Scholar
Wen-Hsiao Peng
Google Scholar ID: HucsFB4AAAAJ
Professor, Computer Science, National Chiao Tung University
Citations & Impact
Citations
1,619
H-index
20
i10-index
31
Publications
20
Co-authors
8
list available
Publications
Resume (English only)
Academic Achievements
- IEEE Fellow (2025)
- Chair, IEEE CASS Visual Signal Processing and Communications Technical Committee (VSPC TC), 2021–2022
- Secretary, IEEE CASS VSPC TC, 2018–2020
- Member, IEEE CASS Standards Activities Sub-Division (SASD), 2022–2023
- Delegate, ISO/IEC Moving Picture Experts Group (MPEG), since 2004
- Contributed to JPEG AI Call-for-Evidence & Call-for-Proposals on learning-based image compression
- Participated in ByteDance’s Grand Challenge on Neural Network-based Video Coding at IEEE ISCAS (2022–2025)
- Participated in Google-led Challenge on Learned Image Compression at IEEE CVPR (2018–2022)
Research Experience
- Part-time Professor in Generative Models for Artificial Intelligence, Leibniz University Hannover (LUH), Germany, starting Oct. 2025
- Director, Institute of Data Science, National Yang Ming Chiao Tung University (NYCU), Aug. 2022 – July 2025
- Associate Director, Joint AI Research Labs (University of Washington & NYCU), Jan. 2020 – Present
- Visiting Professor, IBM Thomas J. Watson Research Center, New York, USA, July 2015 – July 2016
- Professor, Department of Computer Science, NYCU, Aug. 2006 – Present
- Director, Division of Industry Cooperation, Office of International Affairs, NYCU
- Associate Director, Computer Vision Research Center, NYCU
- Secretariat, EECS Center for Circuit Theory, Communications, and Signal Processing, NYCU
- Principal Representative, Industrial Technology Research Institute International (ITRI-USA), to INCITS, Nov. 2011 – Present
- Intern, Intel Microprocessor Research Lab, California, USA, Nov. 2000 – Nov. 2001
Background
- Research interests include neural network-based image/video coding (e.g., end-to-end learned coding, reinforcement learning-assisted encoder control, and coding for machines)
- Active in ISO/IEC and ITU-T video coding standards such as H.264/AVC SVC, H.265/HEVC, Screen Content Coding (SCC), H.266/VVC, JPEG AI, and 360 video
- Visual signal processing, including image/video super-resolution and re-scaling
- Computer vision topics such as semantic segmentation, incremental learning, video prediction, and domain adaptation
- Multi-modality data fusion and graph computing/mining
