副研究员 Asso. Prof.

合肥工业大学 Hefei University of Technology (HFUT)

计算机与信息学院 / 人工智能学院

School of Computer and Information / School of Artificial Interlligence

教育及工作经历 EDUCATION & WORK EXPERIENCE

2004-2008 中国科学技术大学，自动化，本科

    University of Science and Technology of China (USTC), Automation, Bachelor

2008-2013 中国科学技术大学，模式识别，博士 (导师：黄德双教授)

    University of Science and Technology of China (USTC), Pattern Recognition, PhD. (Prof. Deshuang Huang)

2013-2015 北京大学，深圳研究生院，博士后 (合作导师：高文教授)

    Peking Univeristy (PKU), Shenzhen Graduate School, PostDoctor (Prof. Wen Gao)

2018-2022 鹏城实验室，双聘研究员 / 访问学者

    Peng Cheng Laboratory, Shenzhen, China, Part-time Reseacher

2016-至今 合肥工业大学，计算机与信息学院，副研究员 / 副教授

    Hefei University of Technology (HFUT), China, Associate Professor

研究方向 RESEARCH INTERESTS

视频图像处理 | 计算机视觉 | 模式识别

Video Image Processing | Computer Vision | Pattern Recognition

个人简介 RESUME

赵洋，男，合肥工业大学计算机与信息学院，副研究员，博士生导师。 2008年、2013年分别于中国科学技术大学获学士与博士学位。2013-2015年在北京大学深圳研究生院从事博士后研究。2016年起任合肥工业大学计算机与信息学院副研究员。主要研究领域为视频图像处理、计算机视觉、人工智能。近年来，在TIP/TCSVT/IJCV/TMM等国际期刊、会议上发表论文50余篇（其中中科院二区以上期刊论文30余篇）；已授权中国及美国发明专利10余项；曾主持科研项目多项，其中国家自然科学基金项目3项。学术服务方面，任中国人工智能学会模式识别专业委员会委员，中国计算机学会计算机视觉专业委员会委员，中国图象图形学学会青工委副秘书长，视觉与学习青年研讨会执行委员；中国图象图形学报青年编委；为多个国际期刊和会议审稿，CVPR等多个期刊和会议的优秀审稿人，曾任多个学术会议主席或程序委员会成员；课题组多项算法被海信、创维、咪咕、优微视觉等相关企业应用。

个人主页：http://gityzhao.gitee.io

科研项目 RESEARCH PROJECTS

  • 稀疏多视角视频视觉质量联合增强关键技术研究, 62272142, 国家自然科学基金面上项目，主持，在研，2023/01-2026/12.

  • 全4K视频视觉质量增强关键技术研究, 61972129, 国家自然科学基金面上项目，主持，在研，2020/01-2023/12.

  • 基于局部纹理特征的图像细节超分辨率技术研究, 61402018, 国家自然科学基金青年基金, 主持，已结题, 2015/01-2017/12.

  • 热贡艺术元素智能提取与生成关键技术研究及应用, 2021-GX-111, 青海省重点研发与转化计划, 子课题，在研, 2021/01-2023/12.

  • 基于局部模式的图像细节超分辨率技术研究, 2014M550016, 中国博士后科学基金面上资助, 主持，已结题, 2014/05-2015/12.

  • 面向超高清显示的视频增强关键技术研究，合肥工业大学优秀青年人才培育A计划, 主持，在研，2022/04-2024/12.

  • 基于深度学习的图像超分辨率技术研究, 合肥工业大学学术新人提升B计划, 主持，已结题, 2017/01-2018/12.

  • 面向VR实景采集的GPU实时拼接技术, 合肥工业大学应用科技成果培育计划, 主持，已结题, 2017/01-2018/12.

部分发表论文 SELECTED PUBLICATIONS

  • Y. Zhao, W. Jia, Y. Chen, R. Wang, Fast Blind Decontouring Network, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol.33, no.2, pp.478-490, 2023.

  • H. Min, Y. Zhang, Y. Zhao*, W. Jia, Y. Lei, C. Fan, Hybrid Feature Enhancement Network for Few-Shot Semantic Segmentation, Pattern Recognition (PR), 2023.

