季向阳 教授

控制理论与技术研究所

通信地址:北京清华大学自动化系中央主楼  邮编:100084
联系电话:010-6279481
E-mail: xyji@tsinghua.edu.cn

教育背景

1999年、2001年 分别获哈尔滨工业大学工学学士、硕士学位
2008年 中科院计算技术研究所工学博士学位

工作履历

2008年6月至2010年2月 清华大学自动化系 博士后

2010年3月至2011年11月 清华大学自动化系 讲师

2012年12月至2014年11月 清华大学自动化系 副教授

2013年12月至2014年12月 普林斯顿大学 访问学者

2014-12至今 清华大学自动化系 教授

学术兼职

Signal Processing: Image Communication  Area Editor

中国电子学会青年科学家俱乐部 轮值主席

研究领域

信号/视频处理、压缩

统计分析、机器学习

光学成像

研究概况

视频编码,国家杰出青年科学基金项目,2014年1月至2017年12月

编码摄像理论与方法研究,国家自然科学基金重点国际合作研究项目,2017年1月至2021年12月

奖励与荣誉

2016年 第二批国家“万人计划”领军人才

2014年 中国青年科技奖

2014年 中国青年科技创新领军人才

2013年 国家杰出青年科学基金

2013年 IEEE Outstanding Contributions IEEE Std 1875TM

2012年 国家技术发明一等奖,排名第2

2010年 国家科学技术进步二等奖,排名第2

2009年 中国计算机学会优秀博士学位论文

2009年 清华大学优秀博士后

2009年 中科院优秀博士论文

学术成果

发表论文:
[1]Wen Ji, Xiangyang Ji, Yiqiang Chen, “Feedback-Free Binning Design for Mobile Wyner-Ziv Video Coding: An Operational Duality between Source Distortion and Channel Capacity,” Transactions on Mobile Computing, Accepted.

[2]Zhenyu Liu, Xianyu Yu, Yuan Gao, Shaolin Chen, Xiangyang Ji, Dongsheng Wang, “CU Partition Mode Decision for HEVC Hardwired Intra Encoder Using Convolution Neural Network”, IEEE Transaction on Image Processing, Accepted

[3]Yongbing Zhang, Long Xu, Xiangyang Ji, Qionghai Dai, “A Polynomial Approximation Motion Estimation Model for Motion-Compensated Frame Interpolation,” IEEE Transactions on Circuits and System for Video Technology, 2016, Vol. 26, No. 8, pp. 1421-1432.

[4]Qi Guo, Bo-Wei Chen, Seungmin Rho,Wen Ji, Feng Jiang, Xianyang Ji, Sun-Yuan Kung, “Efficient Divide-and-Conquer Classification Based on Parallel Feature-Space Decomposition for Distributed Systems,” IEEE Systems Journal, in press

[5]Xiangyang Ji, Sam Kwong, Bo-Wei Chen, Seungmin Rho, “High-efficient video compression for social multimedia distribution,” The Journal of Supercomputing, 2015, vol. 71, no. 6, pp. 2138-2152.

[6]Yue Deng, Yipeng Li, Yanjun Qian, Xiangyang Ji, and Qionghai Dai, “Visual Words Assignment via Information-Theoretic Manifold Embedding,” IEEE Transactions on Cybernics, 2014, vol. 44, no. 10, pp. 1924-1937.

[7]Xiangyang Ji, Qifei Wang, Bo-Wei Chen, Seungmin Rho, C. C. Jay Kuo, Qionghai Dai, “Online distribution and interaction of video data in social multimedia network,” Multimedia Tools and Applications, 2014, pp. 1-14.

[8]Jingyu Lin, Xing Lin, Xiangyang Ji, Qionghai Dai, “Separable Coded Aperture for Depth from a Single Image,” IEEE Signal Processing Letters, Dec. 2014, vol.21, no.12, pp. 1471-1475.

[9]Jingyu Lin, Xiangyang Ji, Wenli Xu, Qionghai Dai, “Absolute Depth Estimation from a Single Defocused Image,” IEEE Transactions on Image Processing, Nov. 2013, vol.22, no.11, pp. 4545 - 4550.

[10]Genzhi Ye, Yebin Liu, Yue Deng, Nils Hasler, Xiangyang Ji, Qionghai Dai, Christian Theobalt, “Free-Viewpoint Video of Human Actors Using Multiple Handheld Kinects,” IEEE Transactions on Image Cybernics, Oct. 2013, vol.43, no.5, pp. 1370 - 1382.

[11]Yongbing Zhang, Xiangyang Ji, Haoqian Wang, Qionghai Dai, “Stereo Interleaving Video Coding with Content Adaptive Image Subsampling,” IEEE Transactions on Circuits and System for Video Technology, Jul. 2013, vol.23, no.7, pp. 1097 – 1108.

[12]Qifei Wang, Xiangyang Ji, M Sun, G Sullivan, Jin Li, Qionghai Dai, “Complexity Reduction and Performance Improvement for Geometry Partitioning in Video Coding,” Feb. 2013, vol.23, no.2, pp. 1051-8215

[13]Qifei Wang, Xiangyang Ji, Qionghai Dai, and Naiyao Zhang, “Free Viewpoint Video Coding with Rate-Distortion Analysis,” IEEE Transactions on Circuits and System for Video Technology, Jun. 2012, vol.22, no.6, pp.875-889.

