{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T16:45:35Z","timestamp":1783010735002,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Natural Science Foundation of the Jiangsu Higher Education Institutions of China","award":["No. 20KJA520006"],"award-info":[{"award-number":["No. 20KJA520006"]}]},{"name":"National Natural Science Foundation of China","award":["Nos. 62176116, 62276136"],"award-info":[{"award-number":["Nos. 62176116, 62276136"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611747","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"1422-1430","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["Hierarchical Dynamic Image Harmonization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6637-8741","authenticated-orcid":false,"given":"Haoxing","family":"Chen","sequence":"first","affiliation":[{"name":"Nanjing University & Ant Group, Nanjing & Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2102-2693","authenticated-orcid":false,"given":"Zhangxuan","family":"Gu","sequence":"additional","affiliation":[{"name":"Ant Group, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6732-4961","authenticated-orcid":false,"given":"Yaohui","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0921-0613","authenticated-orcid":false,"given":"Jun","family":"Lan","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8992-9833","authenticated-orcid":false,"given":"Changhua","family":"Meng","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6159-619X","authenticated-orcid":false,"given":"Weiqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0395-1525","authenticated-orcid":false,"given":"Huaxiong","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"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":"crossref","unstructured":"Yingjie Cai Xuesong Chen Chao Zhang Kwan-Yee Lin Xiaogang Wang and Hongsheng Li. 2021. Semantic scene completion via integrating instances and scene in-the-loop. In CVPR. 324--333.","DOI":"10.1109\/CVPR46437.2021.00039"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Jin Chen Xijun Wang Zichao Guo Xiangyu Zhang and Jian Sun. 2021. Dynamic region-aware convolution. In CVPR. 8064--8073.","DOI":"10.1109\/CVPR46437.2021.00797"},{"key":"e_1_3_2_1_4_1","volume-title":"Dense Pixel-to-Pixel Harmonization via Continuous Image Representation. arXiv preprint arXiv:2303.01681","author":"Chen Jianqi","year":"2023","unstructured":"Jianqi Chen, Yilan Zhang, Zhengxia Zou, Keyan Chen, and Zhenwei Shi. 2023. Dense Pixel-to-Pixel Harmonization via Continuous Image Representation. arXiv preprint arXiv:2303.01681 (2023)."},{"key":"e_1_3_2_1_5_1","volume-title":"Bargainnet: Background-Guided Domain Translation for Image Harmonization. In ICME. 1--6.","author":"Cong Wenyan","year":"2021","unstructured":"Wenyan Cong, Li Niu, Jianfu Zhang, Jing Liang, and Liqing Zhang. 2021. Bargainnet: Background-Guided Domain Translation for Image Harmonization. In ICME. 1--6."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Wenyan Cong Xinhao Tao Li Niu Jing Liang Xuesong Gao Qihao Sun and Liqing Zhang. 2022. High-Resolution Image Harmonization via Collaborative Dual Transformations. In CVPR. 18470--18479.","DOI":"10.1109\/CVPR52688.2022.01792"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Wenyan Cong Jianfu Zhang Li Niu Liu Liu Zhixin Ling Weiyuan Li and Liqing Zhang. 2020. DoveNet: Deep Image Harmonization via Domain Verification. In CVPR. 8391--8400.","DOI":"10.1109\/CVPR42600.2020.00842"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2975979"},{"key":"e_1_3_2_1_9_1","unstructured":"Ian J. Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron C. Courville and Yoshua Bengio. 2014. Generative Adversarial Nets. In NeurIPS. 2672--2680."},{"key":"e_1_3_2_1_10_1","volume-title":"DiffusionInst: Diffusion Model for Instance Segmentation. arXiv preprint arXiv:2212.02773","author":"Gu Zhangxuan","year":"2022","unstructured":"Zhangxuan Gu, Haoxing Chen, Zhuoer Xu, Jun Lan, Changhua Meng, and Weiqiang Wang. 2022. DiffusionInst: Diffusion Model for Instance Segmentation. arXiv preprint arXiv:2212.02773 (2022)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Zhangxuan Gu Siyuan Zhou Li Niu Zihan Zhao and Liqing Zhang. 2020. Context-Aware Feature Generation For Zero-Shot Semantic Segmentation. In ACM MM. 1921--1929.","DOI":"10.1145\/3394171.3413593"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Zonghui Guo Dongsheng Guo Haiyong Zheng Zhaorui Gu Bing Zheng and Junyu Dong. 2021a. Image Harmonization with Transformer. In ICCV. 14850--14859.","DOI":"10.1109\/ICCV48922.2021.01460"},{"key":"e_1_3_2_1_13_1","unstructured":"Zonghui Guo Haiyong Zheng Yufeng Jiang Zhaorui Gu and Bing Zheng. 2021b. Intrinsic Image Harmonization. In CVPR. 16367--16376."},{"key":"e_1_3_2_1_14_1","volume-title":"Scs-co: Self-consistent style contrastive learning for image harmonization. In CVPR. 19710--19719.","author":"Hang Yucheng","year":"2022","unstructured":"Yucheng Hang, Bin Xia, Wenming Yang, and Qingmin Liao. 2022. Scs-co: Self-consistent style contrastive learning for image harmonization. In CVPR. 19710--19719."