{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T12:27:03Z","timestamp":1769257623779,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":74,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,9]]},"DOI":"10.1145\/3769748.3773342","type":"proceedings-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T10:33:15Z","timestamp":1765189995000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-scale Dynamic Network for Document Shadow Removal"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0292-9991","authenticated-orcid":false,"given":"Jiarui","family":"Li","sequence":"first","affiliation":[{"name":"Qingdao University, Qingdao, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8491-1968","authenticated-orcid":false,"given":"Jiaqi","family":"Ma","sequence":"additional","affiliation":[{"name":"MBZUAI, Abu Dhabi, United Arab Emirates"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9171-9234","authenticated-orcid":false,"given":"Zeyu","family":"Xiao","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2522-4080","authenticated-orcid":false,"given":"Ziyi","family":"Zhuang","sequence":"additional","affiliation":[{"name":"University of Hawaii at Monoa, Hawaii, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6917-8654","authenticated-orcid":false,"given":"Zhihe","family":"Lu","sequence":"additional","affiliation":[{"name":"Hamad Bin Khalifa University, Doha, Qatar"}]}],"member":"320","published-online":{"date-parts":[[2025,12,8]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6695"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Paul\u00a0M Dare. 2005. Shadow analysis in high-resolution satellite imagery of urban areas. Photogrammetric Engineering & Remote Sensing 71 2 (2005) 169\u2013177.","DOI":"10.14358\/PERS.71.2.169"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Na Feng Zikai Song Junqing Yu Yi-Ping\u00a0Phoebe Chen Yizhu Zhao Yunfeng He and Tao Guan. 2020. SSET: a dataset for shot segmentation event detection player tracking in soccer videos. Multimedia Tools and Applications 79 39 (2020) 28971\u201328992.","DOI":"10.1007\/s11042-020-09414-3"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.5244\/C.19.51"},{"key":"e_1_3_3_1_6_2","unstructured":"Lanqing Guo Siyu Huang Ding Liu Hao Cheng and Bihan Wen. 2023. Shadowformer: Global context helps image shadow removal. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.01650 (2023)."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Keji He Ya Jing Yan Huang Zhihe Lu Dong An and Liang Wang. 2024. Memory-adaptive vision-and-language navigation. Pattern Recognition 153 (2024) 110511.","DOI":"10.1016\/j.patcog.2024.110511"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00256"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00498"},{"key":"e_1_3_3_1_10_2","first-page":"398","volume-title":"Asian Conference on Computer Vision","author":"Jung Seungjun","year":"2018","unstructured":"Seungjun Jung, Muhammad\u00a0Abul Hasan, and Changick Kim. 2018. Water-filling: An efficient algorithm for digitized document shadow removal. In Asian Conference on Computer Vision. Springer, 398\u2013414."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00252"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00867"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Jiarui Li. 2025. A Deep Learning Method for Document Shadow Removal with Sobel Prior under Mask Supervision. Proceedings of the AAAI Conference on Artificial Intelligence 39 28 (2025) 29584\u201329586.","DOI":"10.1609\/aaai.v39i28.35333"},{"key":"e_1_3_3_1_14_2","unstructured":"Zinuo Li Xuhang Chen Chi-Man Pun and Xiaodong Cun. 2023. High-Resolution Document Shadow Removal via A Large-Scale Real-World Dataset and A Frequency-Aware Shadow Erasing Net. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.14221 (2023)."},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP63160.2024.10849917"},{"key":"e_1_3_3_1_16_2","unstructured":"Zhuoyuan Li Junqi Liao Chuanbo Tang Haotian Zhang Yuqi Li Yifan Bian Xihua Sheng Xinmin Feng Yao Li Changsheng Gao et\u00a0al. 2025. Ustc-td: A test dataset and benchmark for image and video coding in 2020s. IEEE Transactions on Multimedia (2025)."},{"key":"e_1_3_3_1_17_2","unstructured":"Zhuoyuan Li Zikun Yuan Li Li Dong Liu Xiaohu Tang and Feng Wu. 2024. Object segmentation-assisted inter prediction for versatile video coding. IEEE Transactions on Broadcasting (2024)."},{"key":"e_1_3_3_1_18_2","first-page":"2344","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Lin Z.","year":"2020","unstructured":"Z. Lin, Y. Zhang, and J. Li. 2020. BEDSR-Net: A Benchmark Model for Document Image Shadow Removal. In Proceedings of the European Conference on Computer Vision (ECCV). 2344\u20132353."