{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:21:08Z","timestamp":1765340468657,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","funder":[{"name":"The National Natural ScienceFoundation of China","award":["No.62402306"],"award-info":[{"award-number":["No.62402306"]}]},{"name":"The Natural Science Foundation of Shanghai","award":["No.24ZR1422400"],"award-info":[{"award-number":["No.24ZR1422400"]}]},{"name":"2024 CCF-BAIDU OPEN FUND","award":["CCF-BAIDU OF202424"],"award-info":[{"award-number":["CCF-BAIDU OF202424"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754926","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:47:18Z","timestamp":1761374838000},"page":"9509-9518","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["EditMaster: Bridging Text instruction and Visual Example for Multimodal guided Image Editing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3219-5779","authenticated-orcid":false,"given":"Jiahui","family":"Zhang","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7281-2812","authenticated-orcid":false,"given":"Mengtian","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China and Fudan University, Shang hai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8711-4866","authenticated-orcid":false,"given":"Jiewei","family":"Tang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6313-7378","authenticated-orcid":false,"given":"Junyu","family":"Deng","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4739-3065","authenticated-orcid":false,"given":"Siyu","family":"Tian","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7261-0454","authenticated-orcid":false,"given":"Xiang","family":"Liu","sequence":"additional","affiliation":[{"name":"New York University Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2174-3629","authenticated-orcid":false,"given":"Meng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4973-7942","authenticated-orcid":false,"given":"Guangnan","family":"Ye","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1907-8567","authenticated-orcid":false,"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Fudan University, 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","unstructured":"Jinze Bai Shuai Bai Shusheng Yang Shijie Wang Sinan Tan Peng Wang Junyang Lin Chang Zhou and Jingren Zhou. 2023. Qwen-VL: A Versatile Vision-Language Model for Understanding Localization Text Reading and Beyond. arXiv:2308.12966 [cs.CV] https:\/\/arxiv.org\/abs\/2308.12966"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2669"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01391"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00454"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"key":"e_1_3_2_1_10_1","volume-title":"Freeedit: Mask-free reference-based image editing with multi-modal instruction. arXiv preprint arXiv:2409.18071","author":"He Runze","year":"2024","unstructured":"Runze He, Kai Ma, Linjiang Huang, Shaofei Huang, Jialin Gao, Xiaoming Wei, Jiao Dai, Jizhong Han, and Si Liu. 2024. Freeedit: Mask-free reference-based image editing with multi-modal instruction. arXiv preprint arXiv:2409.18071 (2024)."},{"key":"e_1_3_2_1_11_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_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"e_1_3_2_1_13_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840-6851."},{"key":"e_1_3_2_1_14_1","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2022. Lora: Low-rank adaptation of large language models. ICLR, Vol. 1, 2 (2022), 3.","journal-title":"ICLR"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00455"},{"key":"e_1_3_2_1_16_1","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems.","author":"Hu Minghui","year":"2023","unstructured":"Minghui Hu, Jianbin Zheng, Daqing Liu, Chuanxia Zheng, Chaoyue Wang, Dacheng Tao, and Tat-Jen Cham. 2023. Cocktail: Mixing multi-modality control for text-conditional image generation. In Thirty-seventh Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_17_1","volume-title":"Composer: Creative and controllable image synthesis with composable conditions. arXiv preprint arXiv:2302.09778","author":"Huang Lianghua","year":"2023","unstructured":"Lianghua Huang, Di Chen, Yu Liu, Yujun Shen, Deli Zhao, and Jingren Zhou. 2023. Composer: Creative and controllable image synthesis with composable conditions. arXiv preprint arXiv:2302.09778 (2023)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00799"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"e_1_3_2_1_20_1","first-page":"21487","article-title":"Generating images with multimodal language models","volume":"36","author":"Koh Jing Yu","year":"2023","unstructured":"Jing Yu Koh, Daniel Fried, and Russ R Salakhutdinov. 2023a. Generating images with multimodal language models. Advances in Neural Information Processing Systems, Vol. 36 (2023), 21487-21506.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_21_1","volume-title":"International Conference on Machine Learning. PMLR, 17283-17300","author":"Koh Jing Yu","year":"2023","unstructured":"Jing Yu Koh, Ruslan Salakhutdinov, and Daniel Fried. 