[14]Hongjiang Xiao, Xiangyang Ji, Qionghai Dai, “Relay-assisted hierarchical adaptation Scheme for Multi-user Scalable Video Delivery to Heterogeneous Mobile Devices,” SCIENCE CHINA Information Sciences F, Jul. 2012, , vol.55, no.7, pp. 1541-1550.

[15]Jinli shuo, Xiangyang Ji, Qionghai Dai, “Computational Photography,” SCIENCE CHINA Information Sciences F. Jun. 2012, vol.55, no.6, pp. 1229-1248.

[16]Long Xu, Debin Zhao, Xiangyang Ji, Lei Deng, Sam Kwong, Wen Gao,“Window-Level Rate Control for Smooth Picture Quality and Smooth Buffer Occupancy,” IEEE Transactions on Image Processing, Mar. 2011, vol. 20, pp. 723-734.

[17]Mei. Guo, Zixiang Xiong, Feng Wu, Debin Zhao, Xiangyang Ji, Wen Gao “Witsenhausen-Wyner Video Coding,” IEEE Transactions on Circuits and Systems for Video Technology, Aug. 2011, vol. 21, pp. 1049-1060.

[18]Changjun Fu, Xiangyang Ji, and Qionghai Dai, “Adaptive compressed sensing recovery utilizing the property of signal’s autocorrelations,” IEEE Transactions on Image Processing, May 2011, vol.21, no.5, pp.2369-2378.

[19]Xiangyang Ji, Yongbing Zhang, and Qionghai Dai “Opposite parity packing arrangement for 3D stereoscopic video coding,” IET Electronics Letters, Oct. 2011, vol. 47, no.21, pp. 1801-1802.

[20]Hongjiang Xiao, Qionghai Dai, Xiangyang Ji, Wenwu Zhu “A Novel JSCC Framework with Diversity-multiplexing-coding Gain Tradeoff for Scalable Video Transmission over Cooperative MIMO,” IEEE Transactions on Circuits and System for Video Technology, Jul. 2010, vol.20, no.7, pp.994-1006.

[21]Da Liu, Debin Zhao, Xiangyang Ji, Wen Gao, “Dual Frame Motion Compensation with Optimal Long-Term Reference Frame Selection and Bit Allocation,” IEEE Transactions on Circuits and System for Video Technology, Mar. 2010, vol.20, no.3, pp. 325-339.

[22]Yu Wang, Xiangyang Ji, Qionghai Dai, “Fourth-order Oriented Partial-differential Equations for Noise Removal of Two-photon Fluorescence Images,” Optics Letters, Sep.2010, vol. 35, no. 17, pp. 2943-2945.

[23]Yu Wang, Xiangyang Ji , Qionghai Dai,“Key Technologies of Light Field Capture for 3D Reconstruction in Microscopic Scene,” SCIENCE CHINA Information Sciences F, 2010, vol 53, no. 10, pp 1917-1930.

[24]Xiangyang Ji, Debin Zhao, Wen Gao “Concealment of Whole-picture Loss in Hierarchical B-picture Scalable Video Coding,” IEEE Transactions on Multimedia, Jan. 2009, vol.11, no.1, pp.11-22.

[25]Yongbing Zhang, Debin Zhao, Xiangyang Ji, Rong gang Wang, Wen Gao, “A Spatio-Temporal Auto Regressive Model for Frame Rate Upconversion,” IEEE Transactions on Circuits and System for Video Technology, Sep. 2009, vol.19, no.9, pp.1289-1301.

[26]Yongbing Zhang, Debin Zhao, Xiangyang Ji, Rong gang Wang, Wen Gao, “Corrections to ‘A Spatio-Temporal Auto Regressive Model for Frame Rate Up-Conversion’ ,” IEEE Transactions on Circuits and System for Video Technology, Sep. 2009, vol.19, no.9, pp.1289-1301.

[27]Xiangyang Ji, Sam Kwong, Debin Zhao, Hanli Wang, C. Kuo, Qionghai Dai, “Early Determination of Zero-quantized 8x8 DCT Coefficients,” IEEE Transactions on Circuits and System for Video Technology, Dec. 2009, vol.19, no.12, pp. 1755-1765.

[28]Bo Wu, Xiangyang Ji, Debin Zhao, Wen Gao, “Spatial-Aided Low-Delay Wyner-Ziv Video Coding,” Eurasip Journal on Image and Video Processing, Jan. 2009, vol. 2009, pp. 1-11.

[29]Xiangyang Ji, Yanyan Zheng, Debin Zhao, Feng Wu, Wen Gao “FGS Coding Using Cycle-Based Leaky Prediction through Multiple Leaky Factors,” IEEE Transactions on Circuits and System for Video Technology, Sep. 2008, vol.18, no.9, pp. 1201-1211.

[30]Xiangyang Ji, Debin Zhao, Wen Gao,“Bi-directionally Predicted Coding Techniques in AVS,” Signal Processing: Image Communication, vol.23, no.1, pp.31-41, Jan. 2008.

[31]Long Xu, Lei Deng, Xiangyang Ji, Xiaoming Peng, Wen Gao, “Hardware Architecture of AVS Entropy Encoder,” IEEE Transactions on Consumer Electronics, vol.54, no.2, pp.769-777, Jul.2008.

[32]Xiangyang Ji, Debin Zhao, Wen Gao, “Block-Wise Adaptive Motion Accuracy based B-Picture Coding With Low-Complexity Motion Compensation,” IEEE Transactions on Circuits and System for Video Technology, Aug. 2007, vol.17, no.8, pp.1085-1090. 


研究生课程:
机器学习基础


本科生课程:
数字视频基础与应用