  • N. Zhang, Y. Ye, Y. Zhao, R. Wang, Revisiting the Stack-Based Inverse Tone Mapping, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.

  • Y. Zhao, Y. Ma, Y. Chen, W. Jia, R. Wang, X. Liu, Multi-frame Joint Enhancement for Early Interlaced Videos, IEEE Transactions on Image Processing (TIP), vol.31, pp.6282-6294, 2022. (Ranked 1st in the MSU Deinterlacer Benchmark)

  • Y. Zhao, W. Jia, R. Wang, Rethinking Deinterlacing for Early Interlaced Videos, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol.32, no. 7, pp.4872-4878, 2022.

  • Y. Zhao, D. Ren, Y. Chen, W. Jia, R. Wang, X. Liu, Cartoon Image Processing: A Survey, International Journal of Computer Vision (IJCV), vol.130, pp.2733-2769, 2022.

  • Y. Chen, P. Zhao, M. Qi, Y. Zhao*, W. Jia, R. Wang, Audio Matters in Video Super-Resolution by Implicit Semantic Guidance, IEEE Transactions on Multimedia (TMM), vol.24, pp. 4128-4142, 2022.

  • N. Zhang, Y. Zhao, C. Wang, R. Wang, A Real-Time Semi-Supervised Deep Tone Mapping Network, IEEE Transactions on Multimedia (TMM), vol. 24, pp. 2815-2827, 2022.

  • D. Hou, Y. Du, K. Zhao, Y. Zhao*, Learning an Efficient Multimodal Depth Completion Model, European Conference on Computer Vision (ECCV) workshop, 2022. (Invited Paper, Champion in the MIPI2022 depth completion challenge)

  • N. Zhang, Y. Ye, Y. Zhao, R. Wang, Fast and Flexible Deep Stack-based Inverse Tone Mapping, CAAI Transactions on Intelligence Technology, 2022.

  • Y. Zhao, R. Wang, Y. Chen, W. Jia, X. Liu, W. Gao, Lighter but Efficient Bit-Depth Expansion Network, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), vol. 31, no. 5, pp. 2063-2069, 2021.

  • Y. Chen, Y. Zhao, L. Cao, W. Jia, X. Liu, Learning Deep Blind Quality Assessment for Cartoon Images, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), DOI: 10.1109/TNNLS.2021.3127720, 2021.

  • W. Jia, W. Xia, B. Zhang, Y. Zhao, L. Fei, W. Kang, A Survey on Dorsal Hand Vein Biometrics, Pattern Recognition (PR), vol. 120, pp.108-122, 2021.

  • W. Jia, Q. Ren, Y. Zhao, S. Li, H. Min, Y. Chen, EEPNet: An efficient and effective convolutional neural network for palmprint recognition, Pattern Recognit. Lett., vol. 159, pp. 140-149, 2022.

  • W. Jia, W. Xia, Y. Zhao, H. Min, Y. Chen, 2D and 3D Palmprint and Palm Vein Recognition Based on Neural Architecture Search, Int. J. Autom. Comput., vol. 18, no. 3, pp.377-409, 2021.

  • W. Jia, J. Gao, W. Xia, Y. Zhao, H. Min, J. Lu, A Performance Evaluation of Classic Convolutional Neural Networks for 2D and 3D Palmprint and Palm Vein Recognition, Int. J. Autom. Comput., vol. 18, no. 1, pp.18-44, 2021.

  • Y. Chen, Y. Zhao, W. Jia, L. Cao, X. Liu, Adversarial-Learning-Based Image-to-Image Transformation A Survey, Neurocomputing, vol. 411, pp.468-486, 2020.

  • Y. Zhao, R. Wang, W. Jia, W. Zuo, X. Liu, W. Gao, Deep Reconstruction of Least Significant Bits for Bit-Depth Expansion, IEEE Transactions on Image Processing (TIP), vol. 28, no. 6, pp. 2847-2859, 2019.

