{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:03Z","timestamp":1750309503352,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":45,"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-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["No. NRF- 2022R1A4A1023248 and No. RS-2023-00209794"],"award-info":[{"award-number":["No. NRF- 2022R1A4A1023248 and No. RS-2023-00209794"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100003725","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\/3664647.3681662","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"3275-3283","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DAFT-GAN: Dual Affine Transformation Generative Adversarial Network for Text-Guided Image Inpainting"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6665-3739","authenticated-orcid":false,"given":"Jihoon","family":"Lee","sequence":"first","affiliation":[{"name":"School of Electronic and Electrical Engineering, Kyungpook National University, Daegu, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0657-5733","authenticated-orcid":false,"given":"Yunhong","family":"Min","sequence":"additional","affiliation":[{"name":"School of Electronics Engineering, Kyungpook National University, Daegu, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7824-2460","authenticated-orcid":false,"given":"Hwidong","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Electronics Engineering, Kyungpook National University, Daegu, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9487-5649","authenticated-orcid":false,"given":"Sangtae","family":"Ahn","sequence":"additional","affiliation":[{"name":"School of Electronic and Electrical Engineering, Kyungpook National University, Daegu, Republic of Korea"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Demystifying mmd gans. arXiv preprint arXiv:1801.01401","author":"Bi'nkowski Miko\u0142aj","year":"2018","unstructured":"Miko\u0142aj Bi'nkowski, Danica J Sutherland, Michael Arbel, and Arthur Gretton. 2018. Demystifying mmd gans. arXiv preprint arXiv:1801.01401 (2018)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2004.833105"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185578"},{"key":"e_1_3_2_1_4_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073659"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1186822.1073263"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.11.074"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00778"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01049"},{"key":"e_1_3_2_1_10_1","volume-title":"GLIGEN: Open-Set Grounded Text-to-Image Generation. CVPR","author":"Li Yuheng","year":"2023","unstructured":"Yuheng Li, Haotian Liu, Qingyang Wu, Fangzhou Mu, Jianwei Yang, Jianfeng Gao, Chunyuan Li, and Yong Jae Lee. 2023. GLIGEN: Open-Set Grounded Text-to-Image Generation. CVPR (2023)."},{"key":"e_1_3_2_1_11_1","volume-title":"Sketch guided and progressive growing GAN for realistic and editable ultrasound image synthesis. Medical image analysis","author":"Liang Jiamin","year":"2022","unstructured":"Jiamin Liang, Xin Yang, Yuhao Huang, Haoming Li, Shuangchi He, Xindi Hu, Zejian Chen, Wufeng Xue, Jun Cheng, and Dong Ni. 2022. Sketch guided and progressive growing GAN for realistic and editable ultrasound image synthesis. Medical image analysis, Vol. 79 (2022), 102461."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01765"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413982"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00427"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00925"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Yuqing Ma Xianglong Liu Shihao Bai Lei Wang Dailan He and Aishan Liu. 2019. Coarse-to-Fine Image Inpainting via Region-wise Convolutions and Non-Local Correlation.. In Ijcai. 3123--3129.","DOI":"10.24963\/ijcai.2019\/433"},{"key":"e_1_3_2_1_18_1","volume-title":"Edgeconnect: Generative image inpainting with adversarial edge learning. arXiv","author":"Nazeri K","year":"2020","unstructured":"K Nazeri, E Ng, T Joseph, FZ Qureshi, and M Ebrahimi. 2020. Edgeconnect: Generative image inpainting with adversarial edge learning. arXiv 2019. arXiv preprint arXiv:1901.00212 (2020)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01363"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"e_1_3_2_1_21_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_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-010-0601-4"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_24_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention--MICCAI 2015: 18th international conference","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention--MICCAI 2015: 18th international conference, Munich, Germany, October 5--9, 2015, proceedings, part III 18. Springer, 234--241."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_1"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00465"},{"key":"e_1_3_2_1_29_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, Vol. 13, 4 (2004), 600--612."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109961"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_1"},{"key":"e_1_3_2_1_33_1","volume-title":"Recurrent affine transformation for text-to-image synthesis","author":"Ye Senmao","year":"2023","unstructured":"Senmao Ye, Huan Wang, Mingkui Tan, and Fei Liu. 2023. Recurrent affine transformation for text-to-image synthesis. IEEE Transactions on Multimedia (2023)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00457"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475436"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3156949"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01390"},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings, Part XIX 16","author":"Zeng Yu","year":"2020","unstructured":"Yu Zeng, Zhe Lin, Jimei Yang, Jianming Zhang, Eli Shechtman, and Huchuan Lu. 2020. High-resolution image inpainting with iterative confidence feedback and guided upsampling. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XIX 16. Springer, 1--17."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414017"},{"key":"e_1_3_2_1_41_1","volume-title":"Large scale image completion via co-modulated generative adversarial networks. arXiv preprint arXiv:2103.10428","author":"Zhao Shengyu","year":"2021","unstructured":"Shengyu Zhao, Jonathan Cui, Yilun Sheng, Yue Dong, Xiao Liang, Eric I Chang, and Yan Xu. 2021. Large scale image completion via co-modulated generative adversarial networks. arXiv preprint arXiv:2103.10428 (2021)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00153"},{"key":"e_1_3_2_1_43_1","volume-title":"Tfill: Image completion via a transformer-based architecture. arXiv preprint arXiv:2104.00845","author":"Zheng Chuanxia","year":"2021","unstructured":"Chuanxia Zheng, Tat-Jen Cham, and Jianfei Cai. 2021. Tfill: Image completion via a transformer-based architecture. arXiv preprint arXiv:2104.00845, Vol. 2, 3 (2021), 6."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_16"},{"key":"e_1_3_2_1_45_1","volume-title":"Improving cross-modal alignment for text-guided image inpainting. arXiv preprint arXiv:2301.11362","author":"Zhou Yucheng","year":"2023","unstructured":"Yucheng Zhou and Guodong Long. 2023. Improving cross-modal alignment for text-guided image inpainting. arXiv preprint arXiv:2301.11362 (2023). gr"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681662","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681662","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:50Z","timestamp":1750295870000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681662"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":45,"alternative-id":["10.1145\/3664647.3681662","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681662","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"}}]}}