{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:15:01Z","timestamp":1765340101187,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","funder":[{"name":"Shanghai Pujiang Programme","award":["24PJD030"],"award-info":[{"award-number":["24PJD030"]}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["25ZR1402138"],"award-info":[{"award-number":["25ZR1402138"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755429","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:47:18Z","timestamp":1761374838000},"page":"10132-10141","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Prompt-Softbox-Prompt: A Free-Text Embedding Control for Image Editing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5855-7248","authenticated-orcid":false,"given":"Yitong","family":"Yang","sequence":"first","affiliation":[{"name":"Shanghai University of Finance and Economics, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0276-5029","authenticated-orcid":false,"given":"Yinglin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computing and Aritificial Intelligence, Shanghai University of Finance and Economics, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9507-3049","authenticated-orcid":false,"given":"Tian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai University of Finance and Economics, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3941-2147","authenticated-orcid":false,"given":"Jing","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai University of Finance and Economics, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1582-5684","authenticated-orcid":false,"given":"Shuting","family":"He","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Interdisciplinary Research of Computation and Economics, Shanghai University of Finance and Economics, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657423"},{"key":"e_1_3_2_1_2_1","unstructured":"James Betker Gabriel Goh Li Jing Tim Brooks Jianfeng Wang Linjie Li Long Ouyang Juntang Zhuang Joyce Lee Yufei Guo et al. 2023. Improving image generation with better captions. Computer Science. https:\/\/cdn. openai. com\/papers\/dall-e-3. pdf Vol. 2 3 (2023) 8."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_2_1_4_1","volume-title":"Colorpeel: Color prompt learning with diffusion models via color and shape disentanglement. In European Conference on Computer Vision","author":"Butt Muhammad Atif","year":"2024","unstructured":"Muhammad Atif Butt, Kai Wang, Javier Vazquez-Corral, and Joost van de Weijer. 2024. Colorpeel: Color prompt learning with diffusion models via color and shape disentanglement. In European Conference on Computer Vision. Springer, 456-472."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00385"},{"key":"e_1_3_2_1_7_1","volume-title":"Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models. ACM transactions on Graphics (TOG)","author":"Chefer Hila","year":"2023","unstructured":"Hila Chefer, Yuval Alaluf, Yael Vinker, Lior Wolf, and Daniel Cohen-Or. 2023. Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models. ACM transactions on Graphics (TOG), Vol. 42, 4 (2023), 1-10."},{"key":"e_1_3_2_1_8_1","volume-title":"Enhancing Prompt Following with Visual Control Through Training-Free Mask-Guided Diffusion. arXiv preprint arXiv:2404.14768","author":"Chen Hongyu","year":"2024","unstructured":"Hongyu Chen, Yiqi Gao, Min Zhou, Peng Wang, Xubin Li, Tiezheng Ge, and Bo Zheng. 2024a. Enhancing Prompt Following with Visual Control Through Training-Free Mask-Guided Diffusion. arXiv preprint arXiv:2404.14768 (2024)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"e_1_3_2_1_12_1","volume-title":"Diffedit: Diffusion-based semantic image editing with mask guidance. arXiv preprint arXiv:2210.11427","author":"Couairon Guillaume","year":"2022","unstructured":"Guillaume Couairon, Jakob Verbeek, Holger Schwenk, and Matthieu Cord. 2022. Diffedit: Diffusion-based semantic image editing with mask guidance. arXiv preprint arXiv:2210.11427 (2022)."},{"key":"e_1_3_2_1_13_1","volume-title":"European Conference on Computer Vision. Springer, 432-449","author":"Duan Yiquan","year":"2024","unstructured":"Yiquan Duan, Xianda Guo, and Zheng Zhu. 2024. Diffusiondepth: Diffusion denoising approach for monocular depth estimation. In European Conference on Computer Vision. Springer, 432-449."},{"key":"e_1_3_2_1_14_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_15_1","volume-title":"Highly personalized text embedding for image manipulation by stable diffusion. arXiv preprint arXiv:2303.08767","author":"Han Inhwa","year":"2023","unstructured":"Inhwa Han, Serin Yang, Taesung Kwon, and Jong Chul Ye. 2023. Highly personalized text embedding for image manipulation by stable diffusion. arXiv preprint arXiv:2303.08767 (2023)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28690"},{"key":"e_1_3_2_1_17_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_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"e_1_3_2_1_19_1","volume-title":"Training-and-prompt-free General Painterly Harmonization Using Image-wise Attention Sharing. arXiv preprint arXiv:2404.12900","author":"Hsiao Teng-Fang","year":"2024","unstructured":"Teng-Fang Hsiao, Bo-Kai Ruan, and Hong-Han Shuai. 