  • Y. Chen, Y. Zhao, S. Li, W. Zuo, W. Jia, X. Liu, Blind Quality Assessment for Cartoon Images, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), Accept, 2019.

  • W. Jia, Y. Zhao*, R. Wang, S. Li, H. Min, X. Liu, Are Recent SISR Techniques Suitable for IndustrialApplications at Low Magnification, IEEE Transactions on Industrial Electronics (TIE), vol.66, no. 12, pp.9828-9836, 2019.

  • Y. Zhao, R. Wang, W. Jia, J. Yang, W. Wang , W. Gao, Local patch encoding-based method for single image super-resolution, Information Sciences (INS), vol.433, pp.292-305, 2018.

  • H. Min, W. Jia, Y. Zhao, W. Zuo, H. Ling, Y. Luo, LATE A Level Set Method Based on Local Approximation of Taylor Expansion for Segmenting Intensity Inhomogeneous Images, IEEE Transactions on Image Processing (TIP), vol.27, no.10, pp.5016-5031, 2018.

  • H. Min, W. Jia, X. Wang, Y. Zhao, Y. Luo, A polynomial piecewise constant approximation method based on dual constraint relaxation for segmenting images with intensity inhomogeneity, Pattern Recognition (PR), vol. 73, pp. 15-32, 2018.

  • H. Min, J. Lu, W. Jia, Y. Zhao, Y. Luo, An effective local regional model based on salient fitting for image segmentation, Neurocomputing, vol.311, pp.245-259, 2018.

  • Y. Zhao, R. Wang, W. Jia, W. Wang, W. Gao, Iterative projection reconstruction for fast and efficient image upsampling, Neurocomputing，vol.226, pp.200-211, 2017.

  • W. Jia, Zhang, J. Lu, Y. Zhu, Y. Zhao, Based on Complete Direction Representation, IEEE Transactions on Image Processing (TIP), vol.26, pp. 4483-4498, 2017.

  • Y. Zhao, R. Wang, W. Wang, W. Gao, Multilevel modified finite radon transform network for image upsampling, IEEE Transactions on Circuits and System for Video Technology (TCSVT), vol. 26, no.12, pp. 2189-2199, 2016.

  • Y. Zhao, R. Wang, W. Wang, W. Gao, High resolution local structure constrained image upsampling, IEEE Transactions on Image Processing (TIP), vol.24, no.11, pp.4394-4407, Nov. 2015.

  • H. Min, W. Jia, X. Wang, R. Hu, Y. Zhao, et al., An Intensity Texture model based level set method for image segmentation, Pattern Recognition (PR), vol. 48, pp. 1547-1562, 2015.

  • W. Jia, R. Hu, Y. Lei, Y. Zhao, J. Gui, Histogram of oriented lines for palmprint recognition, IEEE Transactions on Systems, Man, and Cybernetics Systems (TSMC), vol.44, no.3, pp. 385-395, 2014.

  • Y. Zhao, W. Jia, R. Hu, H. Min, Completed robust local binary pattern for texture classification, Neurocomputing, vol. 106, no.15, pp. 68-76, 2013.

  • Y. Zhao, D. Huang, W. Jia, Completed local binary count for rotation invariant texture classification, IEEE Transaction on Image Processing (TIP), vol.21, pp. 4492-4497, 2012.

  • R. Hu, W. Jia, Y. Zhao, J. Gui, Perceptually motivated morphological strategies for shape retrieval, Pattern Recognition (PR), vol. 45, pp. 3222-3230, 2012.

  • H. Zhang, Y. Zhao, R. Wang, A Flexible Recurrent Residual Pyramid Network for Video Frame Interpolation, European Conference on Computer Vision (ECCV), 2020.

  • X. Liu, Y. Zhao, Y. Chen, W. Jia, R. Wang, X. Liu, Estimated Exposure Guided Reconstruction Model for Low-Light Image Enhancement, Chinese Conference on Pattern Recognition and Computer Vision, 2020.

  • N. Zhang, R. Wang, Y. Zhao, Deep tone mapping network in HSV color space, VCIP, 2019.