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Deyang Liu Shizheng Li Yifan Mao Xiaofei Zhou Zeyu Xiao and Caifeng Shan. 2025. Learning Implicit and Detail-Enhanced Network for Light Field Image Spatial-Angular Super-Resolution. IEEE Transactions on Circuits and Systems for Video Technology (2025).","DOI":"10.1109\/TCSVT.2025.3612939"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Deyang Liu Shizheng Li Zeyu Xiao Ping An and Caifeng Shan. 2025. L3fmamba: Low-light light field image enhancement with prior-injected state space models. IEEE Signal Processing Letters (2025).","DOI":"10.1109\/LSP.2025.3599733"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Zhihao Liu Hui Yin Yang Mi Mengyang Pu and Song Wang. 2021. Shadow removal by a lightness-guided network with training on unpaired data. IEEE Transactions on Image Processing 30 (2021) 1853\u20131865.","DOI":"10.1109\/TIP.2020.3048677"},{"key":"e_1_3_3_1_22_2","unstructured":"Zhihe Lu Jiawang Bai Xin Li Zeyu Xiao and Xinchao Wang. 2025. Task-to-instance prompt learning for vision-language models at test time. IEEE Transactions on Image Processing (2025)."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00862"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240647"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Zhihe Lu Da Li Yi-Zhe Song Tao Xiang and Timothy\u00a0M Hospedales. 2023. Uncertainty-aware source-free domain adaptive semantic segmentation. IEEE Transactions on Image Processing 32 (2023) 4664\u20134676.","DOI":"10.1109\/TIP.2023.3295929"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACPR.2017.2"},{"key":"e_1_3_3_1_27_2","unstructured":"Zhihe Lu Zeyu Xiao Jiawang Bai Zhiwei Xiong and Xinchao Wang. 2023. Can sam boost video super-resolution? arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.06524 (2023)."},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00913"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28192"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Jiaqi Ma Guoli Wang Lefei Zhang and Qian Zhang. 2023. Restoration and enhancement on low exposure raw images by joint demosaicing and denoising. Neural Networks 162 (2023) 557\u2013570.","DOI":"10.1016\/j.neunet.2023.03.018"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547767"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Jiaqi Ma Yipeng Zhang and Lefei Zhang. 2021. Discriminative subspace matrix factorization for multiview data clustering. Pattern Recognition 111 (2021) 107676.","DOI":"10.1016\/j.patcog.2020.107676"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/633"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"Yifan Mao Zeyu Xiao Ping An Deyang Liu and Caifeng Shan. 2025. Deep Sparse-to-Dense Inbetweening for Multi-View Light Fields. IEEE Transactions on Image Processing (2025).","DOI":"10.1109\/TIP.2025.3612257"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"crossref","unstructured":"Vicky Nair Parimala\u00a0Geetha Kosal\u00a0Ram and Sundaravadivelu Sundararaman. 2019. Shadow detection and removal from images using machine learning and morphological operations. The Journal of Engineering 2019 1 (2019) 11\u201318.","DOI":"10.1049\/joe.2018.5241"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Simone Parisotto Luca Calatroni Marco Caliari Carola-Bibiane Sch\u00f6nlieb and Joachim Weickert. 2019. Anisotropic osmosis filtering for shadow removal in images. Inverse Problems 35 5 (2019) 054001.","DOI":"10.1088\/1361-6420\/ab08d2"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462476"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240612"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32749"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25327"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681104"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463629"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00859"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803486"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"crossref","unstructured":"Bingshu Wang Changping Li Wenbin Zou Yongjun Zhang Xuhang Chen and CL\u00a0Philip Chen. 2025. A comprehensive survey on shadow removal from document images: datasets methods and opportunities. Vicinagearth 2 1 (2025) 1.","DOI":"10.1007\/s44336-024-00010-9"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00192"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053378"},{"key":"e_1_3_3_1_48_2","unstructured":"Zeyu Xiao Jiawang Bai Zhihe Lu and Zhiwei Xiong. 2023. A dive into sam prior in image restoration. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.13620 (2023)."},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"crossref","unstructured":"Zeyu Xiao Zhen Cheng and Zhiwei Xiong. 2023. Space-time super-resolution for light field videos. IEEE Transactions on Image Processing 32 (2023) 4785\u20134799.","DOI":"10.1109\/TIP.2023.3300121"},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00215"},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00343"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681357"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32940"},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00167"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681144"},{"key":"e_1_3_3_1_56_2","first-page":"4403","volume-title":"Proceedings of the Asian Conference on Computer Vision","author":"Xiao Zeyu","year":"2024","unstructured":"Zeyu Xiao, Jiateng Shou, and Zhiwei Xiong. 2024. Learning Complementary Maps for Light Field Salient Object Detection. In Proceedings of the Asian Conference on Computer Vision. 4403\u20134421."},{"key":"e_1_3_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01172"},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"crossref","unstructured":"Zeyu Xiao Wenming Weng Yueyi Zhang and Zhiwei Xiong. 