Email: jsyeh [at] cmlab.csie.ntu.edu.tw, jsyeh [at] mcu.edu.tw
Lab: +886-2-2362-5336 ext. 501
Communication and Multimedia Lab
Room 501, Dept. of CSIE, NTU ,
#1 Roosevelt Rd. Sec. 4, Taipei 106, TAIWAN
Research Interests
Computer Graphics
Virtual Reality and User Interface
Computer Vision
Bio Graphics
Publications
- Jeng-Sheng Yeh, Jen-Yuan Chiang, Ting-Hao Huan, Li-Fong Lin, Ming-Yang Yu, Chung-Lin Wen, Jean Y.C. Tsai, Liang-Kai Wang, Ding-Yun Chen, Yung-Yu Chuang, Bing-Yu Chen, Ming Ouhyoung (2006), "Hand-Shadow Illusions and 3D DDR based on efficient model retrieval", SIGGRAPH 2006 Emerging Technologies (Demo), Boston, July 30-Auguest 3, 2006.
- Jeng-Sheng Yeh (2005), 3D protein retrieval based on pocket modeling and matching, Ph.D. Dissertation, Dept. CSIE, National Taiwan University, July 2005.
- Jeng-Sheng Yeh, Ding-Yun Chen, Bing-Yu Chen, Ming Ouhyoung (2005), "A web-based three-dimensional protein retrieval system by matching visual similarity", Bioinformatics, 2005 21: 3056-3057.
- Pei-Hsuan Tu, I-Chen Lin, Jeng-Sheng Yeh, Rung-Huei Liang, Ming Ouhyoung (2004), "Surface detail capturing for realistic facial animation", Journal of Computer Science and Technology (special issue on Advances in Computer Graphics), 19(5):618-625, Sept. 2004 (SCIE, EI).
- Pei-Hsuan Tu, I-Chen Lin, Jeng-Sheng Yeh, Rung-Huei Liang, Ming Ouhyoung (2003), "Expression detail mapping for realistic facial animation", Proc. CAD/Graphics 2003, pp. 20-25. Macau, Oct 28-30, 2003
- I-Chen Lin, Jeng-Sheng Yeh, and Ming Ouhyoung (2002), "Extracting 3D facial animation parameters from multiview video clips", IEEE Computer Graphics and Applications (special issue on Tracking), Vol. 22, no. 6, pp. 72-80, Nov-Dec 2002.
- Jeng-Sheng Yeh, Ting-Yu. Lien, Ming Ouhyoung (2002), "On the effects of haptic display in brush and ink simulation for Chinese painting and calligraphy", Proc. Pacific Graphics 2002 (PG 2002), pp. 439-441, Beijing, China, Oct. 2002.
- I-Chen Lin, Jeng-Sheng Yeh, Ming Ouhyoung (2001), "Extraction of 3D facial parameters from mirror-reflected multi-view video for audio-visual synthesis", Proc. of AVSP2001 (Int'l Conf. of Auditory-Visual Speech Processing), (ISBN 0-9712714-0-2) pp. 66-71, Aalborg, Denmark, Sept. 2001.
- I-Chen Lin, Jeng-Sheng Yeh, Ming Ouhyoung (2001), "Realistic 3D facial animation parameters from mirror-reflected multi-view video", Proc. IEEE Computer Animation 2001, pp. 2-11, Seoul, Korea, Nov. 2001. ISSN 1087-4844.
- Chia-Ying Lee, Jeng-Sheng Yeh, Kuo-Luen Perng, Yu-Chung Lee, Ming Ouhyoung (2000), "A facial animation module of MPEG-4 system based on VRML97 for virtual and natural scene integration", Proc. ICS2000, Taiwan.
Teaching Experience
Current Projects
- Camera-Array Video Conferencing (2005-now)
- Matching of Proteins or Models by GPU (2005-now)
- 3D Model Retreival (2003-now) and 3D Protein Model Retrieval (2003-now)

The left is a 3D model retrieval system based on multi-view
LightField descriptors and multi-resolution reeb graph.
The right is a 3D Protein Model Retrieval System based on multi-view
LightField descriptors and spin-images.
Involved Projects
Non-photorealistic rendering and interactive user interface
- ChineseBrush and Chinese Painting (2002)

This was one of his major projects.
User can use WACOM tablet to control the Chinese brush and to do their
artworks. He cooperated with Andie Lian for more than one year.
Their system uses ink-water simulation model and hair-spring modeling
to simulate painting in computer.
On the other hand, another goal is to use Phantom Desktop force-feedback
device to simulate Chinese painting brush with force feedback.
(ps. The Chinese artwork on the rhgit desktop is not the result of this system.
It is only a texture.)
Facial modeling, tracking, and animation
- Realistic 3D facial animation parameters

Accurate 3D facial motion trajectories are reconstructed from mirror-reflected multiview videos, and the estimated data are also applied to synthetic face for realistic facial animation.
- Expression Detail Mapping for Realistic Facial Animation (2003)

In this realistic facial animation, Pei-Hsuan proposed the Expression
Detail Mapping (EDM) method to capture and apply the expression detail
in 2D and 3D.
- Face Modeling From 3D Scanned Datar with I-Chen's RSHead (2001-2003)
- Rendering Face (2001)

In the autumn of year 2001, he was trying to implement BSSRDF.
The head model is from Alex Ma.
- MPEG4 Face Object (FAP, FDP) with Carol Lee and I-Chen Lin (2000)
- Lip Tracking and Detection with Carol Lee (2000)
Short projects
- Maya 3D Model Query System Plug-In (2001)

Dr. Din-Yung Chen
developed a 3D Model Query
Server for online query.
What Jeng-Sheng do here is to write a Maya Plug-In to submit
a 3D model in Maya's Scene to this 3D Model Query Server through
HTTP in MIME format.
- News Segmentation System (2002)

Users can divide the news video clips
from TV news video event-by-event. He used and modified the code of
VirtualDub to prove the concept and prototype.
- Reverse Engineering for FreeForm Cly File Format
- Speech query for news (video and movie player)
- Trying Phantom Force-feedback device and VisionStation
- Multi-camera Dodecahedral Spider for 3D Model Retrieval
- Film Restoration
- Talking Head Synthesis on PDA
Created time: 1999-09-02 13:11
Last modified:
Access times since Oct 2001: