"Shilong Liu Zhaoyang Zeng Tianhe Ren Feng Li Hao Zhang Jie Yang Chunyuan Li Jianwei Yang Hang Su Jun Zhu et al. 2023. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)."},{"key":"e_1_3_2_1_18_1","first-page":"5775","article-title":"Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps","volume":"35","author":"Lu Cheng","year":"2022","unstructured":"Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu. 2022. Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps. Advances in Neural Information Processing Systems, Vol. 35, 5775--5787.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_19_1","volume-title":"Latent consistency models: Synthesizing high-resolution images with few-step inference. arXiv preprint arXiv:2310.04378","author":"Luo Simian","year":"2023","unstructured":"Simian Luo, Yiqin Tan, Longbo Huang, Jian Li, and Hang Zhao. 2023. Latent consistency models: Synthesizing high-resolution images with few-step inference. arXiv preprint arXiv:2310.04378 (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"Subject-diffusion: Open domain personalized text-to-image generation without test-time fine-tuning.","author":"Ma Jian","year":"2024","unstructured":"Jian Ma, Junhao Liang, Chen Chen, and Haonan Lu. 2024. Subject-diffusion: Open domain personalized text-to-image generation without test-time fine-tuning. (2024), 1--12."},{"key":"e_1_3_2_1_21_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."},{"key":"e_1_3_2_1_22_1","first-page":"79320","article-title":"Controlling text-to-image diffusion by orthogonal finetuning","volume":"36","author":"Qiu Zeju","year":"2023","unstructured":"Zeju Qiu, Weiyang Liu, Haiwen Feng, Yuxuan Xue, Yao Feng, Zhen Liu, Dan Zhang, Adrian Weller, and Bernhard Sch\u00f6lkopf. 2023. Controlling text-to-image diffusion by orthogonal finetuning. Advances in Neural Information Processing Systems, Vol. 36, 79320--79362.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","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, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_24_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, Vol. 1, 2 (2022), 3."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_26_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention--MICCAI 2015: 18th international conference","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention--MICCAI 2015: 18th international conference, Munich, Germany, October 5--9, 2015, proceedings, part III 18. Springer, 234--241."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_28_1","volume-title":"Burcu Karagol Ayan, Tim Salimans, et al.","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al. 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in neural information processing systems, Vol. 35, 36479--36494."},{"key":"e_1_3_2_1_29_1","volume-title":"Instantbooth: Personalized text-to-image generation without test-time finetuning.","author":"Shi Jing","year":"2024","unstructured":"Jing Shi, Wei Xiong, Zhe Lin, and Hyun Joon Jung. 2024. Instantbooth: Personalized text-to-image generation without test-time finetuning. (2024), 8543--8552."},{"key":"e_1_3_2_1_30_1","unstructured":"Jiaming Song Chenlin Meng and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502."},{"key":"e_1_3_2_1_31_1","unstructured":"Yang Song Prafulla Dhariwal Mark Chen and Ilya Sutskever. 2023. Consistency models. arXiv preprint arXiv:2303.01469."},{"key":"e_1_3_2_1_32_1","unstructured":"Ashish Vaswani. 2017. Attention is all you need. arXiv preprint arXiv:1706.03762."},{"key":"e_1_3_2_1_33_1","volume-title":"Diffusers: State-of-the-art diffusion models.","author":"von Platen Patrick","year":"2022","unstructured":"Patrick von Platen, Suraj Patil, Anton Lozhkov, Pedro Cuenca, Nathan Lambert, Kashif Rasul, Mishig Davaadorj, Dhruv Nair, Sayak Paul, William Berman, Yiyi Xu, Steven Liu, and Thomas Wolf. 2022. Diffusers: State-of-the-art diffusion models."},{"key":"e_1_3_2_1_34_1","unstructured":"Zhendong Wang Yifan Jiang Huangjie Zheng Peihao Wang Pengcheng He Zhangyang Wang Weizhu Chen Mingyuan Zhou et al. 2024. Patch diffusion: Faster and more data-efficient training of diffusion models. Advances in neural information processing systems Vol. 36."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"e_1_3_2_1_36_1","volume-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721","author":"Ye Hu","year":"2023","unstructured":"Hu Ye, Jun Zhang, Sibo Liu, Xiao Han, and Wei Yang. 2023. Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)."},{"key":"e_1_3_2_1_37_1","unstructured":"Ge Yuan Xiaodong Cun Yong Zhang Maomao Li Chenyang Qi Xintao Wang Ying Shan and Huicheng Zheng. 2023. Inserting anybody in diffusion models via celeb basis. arXiv preprint arXiv:2306.00926."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618342"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02065"}],"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\/3664647.3680734","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680734","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:06:24Z","timestamp":1750291584000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680734"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":40,"alternative-id":["10.1145\/3664647.3680734","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680734","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"}}]}}