2024. Training-and-prompt-free General Painterly Harmonization Using Image-wise Attention Sharing. arXiv preprint arXiv:2404.12900 (2024)."},{"key":"e_1_3_2_1_20_1","volume-title":"International Conference on Learning Representations","author":"Ju Xuan","year":"2024","unstructured":"Xuan Ju, Ailing Zeng, Yuxuan Bian, Shaoteng Liu, and Qiang Xu. 2024. PnP Inversion: Boosting Diffusion-based Editing with 3 Lines of Code. International Conference on Learning Representations (2024)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_23_1","unstructured":"Black Forest Labs. 2024. FLUX. https:\/\/huggingface.co\/black-forest-labs\/FLUX.1-Fill-dev."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00194"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.10308948"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"e_1_3_2_1_27_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_28_1","first-page":"285","article-title":"A threshold selection method from gray-level histograms","volume":"11","author":"Nobuyuki Otsu","year":"1975","unstructured":"Nobuyuki Otsu et al., 1975. A threshold selection method from gray-level histograms. Automatica, Vol. 11, 285-296 (1975), 23-27.","journal-title":"Automatica"},{"key":"e_1_3_2_1_29_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_30_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_31_1","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research, Vol. 21, 140 (2020), 1-67.","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01110"},{"key":"e_1_3_2_1_33_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_34_1","volume-title":"International conference on machine learning. PMLR, 1060-1069","author":"Reed Scott","year":"2016","unstructured":"Scott Reed, Zeynep Akata, Xinchen Yan, Lajanugen Logeswaran, Bernt Schiele, and Honglak Lee. 2016. Generative adversarial text to image synthesis. In International conference on machine learning. PMLR, 1060-1069."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_37_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 (2022), 36479-36494."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"e_1_3_2_1_39_1","volume-title":"Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658157"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"e_1_3_2_1_42_1","volume-title":"Instructedit: Improving automatic masks for diffusion-based image editing with user instructions. arXiv preprint arXiv:2305.18047","author":"Wang Qian","year":"2023","unstructured":"Qian Wang, Biao Zhang, Michael Birsak, and Peter Wonka. 2023b. Instructedit: Improving automatic masks for diffusion-based image editing with user instructions. arXiv preprint arXiv:2305.18047 (2023)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01761"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00706"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00820"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00748"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"e_1_3_2_1_52_1","first-page":"26291","article-title":"Dynamic prompt learning: Addressing cross-attention leakage for text-based image editing","volume":"36","author":"Yang Fei","year":"2023","unstructured":"Fei Yang, Shiqi Yang, Muhammad Atif Butt, Joost van de Weijer, et al., 2023b. Dynamic prompt learning: Addressing cross-attention leakage for text-based image editing. Advances in Neural Information Processing Systems, Vol. 36 (2023), 26291-26303.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_53_1","volume-title":"Uncovering the Text Embedding in Text-to-Image Diffusion Models. arXiv preprint arXiv:2404.01154","author":"Yu Hu","year":"2024","unstructured":"Hu Yu, Hao Luo, Fan Wang, and Feng Zhao. 2024. Uncovering the Text Embedding in Text-to-Image Diffusion Models. arXiv preprint arXiv:2404.01154 (2024)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_57_1","volume-title":"ObjectAdd: Adding Objects into Image via a Training-Free Diffusion Modification Fashion. arXiv preprint arXiv:2404.17230","author":"Zhang Ziyue","year":"2024","unstructured":"Ziyue Zhang, Mingbao Lin, and Rongrong Ji. 2024. ObjectAdd: Adding Objects into Image via a Training-Free Diffusion Modification Fashion. arXiv preprint arXiv:2404.17230 (2024)."},{"key":"e_1_3_2_1_58_1","volume-title":"StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation. arXiv preprint arXiv:2405.01434","author":"Zhou Yupeng","year":"2024","unstructured":"Yupeng Zhou, Daquan Zhou, Ming-Ming Cheng, Jiashi Feng, and Qibin Hou. 2024. StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation. arXiv preprint arXiv:2405.01434 (2024)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755429","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:11:25Z","timestamp":1765339885000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755429"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":58,"alternative-id":["10.1145\/3746027.3755429","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755429","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}