Personal Information

  • Multimedia Architecture and Processing Laboratory
  • Dept. of Computer Science, National Chiao-Tung University
  • Office: Room 621 at Engineering Building C (EC621)
  • Address: National Chiao Tung University 1001 University Road, Hsinchu, Taiwan 300, ROC
  • Tel: +886-3-5712121 ext.57449; +886-976-239-665
  • Email: hujh@cs.nctu.edu.tw

Education

Research Interests

  • Video compression
  • High Efficiency Video Coding (HEVC)
  • Machine Learning
  • Deep Learning
  • Reinforcement Learning

Conference Publications

  • L. C. Chen*, J. H. Hu*, and W. H. Peng, "Reinforcement Learning for HEVC/H.265 Frame-level Bit allocation," IEEE International Conference on Digital Signal Processing (DSP), Nov. 2018. (*equal contribution)
  • J. H. Hu, W. H. Peng, and C. H. Chung, "Reinforcement Learning for HEVC/H.265 Intra-Frame Rate Control," IEEE International Symp. on Circuits and Syst. (ISCAS), May 2018.
  • C. H. Chung, W. H. Peng and J. H. Hu, "HEVC/H.265 Coding Unit Split Decision Using Deep Reinforcement Learning," Proc. IEEE Int. Symp. on Intelligent Signal Process. and Comm. Syst. (ISPACS), Xiamen, November 2017.

Specialized Courses

  • Deep learning
  • Machine Learning.
  • Artificial Intelligence
  • Pattern Recognition
  • Video Compression
  • Random Process
  • Big Data Analysis
  • Parallel Programming

Research Highlights

  • Video Compression and Reinforcement Learning (RL)
    • Propose an RL-based coding unit split decision algorithm for HEVC/H.265.
      • Formulate the coding unit split decision as an RL problem.
      • Train an RL agent to predict the RD cost reduction associated with a CU split decision
      • Results: The model shows the same level of RD cost prediction accuracy as the exhaustive search scheme.
    • Propose an RL-based intra frame rate control algorithm for HEVC/H.265
      • Formulate the Frame-level rate control as a sequential QP determination problem.
      • Train an RL agent to determine QP for each CTU based on long-term RD benefits.
      • Results: The model is able to perform comparably with the rate control scheme in HEVC/H.265 when trained only on few sequences and shows better subjective quality.
    • Propose an RL-based inter frame rate control algorithm for HEVC/H.265.
      • Extend the notion of the previous work to inter-frame rate control.
      • Introduce the actor-critic method (DDPG) for fine-grained QP determination for each CTU.
      • Results: The model shows 1-2% BD-rate savings relative to HEVC/H.265 rate control, with less bit rate errors.
    • Propose an RL-based frame-level bit allocation algorithm for HEVC/H.265
      • Formulate the frame-level bit allocation problem as an RL problem.
      • Perform frame-level bit allocation by considering long-term impacts on GOP-level distortion.
      • Implement actor-critic method for frame-level bit allocation.
      • Results: The model shows 1-2% BD-rate savings relative to HEVC/H.265 rate control.

Significance: these represent pioneer attempts at applying RL to video encoder control.

  • Domain Transfer
    • Dash-cam Color Transfer (https://goo.gl/zfFMqe )
      • Use deep learning tool for dash-cam training data augmentation.
      • Implement cycle-GAN to deal with style transfer problem.
  • 3D Reconstruction
    • Interior Design (Independent Research/Undergraduate Research)
      • Implement a vanishing point based 3D reconstruction
      • Use extrapolation to calculate the each depth of corner in 3D space

Programming Experience

  • Desktop Application Development (C, C++)
  • Website Development (JavaScript, HTML, CSS)
  • Linux Environment (Ubuntu)
  • Mobile Application Development (Android)
  • Deep Learning Environment (Tensorflow, Python)
  • Programming Exam
    • Top 4.4% in College Programming Exam, 2013-12-17
    • Top 2.9% in College Programming Exam, 2014-03-25
    • Top 5.4% in College Programming Exam, 2014-09-23
    • Top 5.5% in College Programming Exam, 2015-03-24

Teaching Assistant

  • Feb. 2015 - Jun. 2015, Computer Programming
  • Sep. 2016 - Jan. 2017, Linear Algebra

Referees

  • Advisor: Professor Wen-Hsiao Peng, Dept. of CS, National Chiao-Tung University
  • Office: EC431, National Chiao Tung University 1001 University Road, Hsinchu, Taiwan 300, ROC
  • Tel: +886-3-5712121 ext.56625
  • Email: wpeng@cs.nctu.edu.tw