{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:47:04Z","timestamp":1772905624921,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":39,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680658","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"10535-10543","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Pick-and-Draw: Training-free Semantic Guidance for Text-to-Image Personalization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1907-0996","authenticated-orcid":false,"given":"Henglei","family":"Lv","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3510-8301","authenticated-orcid":false,"given":"Jiayu","family":"Xiao","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1943-8219","authenticated-orcid":false,"given":"Liang","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27850"},{"key":"e_1_3_2_1_2_1","volume-title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing. arXiv preprint arXiv:2304.08465","author":"Cao Mingdeng","year":"2023","unstructured":"Mingdeng Cao, Xintao Wang, Zhongang Qi, Ying Shan, Xiaohu Qie, and Yinqiang Zheng. 2023. MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing. arXiv preprint arXiv:2304.08465 (2023)."},{"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","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"e_1_3_2_1_5_1","volume-title":"Disenbooth: Disentangled parameter-efficient tuning for subject driven text-to-image generation. arXiv preprint arXiv:2305.03374","author":"Chen Hong","year":"2023","unstructured":"Hong Chen, Yipeng Zhang, Xin Wang, Xuguang Duan, Yuwei Zhou, and Wenwu Zhu. 2023. Disenbooth: Disentangled parameter-efficient tuning for subject driven text-to-image generation. arXiv preprint arXiv:2305.03374 (2023)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"e_1_3_2_1_7_1","volume-title":"Diffusion models beat gans on image synthesis. Advances in neural information processing systems 34","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in neural information processing systems 34 (2021), 8780--8794."},{"key":"e_1_3_2_1_8_1","volume-title":"Diffusion self-guidance for controllable image generation. arXiv preprint arXiv:2306.00986","author":"Epstein Dave","year":"2023","unstructured":"Dave Epstein, Allan Jabri, Ben Poole, Alexei A Efros, and Aleksander Holynski. 2023. Diffusion self-guidance for controllable image generation. arXiv preprint arXiv:2306.00986 (2023)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00129"},{"key":"e_1_3_2_1_10_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_11_1","volume-title":"Designing an encoder for fast personalization of text-to-image models. arXiv preprint arXiv:2302.12228","author":"Gal Rinon","year":"2023","unstructured":"Rinon Gal, Moab Arar, Yuval Atzmon, Amit H Bermano, Gal Chechik, and Daniel Cohen-Or. 2023. Designing an encoder for fast personalization of text-to-image models. arXiv preprint arXiv:2302.12228 (2023)."},{"key":"e_1_3_2_1_12_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_13_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 (2021)."},{"key":"e_1_3_2_1_14_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_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"e_1_3_2_1_16_1","volume-title":"Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing. arXiv preprint arXiv:2305.14720","author":"Li Dongxu","year":"2023","unstructured":"Dongxu Li, Junnan Li, and Steven CH Hoi. 2023. Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing. arXiv preprint arXiv:2305.14720 (2023)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"e_1_3_2_1_18_1","volume-title":"Dragondiffusion: Enabling drag-style manipulation on diffusion models. arXiv preprint arXiv:2307.02421","author":"Mou Chong","year":"2023","unstructured":"Chong Mou, Xintao Wang, Jiechong Song, Ying Shan, and Jian Zhang. 2023. Dragondiffusion: Enabling drag-style manipulation on diffusion models. arXiv preprint arXiv:2307.02421 (2023)."},{"key":"e_1_3_2_1_19_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_20_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_21_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 1, 2","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 1, 2 (2022), 3."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_24_1","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","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 35 (2022), 36479--36494.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_25_1","volume-title":"Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456","author":"Song Yang","year":"2020","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 preprint arXiv:2011.13456 (2020)."},{"key":"e_1_3_2_1_26_1","volume-title":"Effective data augmentation with diffusion models. arXiv preprint arXiv:2302.07944","author":"Trabucco Brandon","year":"2023","unstructured":"Brandon Trabucco, Kyle Doherty, Max Gurinas, and Ruslan Salakhutdinov. 2023. Effective data augmentation with diffusion models. arXiv preprint arXiv:2302.07944 (2023)."},{"key":"e_1_3_2_1_27_1","volume-title":"Smart: Syntax-calibrated multi-aspect relation transformer for change captioning","author":"Tu Yunbin","year":"2024","unstructured":"Yunbin Tu, Liang Li, Li Su, Zheng-Jun Zha, and Qingming Huang. 2024. Smart: Syntax-calibrated multi-aspect relation transformer for change captioning. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00706"},{"key":"e_1_3_2_1_30_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_31_1","volume-title":"Region and Boundary Aware Zero-shot Grounded Text-to-image Generation. arXiv preprint arXiv:2310.08872","author":"Xiao Jiayu","year":"2023","unstructured":"Jiayu Xiao, Liang Li, Henglei Lv, Shuhui Wang, and Qingming Huang. 2023. R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation. arXiv preprint arXiv:2310.08872 (2023)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01092"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"e_1_3_2_1_35_1","volume-title":"Zero-shot contrastive loss for text-guided diffusion image style transfer. arXiv preprint arXiv:2303.08622","author":"Yang Serin","year":"2023","unstructured":"Serin Yang, Hyunmin Hwang, and Jong Chul Ye. 2023. Zero-shot contrastive loss for text-guided diffusion image style transfer. arXiv preprint arXiv:2303.08622 (2023)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3432099"},{"key":"e_1_3_2_1_37_1","volume-title":"International Conference on Machine Learning. PMLR, 41164--41193","author":"Zhang Guanhua","year":"2023","unstructured":"Guanhua Zhang, Jiabao Ji, Yang Zhang, Mo Yu, Tommi Jaakkola, and Shiyu Chang. 2023. Towards coherent image inpainting using denoising diffusion implicit models. In International Conference on Machine Learning. PMLR, 41164--41193."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-1025-6"}],"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\/3664647.3680658","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680658","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:57Z","timestamp":1750295877000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680658"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":39,"alternative-id":["10.1145\/3664647.3680658","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680658","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"}}]}}