  • Y. Zhou, R. Wang, Y. Zhao, A night-time outdoor data set for low-light enhancement, VCIP, pp.507-510, 2020.

  • Z. Guo, Y. Ye, Y. Zhao, R. Wang, An Acceleration Framework for Super-Resolution Network via Region Difficulty Self-adaption, MMM, pp.666-677, 2021.

专利授权 PATENTS

  • 赵洋, 王荣刚, 王振宇, 高文, 王文敏, 董胜富, 黄铁军, 马思伟. 一种基于分类字典库的超分辨率图像重构方法及装置: 中国, ZL201410230714.1, 2014.

  • 赵洋, 王荣刚, 王振宇, 高文, 王文敏, 董胜富, 黄铁军, 马思伟，一种快速超分辨率图像重建方法和装置: 中国, ZL201410230840.7, 2014.

  • 王荣刚, 赵洋, 王振宇, 高文, 王文敏, 董胜富, 黄铁军, 马思伟. 一种基于字典库的视频编解码方法及装置: 中国，ZL201410231054.9，2014.

  • 王荣刚, 赵洋, 王振宇, 高文, 王文敏, 董胜富, 黄铁军, 马思伟. 一种基于图像超分辨率的视频编解码方法及装置: 中国, ZL201410230514.6, 2014.

  • 赵洋, 王荣刚, 高文, 王振宇, 王文敏. 基于混合框架的图像位深度扩展方法及装置: 中国, ZL201710717259.1, 2017.

  • 赵洋，王荣刚，高文，王振宇，王文敏, 一种基于字典匹配的图像超分辨率重建方法及装置: 中国, ZL201510741060.3, 2015.

  • 赵洋，陈缘，贾伟，李书杰，曹明伟，李琳，刘晓平，一种卡通图像质量盲评估方法及装置: 中国，ZL201810231457.1，2018.

  • 赵洋，李国庆，贾伟，陈缘，李书杰，曹明伟，李琳，刘晓平, 一种基于先验滤波器的轻量化网络构建方法及装置: 中国, ZL201810703659.1, 2018.

  • 刘晓平, 陈缘, 赵洋, 曹力, 李琳. 一种卡通视频重制方法及系统:中国, ZL202011386058.6, 2020-12.

  • 刘晓平，陈缘，赵洋，贾伟，李书杰，曹明伟，李琳. 一种动画视频自动生成方法及其装置: 中国，ZL201910248746.7，2019-03.

  • 刘晓平，陈缘，赵洋，贾伟，李书杰，曹明伟，李琳. 一种动画视频自动生成方法及其装置: 中国，ZL201910248746.7，2019-03.

  • 赵洋，马彦博，曹力，贾伟，李琳，刘晓平，一种视频处理方法及系统：中国，ZL202011611610.7, 2020.12.

  • 赵洋，任迪雅，曹力，贾伟，李琳，刘晓平，基于注意力双流深度网络的低质量图像降采样方法及其系统：中国，ZL202010103973.3.

  • Y. Zhao, R. Wang, Z. Wang, W. Gao, Hybrid framework-based image bit-depth expansion method and device, US-2020-0364833 A1, 2020.11.19.

  • R. Wang，Y. Zhao，Z. Wang，W. Gao，W. Wang，S. Dong，T. Huang，S., Method and device for video encoding or decoding based on image super-resolution, US9986255B2.

  • Y. Zhao, R. Wang, Wen Gao, Zhenyu Wang, Wenmin Wang, Method and device for super-resolution image reconstruction based on dictionary matching, US10339633B2.

教学及其他 TEACHING AND OTHERS

  • 王荣刚, 王振宇, 赵洋, 高文, 吴伟. 超高清视频高效实时编码与重建关键技术, 深圳市, 深圳市科学技术奖, 技术发明一等奖, 2020

  • 互联网+创新创业大赛国赛银奖(2021)、省赛金奖(2019)，挑战杯创新创业大赛省赛银奖(2022)，等

  • 安徽省教学成果奖一等奖

Simple things are the best things

  yzhao@hfut.edu.cn

  zhaoyang@pkusz.edu.cn