2022. EVA2: Event-assisted video frame interpolation via cross-modal alignment and aggregation. IEEE Transactions on Computational Imaging 8 (2022) 1145\u20131158.","DOI":"10.1109\/TCI.2022.3228747"},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"crossref","unstructured":"Zeyu Xiao and Zhiwei Xiong. 2025. Incorporating degradation estimation in light field spatial super-resolution. Computer Vision and Image Understanding 252 (2025) 104295.","DOI":"10.1016\/j.cviu.2025.104295"},{"key":"e_1_3_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413667"},{"key":"e_1_3_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00409"},{"key":"e_1_3_3_1_62_2","first-page":"136","volume-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"Xing Qilong","year":"2025","unstructured":"Qilong Xing, Zikai Song, Bingxin Gong, Lian Yang, Junqing Yu, and Wei Yang. 2025. Cross-Modality Masked Learning for Survival Prediction in ICI Treated NSCLC Patients. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 136\u2013146."},{"key":"e_1_3_3_1_63_2","first-page":"380","volume-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"Xing Qilong","year":"2025","unstructured":"Qilong Xing, Zikai Song, Youjia Zhang, Na Feng, Junqing Yu, and Wei Yang. 2025. Mca-rg: Enhancing llms with medical concept alignment for radiology report generation. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 380\u2013390."},{"key":"e_1_3_3_1_64_2","first-page":"ii\u2013729","volume-title":"Proceedings.(ICASSP\u201905). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","volume":"2","author":"Xu Li-Qun","year":"2005","unstructured":"Li-Qun Xu, Jos\u00e9\u00a0Luis Landabaso, and Montse Pard\u00e0s. 2005. Shadow removal with blob-based morphological reconstruction for error correction. In Proceedings.(ICASSP\u201905). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005., Vol.\u00a02. IEEE, ii\u2013729."},{"key":"e_1_3_3_1_65_2","doi-asserted-by":"crossref","unstructured":"Qingxiong Yang Kar-Han Tan and Narendra Ahuja. 2012. Shadow removal using bilateral filtering. IEEE Transactions on Image processing 21 10 (2012) 4361\u20134368.","DOI":"10.1109\/TIP.2012.2208976"},{"key":"e_1_3_3_1_66_2","unstructured":"Yifan Ye Jun Cen Jing Chen and Zhihe Lu. 2025. Self-evolved Imitation Learning in Simulated World. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.19460 (2025)."},{"key":"e_1_3_3_1_67_2","doi-asserted-by":"crossref","unstructured":"Aiming Zhang Tianyuan Yu Liang Bai Jun Tang Yanming Guo Yirun Ruan Yun Zhou and Zhihe Lu. 2025. COLA: Context-aware Language-driven Test-time Adaptation. IEEE Transactions on Image Processing (2025).","DOI":"10.1109\/TIP.2025.3607634"},{"key":"e_1_3_3_1_68_2","first-page":"1087","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Zhang L.","year":"2021","unstructured":"L. Zhang, L. Xie, and W. Zhang. 2021. FDRNet: Fast Document Removal Network for Document Image Processing. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 1087\u20131095."},{"key":"e_1_3_3_1_69_2","doi-asserted-by":"crossref","unstructured":"Xu Zhang Jiaqi Ma Guoli Wang Qian Zhang Huan Zhang and Lefei Zhang. 2025. Perceive-ir: Learning to perceive degradation better for all-in-one image restoration. IEEE Transactions on Image Processing (2025).","DOI":"10.1109\/TIP.2025.3566300"},{"key":"e_1_3_3_1_70_2","doi-asserted-by":"crossref","unstructured":"Rui Zhao Ruiqin Xiong Ziluo Ding Xiaopeng Fan Jian Zhang and Tiejun Huang. 2021. MRDFlow: Unsupervised optical flow estimation network with multi-scale recurrent decoder. IEEE Transactions on Circuits and Systems for Video Technology 32 7 (2021) 4639\u20134652.","DOI":"10.1109\/TCSVT.2021.3135440"},{"key":"e_1_3_3_1_71_2","doi-asserted-by":"crossref","unstructured":"Rui Zhao Ruiqin Xiong Jian Zhang Zhaofei Yu Shuyuan Zhu Lei Ma and Tiejun Huang. 2023. Spike camera image reconstruction using deep spiking neural networks. IEEE Transactions on Circuits and Systems for Video Technology 34 6 (2023) 5207\u20135212.","DOI":"10.1109\/TCSVT.2023.3326294"},{"key":"e_1_3_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28581"},{"key":"e_1_3_3_1_73_2","unstructured":"Rui Zhao Ruiqin Xiong Jing Zhao Zhaofei Yu Xiaopeng Fan and Tiejun Huang. 2022. Learning optical flow from continuous spike streams. Advances in Neural Information Processing Systems 35 (2022) 7905\u20137920."},{"key":"e_1_3_3_1_74_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02357"},{"key":"e_1_3_3_1_75_2","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP49819.2020.9301771"}],"event":{"name":"MMAsia '25 Workshops: ACM Multimedia Asia Workshops","location":"Kuala Lumpur Malaysia","acronym":"MMAsia '25 Workshops","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 7th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3769748.3773342","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T22:03:48Z","timestamp":1769205828000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3769748.3773342"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":74,"alternative-id":["10.1145\/3769748.3773342","10.1145\/3769748"],"URL":"https:\/\/doi.org\/10.1145\/3769748.3773342","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]},"assertion":[{"value":"2025-12-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}