{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:09:55Z","timestamp":1765343395168,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","funder":[{"name":"This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT)","award":["No.RS-2022-II220907"],"award-info":[{"award-number":["No.RS-2022-II220907"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754711","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:55Z","timestamp":1761377215000},"page":"9277-9286","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Focus Where It Matters: LLM-Guided Regional Identification for Instruction-based Image Editing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3756-8524","authenticated-orcid":false,"given":"Minho","family":"Park","sequence":"first","affiliation":[{"name":"Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea and Korea Advanced Institute of Science & Technology, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1647-4638","authenticated-orcid":false,"given":"Young Joo","family":"Jo","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7181-6291","authenticated-orcid":false,"given":"Jae-Hyeok","family":"Lee","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8927-6657","authenticated-orcid":false,"given":"Ji Yong","family":"Lee","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1308-0172","authenticated-orcid":false,"given":"Dong-oh","family":"Kang","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5306-6853","authenticated-orcid":false,"given":"Yong Man","family":"Ro","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science & Technology, Daejeon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katherine Millican Malcolm Reynolds et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems Vol. 35 (2022) 23716-23736.","key":"e_1_3_2_1_1_1"},{"unstructured":"Yogesh Balaji Seungjun Nah Xun Huang Arash Vahdat Jiaming Song Qinsheng Zhang Karsten Kreis Miika Aittala Timo Aila Samuli Laine et al. 2022. ediff-i: Text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022).","key":"e_1_3_2_1_2_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_3_1","DOI":"10.1109\/CVPR52729.2023.01764"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_4_1","DOI":"10.1109\/CVPR.2018.00132"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_5_1","DOI":"10.1109\/ICCV51070.2023.02062"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_6_1","DOI":"10.1109\/CVPR.2014.254"},{"key":"e_1_3_2_1_7_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_8_1","volume-title":"Diffusion models beat gans on image synthesis. Advances in neural information processing systems","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, Vol. 34 (2021), 8780-8794."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_9_1","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"e_1_3_2_1_10_1","volume-title":"Yinfei Yang, and Zhe Gan.","author":"Fu Tsu-Jui","year":"2023","unstructured":"Tsu-Jui Fu, Wenze Hu, Xianzhi Du, William Yang Wang, Yinfei Yang, and Zhe Gan. 2023. Guiding instruction-based image editing via multimodal large language models. arXiv preprint arXiv:2309.17102 (2023)."},{"key":"e_1_3_2_1_11_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)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_12_1","DOI":"10.1109\/CVPR52733.2024.01208"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_13_1","DOI":"10.1109\/CVPR52733.2024.00667"},{"key":"e_1_3_2_1_14_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_15_1","volume-title":"Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_16_1","DOI":"10.1109\/ICPR.2010.579"},{"key":"e_1_3_2_1_17_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"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_18_1","DOI":"10.1109\/CVPR52733.2024.00799"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_19_1","DOI":"10.1109\/CVPR52729.2023.00582"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_20_1","DOI":"10.3115\/v1\/D14-1086"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_21_1","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_22_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. 2023. 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"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_23_1","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"e_1_3_2_1_24_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."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_25_1","DOI":"10.1109\/CVPR52733.2024.00598"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_26_1","DOI":"10.1109\/CVPR52733.2024.00674"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_27_1","DOI":"10.1109\/CVPR52729.2023.02259"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_28_1","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_2_1_29_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. 2023b. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2023), 34892-34916."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_30_1","DOI":"10.1109\/CVPR42600.2020.01005"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_31_1","DOI":"10.1109\/CVPR.2016.9"},{"key":"e_1_3_2_1_32_1","volume-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073","author":"Meng Chenlin","year":"2021","unstructured":"Chenlin Meng, Yutong He, Yang Song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, and Stefano Ermon. 2021. Sdedit: Guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073 (2021)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_33_1","DOI":"10.1109\/CVPR52729.2023.00585"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_34_1","DOI":"10.1109\/ICCV.2017.534"},{"key":"e_1_3_2_1_35_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_36_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_37_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."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_38_1","DOI":"10.1109\/CVPR52729.2023.00690"},{"key":"e_1_3_2_1_39_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."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_40_1","DOI":"10.1109\/CVPR52688.2022.01042"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_41_1","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_42_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."},{"unstructured":"Christoph Schuhmann Romain Beaumont Richard Vencu Cade Gordon Ross Wightman Mehdi Cherti Theo Coombes Aarush Katta Clayton Mullis Mitchell Wortsman et al. 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in neural information processing systems Vol. 35 (2022) 25278-25294.","key":"e_1_3_2_1_43_1"},{"key":"e_1_3_2_1_44_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_45_1","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"e_1_3_2_1_46_1","first-page":"41693","article-title":"Raphael: Text-to-image generation via large mixture of diffusion paths","volume":"36","author":"Xue Zeyue","year":"2023","unstructured":"Zeyue Xue, Guanglu Song, Qiushan Guo, Boxiao Liu, Zhuofan Zong, Yu Liu, and Ping Luo. 2023. Raphael: Text-to-image generation via large mixture of diffusion paths. Advances in Neural Information Processing Systems, Vol. 36 (2023), 41693-41706.","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_47_1","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"e_1_3_2_1_48_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. 2023. 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"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_49_1","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_50_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)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_51_1","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"e_1_3_2_1_52_1","volume-title":"Segment everything everywhere all at once. Advances in neural information processing systems","author":"Zou Xueyan","year":"2023","unstructured":"Xueyan Zou, Jianwei Yang, Hao Zhang, Feng Li, Linjie Li, Jianfeng Wang, Lijuan Wang, Jianfeng Gao, and Yong Jae Lee. 2023b. Segment everything everywhere all at once. Advances in neural information processing systems, Vol. 36 (2023), 19769-19782."}],"event":{"sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"acronym":"MM '25","name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754711","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:06:04Z","timestamp":1765343164000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754711"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":52,"alternative-id":["10.1145\/3746027.3754711","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754711","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"}}]}}