},{"key":"e_1_3_2_1_15_1","volume-title":"Belongie","author":"Huang Xun","year":"2017","unstructured":"Xun Huang and Serge J. Belongie. 2017. Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization. In ICCV. 1510--1519."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Yongcheng Jing Xiao Liu Yukang Ding Xinchao Wang Errui Ding Mingli Song and Shilei Wen. 2020. Dynamic Instance Normalization for Arbitrary Style Transfer. In AAAI. 4369--4376.","DOI":"10.1609\/aaai.v34i04.5862"},{"key":"e_1_3_2_1_17_1","volume-title":"Harmonizer: Learning to Perform White-Box Image and Video Harmonization. In ECCV. 690--706.","author":"Ke Zhanghan","year":"2022","unstructured":"Zhanghan Ke, Chunyi Sun, Lei Zhu, Ke Xu, and Rynson WH Lau. 2022. Harmonizer: Learning to Perform White-Box Image and Video Harmonization. In ECCV. 690--706."},{"key":"e_1_3_2_1_18_1","volume-title":"NeurIPS","volume":"30","author":"Li Yijun","year":"2017","unstructured":"Yijun Li, Chen Fang, Jimei Yang, Zhaowen Wang, Xin Lu, and Ming-Hsuan Yang. 2017. Universal style transfer via feature transforms. NeurIPS, Vol. 30 (2017)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Jingtang Liang Xiaodong Cun and Chi-Man Pun. 2022. Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization. In ECCV.","DOI":"10.1007\/978-3-031-20071-7_20"},{"key":"e_1_3_2_1_20_1","first-page":"16331","article-title":"Editgan: High-precision semantic image editing","volume":"34","author":"Ling Huan","year":"2021","unstructured":"Huan Ling, Karsten Kreis, Daiqing Li, Seung Wook Kim, Antonio Torralba, and Sanja Fidler. 2021a. Editgan: High-precision semantic image editing. NeurIPS, Vol. 34 (2021), 16331--16345.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Jun Ling Han Xue Li Song Rong Xie and Xiao Gu. 2021b. Region-Aware Adaptive Instance Normalization for Image Harmonization. In CVPR. 9361--9370.","DOI":"10.1109\/CVPR46437.2021.00924"},{"key":"e_1_3_2_1_22_1","volume-title":"Cong Chen, Maxim Arap, and Raffay Hamid.","author":"Liu Sheng","year":"2023","unstructured":"Sheng Liu, Cong Phuoc Huynh, Cong Chen, Maxim Arap, and Raffay Hamid. 2023. LEMaRT: Label-Efficient Masked Region Transform for Image Harmonization. arXiv preprint arXiv:2304.13166 (2023)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5201\/ipol.2016.163"},{"key":"e_1_3_2_1_24_1","unstructured":"Hyeonseob Nam and Hyo-Eun Kim. 2018. Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks. In NeurIPS. 2563--2572."},{"key":"e_1_3_2_1_25_1","unstructured":"Dae Young Park and Kwang Hee Lee. 2019. Arbitrary style transfer with style-attentional networks. In CVPR. 5880--5888."},{"key":"e_1_3_2_1_26_1","volume-title":"NeurIPS","volume":"32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. NeurIPS, Vol. 32 (2019)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/38.946629"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Jing Shi Ning Xu Haitian Zheng Alex Smith Jiebo Luo and Chenliang Xu. 2022. SpaceEdit: Learning a Unified Editing Space for Open-Domain Image Color Editing. In CVPR. 19730--19739.","DOI":"10.1109\/CVPR52688.2022.01911"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Konstantin Sofiiuk Polina Popenova and Anton Konushin. 2021. Foreground-aware semantic representations for image harmonization. In WACV. 1620--1629.","DOI":"10.1109\/WACV48630.2021.00166"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778862"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20134"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Yi-Hsuan Tsai Xiaohui Shen Zhe Lin Kalyan Sunkavalli Xin Lu and Ming-Hsuan Yang. 2017. Deep Image Harmonization. In CVPR. 2799--2807.","DOI":"10.1109\/CVPR.2017.299"},{"key":"e_1_3_2_1_33_1","first-page":"22844","article-title":"A2: Efficient automated attacker for boosting adversarial training","volume":"35","author":"Xu Zhuoer","year":"2022","unstructured":"Zhuoer Xu, Guanghui Zhu, Changhua Meng, Zhenzhe Ying, Weiqiang Wang, Ming GU, Yihua Huang, et al. 2022. A2: Efficient automated attacker for boosting adversarial training. NeurIPS, Vol. 35 (2022), 22844--22855.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_34_1","volume-title":"DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization. In ECCV.","author":"Xue Ben","year":"2022","unstructured":"Ben Xue, Shenghui Ran, Quan Chen, Rongfei Jia, Binqiang Zhao, and Xing Tang. 2022. DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization. In ECCV."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185580"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611747","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611747","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:12:59Z","timestamp":1755821579000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611747"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":35,"alternative-id":["10.1145\/3581783.3611747","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611747","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}