2023b. Grounding language models to images for multimodal inputs and outputs. In International Conference on Machine Learning. PMLR, 17283-17300."},{"key":"e_1_3_2_1_22_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00598"},{"key":"e_1_3_2_1_24_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2023), 34892-34916."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00644"},{"key":"e_1_3_2_1_26_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"e_1_3_2_1_28_1","unstructured":"Maxime Oquab Timoth\u00e9e Darcet Th\u00e9o Moutakanni Huy Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby et al. 2023. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"Kosmos-2: Grounding multimodal large language models to the world. arXiv preprint arXiv:2306.14824","author":"Peng Zhiliang","year":"2023","unstructured":"Zhiliang Peng, Wenhui Wang, Li Dong, Yaru Hao, Shaohan Huang, Shuming Ma, and Furu Wei. 2023. Kosmos-2: Grounding multimodal large language models to the world. arXiv preprint arXiv:2306.14824 (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","unstructured":"Nikhila Ravi Valentin Gabeur Yuan-Ting Hu Ronghang Hu Chaitanya Ryali Tengyu Ma Haitham Khedr Roman R\u00e4dle Chloe Rolland Laura Gustafson et al. 2024. Sam 2: Segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00847"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00844"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00621"},{"key":"e_1_3_2_1_36_1","first-page":"107984","article-title":"Yolov10: Real-time end-to-end object detection","volume":"37","author":"Wang Ao","year":"2024","unstructured":"Ao Wang, Hui Chen, Lihao Liu, Kai Chen, Zijia Lin, Jungong Han, et al., 2024b. Yolov10: Real-time end-to-end object detection. Advances in Neural Information Processing Systems, Vol. 37 (2024), 107984-108011.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_37_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 2024a. Qwen2-vl: Enhancing vision-language model's perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612200"},{"key":"e_1_3_2_1_40_1","volume-title":"TICondition: Expanding Control Capabilities for Text-to-Image Generation with Multi-Modal Conditions. In International Conference on Multimedia Modeling. Springer, 66-79","author":"Yang Yuhang","year":"2024","unstructured":"Yuhang Yang, Xiao Yan, and Sanyuan Zhang. 2024. TICondition: Expanding Control Capabilities for Text-to-Image Generation with Multi-Modal Conditions. In International Conference on Multimedia Modeling. Springer, 66-79."},{"key":"e_1_3_2_1_41_1","volume-title":"AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea. arXiv preprint arXiv:2411.15738","author":"Yu Qifan","year":"2024","unstructured":"Qifan Yu, Wei Chow, Zhongqi Yue, Kaihang Pan, Yang Wu, Xiaoyang Wan, Juncheng Li, Siliang Tang, Hanwang Zhang, and Yueting Zhuang. 2024. AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea. arXiv preprint arXiv:2411.15738 (2024)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00883"},{"key":"e_1_3_2_1_43_1","first-page":"31428","article-title":"Magicbrush: A manually annotated dataset for instruction-guided image editing","volume":"36","author":"Zhang Kai","year":"2023","unstructured":"Kai Zhang, Lingbo Mo, Wenhu Chen, Huan Sun, and Yu Su. 2023a. Magicbrush: A manually annotated dataset for instruction-guided image editing. Advances in Neural Information Processing Systems, Vol. 36 (2023), 31428-31449.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_45_1","first-page":"3058","article-title":"UltraEdit: Instruction-based fine-grained image editing at scale","volume":"37","author":"Zhao Haozhe","year":"2024","unstructured":"Haozhe Zhao, Xiaojian Shawn Ma, Liang Chen, Shuzheng Si, Rujie Wu, Kaikai An, Peiyu Yu, Minjia Zhang, Qing Li, and Baobao Chang. 2024. UltraEdit: Instruction-based fine-grained image editing at scale. Advances in Neural Information Processing Systems, Vol. 37 (2024), 3058-3093.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_46_1","first-page":"11127","article-title":"Uni-controlnet: All-in-one control to text-to-image diffusion models","volume":"36","author":"Zhao Shihao","year":"2023","unstructured":"Shihao Zhao, Dongdong Chen, Yen-Chun Chen, Jianmin Bao, Shaozhe Hao, Lu Yuan, and Kwan-Yee K Wong. 2023. Uni-controlnet: All-in-one control to text-to-image diffusion models. Advances in Neural Information Processing Systems, Vol. 36 (2023), 11127-11150.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_1_48_1","volume-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592","author":"Zhu Deyao","year":"2023","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)."}],"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\/3746027.3754926","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:18:43Z","timestamp":1765340323000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754926"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":48,"alternative-id":["10.1145\/3746027.3754926","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754926","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"}}]}}