{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T07:20:46Z","timestamp":1781335246864,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":29,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62201526"],"award-info":[{"award-number":["62201526"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["CUC24SG015"],"award-info":[{"award-number":["CUC24SG015"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Research Foundation, Singapore","award":["NRFF Award NRF-NRFF13-2021-0008"],"award-info":[{"award-number":["NRFF Award NRF-NRFF13-2021-0008"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFF0902402"],"award-info":[{"award-number":["2022YFF0902402"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100004543","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\/3664647.3680830","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"6842-6850","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["MAG-Edit: Localized Image Editing in Complex Scenarios via Mask-Based Attention-Adjusted Guidance"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9362-6237","authenticated-orcid":false,"given":"Qi","family":"Mao","sequence":"first","affiliation":[{"name":"Communication University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7469-6730","authenticated-orcid":false,"given":"Lan","family":"Chen","sequence":"additional","affiliation":[{"name":"Communication University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7167-8766","authenticated-orcid":false,"given":"Yuchao","family":"Gu","sequence":"additional","affiliation":[{"name":"Show Lab, National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8165-3696","authenticated-orcid":false,"given":"Zhen","family":"Fang","sequence":"additional","affiliation":[{"name":"Communication University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7681-2166","authenticated-orcid":false,"given":"Mike Zheng","family":"Shou","sequence":"additional","affiliation":[{"name":"Show Lab, National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","article-title":"Blended Latent Diffusion","volume":"42","author":"Avrahami Omri","year":"2023","unstructured":"Omri Avrahami, Ohad Fried, and Dani Lischinski. 2023. Blended Latent Diffusion. Association for Computing Machinery Trans. Graph., Vol. 42, 4 (2023), 149:1--149:11.","journal-title":"Association for Computing Machinery Trans. Graph."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2304.03373"},{"key":"e_1_3_2_1_7_1","volume-title":"International Conference on Learning Representations. 1--22","author":"Couairon Guillaume","year":"2023","unstructured":"Guillaume Couairon, Jakob Verbeek, Holger Schwenk, and Matthieu Cord. 2023. Diffedit: Diffusion-based semantic image editing with mask guidance. In International Conference on Learning Representations. 1--22."},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Learning Representations. 1--36","author":"Hertz Amir","year":"2023","unstructured":"Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, and Daniel Cohen-Or. 2023. Prompt-to-prompt image editing with cross attention control. In International Conference on Learning Representations. 1--36."},{"key":"e_1_3_2_1_9_1","volume-title":"PFB-Diff: Progressive Feature Blending Diffusion for Text-driven Image Editing. arXiv preprint arXiv:2306.16894","author":"Huang Wenjing","year":"2023","unstructured":"Wenjing Huang, Shikui Tu, and Lei Xu. 2023. PFB-Diff: Progressive Feature Blending Diffusion for Text-driven Image Editing. arXiv preprint arXiv:2306.16894 (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"International Conference on Learning Representations (ICLR)","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 (ICLR) (2024)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"e_1_3_2_1_12_1","volume-title":"Qibin Hou, Yaxing Wang, and Jian Yang.","author":"Li Senmao","year":"2023","unstructured":"Senmao Li, Joost van de Weijer, Taihang Hu, Fahad Shahbaz Khan, Qibin Hou, Yaxing Wang, and Jian Yang. 2023. StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing. arXiv preprint arXiv:2303.15649 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models. arXiv preprint arXiv:2305.16807","author":"Miyake Daiki","year":"2023","unstructured":"Daiki Miyake, Akihiro Iohara, Yu Saito, and Toshiyuki Tanaka. 2023. Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models. arXiv preprint arXiv:2305.16807 (2023)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"e_1_3_2_1_15_1","volume-title":"Richard Zhang, Yijun Li, Jingwan Lu, and Jun-Yan Zhu.","author":"Parmar Gaurav","year":"2023","unstructured":"Gaurav Parmar, Krishna Kumar Singh, Richard Zhang, Yijun Li, Jingwan Lu, and Jun-Yan Zhu. 2023. Zero-shot image-to-image translation. In Special Interest Group on Computer Graphics and Interactive Techniques. 1--11."},{"key":"e_1_3_2_1_16_1","volume-title":"Grounded text-to-image synthesis with attention refocusing. arXiv preprint arXiv:2306.05427","author":"Phung Quynh","year":"2023","unstructured":"Quynh Phung, Songwei Ge, and Jia-Bin Huang. 2023. Grounded text-to-image synthesis with attention refocusing. arXiv preprint arXiv:2306.05427 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"International Conference on Machine Learning. 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. 8748--8763."},{"key":"e_1_3_2_1_18_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_19_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Rassin Royi","year":"2024","unstructured":"Royi Rassin, Eran Hirsch, Daniel Glickman, Shauli Ravfogel, Yoav Goldberg, and Gal Chechik. 2024. Linguistic binding in diffusion models: Enhancing attribute correspondence through attention map alignment. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_22_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. In Neural Information Processing Systems, Vol. 35. 36479--36494.","journal-title":"Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","volume-title":"International Conference on Learning Representations. 1--20","author":"Song Jiaming","year":"2021","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2021. Denoising diffusion implicit models. In International Conference on Learning Representations. 1--20."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01048"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"e_1_3_2_1_26_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. 2023. InstructEdit: Improving Automatic Masks for Diffusion-based Image Editing With User Instructions. arXiv preprint arXiv:2305.18047 (2023)."},{"key":"e_1_3_2_1_27_1","volume-title":"BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion. In International Conference on Computer Vision. 7452--7461","author":"Xie Jinheng","year":"2023","unstructured":"Jinheng Xie, Yuexiang Li, Yawen Huang, Haozhe Liu, Wentian Zhang, Yefeng Zheng, and Mike Zheng Shou. 2023. BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion. In International Conference on Computer Vision. 7452--7461."},{"key":"e_1_3_2_1_28_1","unstructured":"Kai Zhang Lingbo Mo Wenhu Chen Huan Sun and Yu Su. 2023. MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing. In Neural Information Processing Systems."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00584"}],"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\/3664647.3680830","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680830","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:07Z","timestamp":1750295887000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680830"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":29,"alternative-id":["10.1145\/3664647.3680830","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680830","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"}}]}}