Zhan Ma

Written by  |  25/12/2019 - 15/39

 Zhan Ma, Ph.D.

IMG 0655

 Professor, PhD Advisor   

   School of Electronic Science and Engineering

Nanjing University

163 Xianlin Ave, Nanjing, Jiangsu, China

Email: mazhan@nju.edu.cn

Tel: 025-89681550

Office: 332B ESE Building

web: https://vision.nju.edu.cn 

Education

Aug. 2006 - Dec. 2010Ph.D. in E.E., New York University, Tandon School of Engineering
Aug. 2003 - July 2006M.S. in E.E., Huazhong University of Science and Technology
Aug. 2000 - July 2003B.S. in E.E., Huazhong University of Science and Technology

Professional Experiences

Dec. 2019 - Present

April 2015 - Dec. 2019

Professor, Nanjing University

Associate Professor, Nanjing University 

April 2013 - April 2015 Senior Staff Researcher, Huawei R&D USA
Jan. 2011 - April 2013Senior Researcher, Samsung Research America at Dallas
2008-2010Summer Research Intern, Thomson Corp. R&D, Texas Instruments, Sharp Labs of America

Research Interests

  • Neural Video Communication (Compression & Networking)

  • Smart (Computational) Cameras

  • Computational Vision Model

Selected Publications ( more 

  • Jianqiang Wang, Hao Zhu, Haojie Liu, and Zhan Ma, "Lossy Point Cloud Geometry Compression via End-to-End Learning," IEEE Trans. Circuits and Systems for Video Technology, 31(12):4909-4932, Dec. 2021. [2023 IEEE CAS Society Outstanding Young Author Award]

  • Zhihao Duan, Ming Lu, Zhan Ma, and Fengqing Zhu, "Lossy Image Compression with Hierarchical VAEs," IEEE WACV, Jan. 2023 [Best Algorithms Paper]

  • Jianqiang Wang, Dandan Ding, Zhu Li, Xiaoxing Feng, Chuntong Cao, and Zhan Ma, "Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression," IEEE Trans. Pattern Analysis and Machine Intelligence, Nov. 2022. [Technical Candidate Under Investigation for Next-Generation Point Cloud Compression Standard]

  • Tong Chen, Haojie Liu, Zhan Ma, Qiu Shen, Xun Cao, and Yao Wang, "End-to-End Learnt Image Compression via Nonlocal Attention Optimization and Improved Context Modeling," IEEE Trans. Image Processing, vol. 30, pp. 1494 -1520, Sept. 2021. [Adopted as the baseline model of IEEE 1857.11 standard]

  • Ming Cheng, Zhan Ma, M. Salman Asif, Yiling Xu, Haojie Liu, Wenbo Bao, and Jun Sun, "A Dual Camera System for High Spatiotemporal Resolution Video Acquisition," IEEE Trans. Pattern Analysis and Machine Intelligence, March 2020. [Open Source[Utilizing off-the-shelf cameras for professional high-speed video acquisition!]

  • Hao Chen, Xu Zhang, Yiling Xu, Ju Ren, Jingtao Fan, Zhan Ma, and Wenjun Zhang, 'T-Gaming: A Cost-Efficient Cloud Gaming System at Scale', IEEE Transactions on Parallel and Distributed System, June 2019. [Adopted into a commercialized AnyGame to support thousands of concurrent gaming users daily!]

  • Yiling Xu, Hao Chen, Yangchao Zhao, Wenjun Zhang, Qiu Shen, Xu Zhang, and Zhan Ma, "Neural Adaptive Transport Framework for Internet-scale Interactive Media Streaming Service", Proc. of IEEE BMSB, Jeju, Korea, June 2019. [2019 IEEE Broadcast Technology Society Best Paper]

  • Qiu Shen, Juanjuan Cai, Linfeng Liu, Haojie Liu, Tong Chen, Long Ye, and Zhan Ma, "CodedVision: Towards Joint Image Understanding and Compression via End-to-End Learning", Proc. of Pacific-Rim Conference on Multimedia, Hefei, China, Sept 21-22, 2018. [Best Paper Finalist]

  • Ming Lu, Ming Cheng, Qiu Shen, Yiling Xu, and Zhan Ma, "Collaborative Video Processing for Networked Video Applications", ACM SIGCOMM Student Research Competition, August, Budapest, 2018. [Finalist]

  • Hao Zhang and Zhan Ma, "Fast intra mode decision for high-efficiency video coding (HEVC)," IEEE Trans. Circuits and Systems for Video Technology, vol. 24, no. 4, pp. 660 - 668, April 2014. [Partial algorithms adopted into x265 encoder for fast intra-decision.]

  • Zhan Ma, Meng Xu, Yen-Fu Ou, and Yao Wang, “Modeling Rate and Perceptual Quality of Video as Functions of Quantization and Frame Rate and Its Applications,” IEEE Trans. Circuits and Systems for Video Technology, vol. 22, no. 5, pp. 671-682, May 2012. (Models used in WeChat and QQ Video for Rate-Quality Optimization.)

  • Zhan Ma, Hao Hu and Yao Wang, “On Complexity Modeling of H.264/AVC Video Decoding and Its Application for Energy Efficient Decoding,” IEEE Trans. Multimedia, vol. 13, no. 6, pp. 1240-1255, December 2011. (Adopted into ISO/IEC 23001-11 as video decoding complexity indicator.)

  • Felix Fernandes, Esmaeil Faramarzi, Xin Li, Zhan Ma, and Xavier Ducloux, 'Mobile Display Power Reduction for Video using Standardized Metadata',  IEEE Trans. Mobile Computing, vol. 18, no. 1, pp. 165-178, Jan. 2019. (Adopted into ISO/IEC 23001-11 as green display adaptation indicator.)

 

Awards and Honors

  • IEEE Circuits and Systems Society Outstanding Young Author Award, 2023

  • IEEE WACV Best Algorithms Paper, 2023

  • IEEE VCIP Learnt Image Coding Challenge - Speed Track 3rd Prize, 2022

  • IEEE CVPR Nighttime Image Rendering Challenge 2nd Best,2022 

  • SPIE ICMV Illumination Estimation Challenge First Prize, 2020

  • IEEE MMSP Grand Challenge Best Performing Image Coding Solution, 2020

  • IEEE Broadcast Technology Society Best Paper Award, 2019

  • PCM Best Paper Finalist, 2018

  • SIGCOMM Student Research Competition Finalist, 2018

  • Deng Feng Plan (登峰人才), Nanjing University, 2015

Links

Vision Lab@NJU
Video Lab@NYU
CITE Lab@NJU