{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T02:07:25Z","timestamp":1778983645590,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T00:00:00Z","timestamp":1702512000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,14]]},"DOI":"10.1145\/3638884.3638906","type":"proceedings-article","created":{"date-parts":[[2024,4,23]],"date-time":"2024-04-23T12:11:26Z","timestamp":1713874286000},"page":"147-152","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Referring Image Harmonization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6871-204X","authenticated-orcid":false,"given":"Zhenghui","family":"Wang","sequence":"first","affiliation":[{"name":"Beijing University of Posts & Telecommunications, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4153-0695","authenticated-orcid":false,"given":"Xiaoxuan","family":"Fan","sequence":"additional","affiliation":[{"name":"State Grid Smart Grid Research Institute Co., Ltd, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6987-3648","authenticated-orcid":false,"given":"Zhuangzhuang","family":"Li","sequence":"additional","affiliation":[{"name":"State Grid Shandong Electric Power Research Institute, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4798-4233","authenticated-orcid":false,"given":"Fangxiang","family":"Feng","sequence":"additional","affiliation":[{"name":"Beijing University of Posts & Telecommunications, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0314-8951","authenticated-orcid":false,"given":"Xiaojie","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts & Telecommunications, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,4,23]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3260620"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428394"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00842"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"e_1_3_2_1_5_1","volume-title":"Transformer for Image Harmonization and Beyond","author":"Guo Zonghui","year":"2022","unstructured":"Zonghui Guo, Zhaorui Gu, Bing Zheng, Junyu Dong, and Haiyong Zheng. 2022. Transformer for Image Harmonization and Beyond. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01460"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01610"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01909"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings, Part I 14","author":"Hu Ronghang","year":"2016","unstructured":"Ronghang Hu, Marcus Rohrbach, and Trevor Darrell. 2016. Segmentation from natural language expressions. In Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14. Springer, 108\u2013124."},{"key":"e_1_3_2_1_10_1","volume-title":"Drag-and-drop pasting. ACM Transactions on graphics (TOG) 25, 3","author":"Jia Jiaya","year":"2006","unstructured":"Jiaya Jia, Jian Sun, Chi-Keung Tang, and Heung-Yeung Shum. 2006. Drag-and-drop pasting. ACM Transactions on graphics (TOG) 25, 3 (2006), 631\u2013637."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00479"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"e_1_3_2_1_14_1","volume-title":"The retinex theory of color vision. Scientific american 237, 6","author":"Land H","year":"1977","unstructured":"Edwin\u00a0H Land. 1977. The retinex theory of color vision. Scientific american 237, 6 (1977), 108\u2013129."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1364\/JOSA.61.000001"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00924"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1201775.882269"},{"key":"e_1_3_2_1_21_1","volume-title":"International conference on machine learning. PMLR, 8748\u20138763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748\u20138763."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/38.946629"},{"key":"e_1_3_2_1_23_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 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\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer, 234\u2013241."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00166"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.299"},{"key":"e_1_3_2_1_26_1","volume-title":"International Conference on Machine Learning. PMLR, 23318\u201323340","author":"Wang Peng","year":"2022","unstructured":"Peng Wang, An Yang, Rui Men, Junyang Lin, Shuai Bai, Zhikang Li, Jianxin Ma, Chang Zhou, Jingren Zhou, and Hongxia Yang. 2022. Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. In International Conference on Machine Learning. PMLR, 23318\u201323340."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548031"},{"key":"e_1_3_2_1_29_1","volume-title":"Understanding and improving the realism of image composites. ACM Transactions on graphics (TOG) 31, 4","author":"Xue Su","year":"2012","unstructured":"Su Xue, Aseem Agarwala, Julie Dorsey, and Holly Rushmeier. 2012. Understanding and improving the realism of image composites. ACM Transactions on graphics (TOG) 31, 4 (2012), 1\u201310."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"e_1_3_2_1_31_1","volume-title":"Towards Unifying Reference Expression Generation and Comprehension. arXiv preprint arXiv:2210.13076","author":"Zheng Duo","year":"2022","unstructured":"Duo Zheng, Tao Kong, Ya Jing, Jiaan Wang, and Xiaojie Wang. 2022. Towards Unifying Reference Expression Generation and Comprehension. arXiv preprint arXiv:2210.13076 (2022)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.449"}],"event":{"name":"ICCIP 2023: 2023 the 9th International Conference on Communication and Information Processing","location":"Lingshui China","acronym":"ICCIP 2023"},"container-title":["Proceedings of the 2023 9th International Conference on Communication and Information Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3638884.3638906","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3638884.3638906","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T01:46:53Z","timestamp":1778982413000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3638884.3638906"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,14]]},"references-count":32,"alternative-id":["10.1145\/3638884.3638906","10.1145\/3638884"],"URL":"https:\/\/doi.org\/10.1145\/3638884.3638906","relation":{},"subject":[],"published":{"date-parts":[[2023,12,14]]},"assertion":[{"value":"2024-04-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}