Thomas Huang

From Wikipedia, the free encyclopedia
Jump to: navigation, search

Thomas Shi-Tao Huang (traditional Chinese: 黃煦濤; simplified Chinese: 黄煦涛; pinyin: Huáng Xùtāo, born Shanghai) is a professor at the University of Illinois at Urbana-Champaign (UIUC). Huang is one of the leading figures in computer vision, pattern recognition and human computer interaction.


Huang studied electronics at the National Taiwan University and received his bachelor's degree in 1956. Huang went to study in the United States, and obtained his D.Sc degree from the Massachusetts Institute of Technology (MIT) in 1963.[1]

Huang is the William L. Everitt Distinguished Professor in the UIUC Department of Electrical & Computer Engineering and the Coordinated Science Lab (CSL). Huang is also a faculty member (full-time) at the Beckman Institute and participates in the Image Formation and Processing and Artificial Intelligence laboratories.[1]


Multimodal human computer interaction, especially the use of speech- and vision-based techniques in developing more natural and effective interfaces as alternatives to complements of conventional interfaces such as the keyboard and the mouse. Research projects include the integration of speech recognition and visual gesture analysis in controlling display in virtual environments; and the use of visual lip reading to enhance audio speech recognition accuracy.

3-D modeling, analysis, and synthesis (animation) of human face, hands, and body. The original motivation for this research is very low bitrate 3-D model-based video coding, esp. for video phone and teleconferencing scenarios. The idea is that if a 3-D model of the user at the transmitting end is constructed at the receiving end, then only the movement information needs to be extracted at the transmitting end and sent to the receiving end, where this information is used to drive the 3-D model and to regenerate the video sequence. Obviously, the tools developed for these scenarios are applicable to many other problems, such as virtual space conferencing with avatars, and electronic games.

Multimedia (images, video, audio, text) databases including content based image retrieval. Of special interest are the use of relevance feedback in adapting the databases system to user intentions (when browsing or searching), and the construction of a table of contents and a semantic index for video using multimedia information (image sequence, audio, and closed-captions if available).

Although the above problems are application motivated, the main goal is to develop general concepts, methodologies, theories, and algorithms which would be widely applicable to multimodal and multimedia signal processing in general. Huang's research support includes the NSF, DOD, UIUC Research Board, and a number of industrial firms.

Published work[edit]

Representative publications by Thomas Huang include:

  • Qi, G. J., Aggarwal, C., Tian, Q., Ji, H., Huang, T. S. (2012), "Exploring Context and Content Links in Social Media: A Latent Space Method", IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 850-862.
  • Jaimes, A., Gatica-Perez, D., Sebe, N., Huang, T.S. (2007), "Human-centered Computing: Toward a Human Revolution", IEEE Computer, 40(5), pp. 30–34.
  • Cohen, I., Cozman, F., Sebe, N., Cirelo, M., Huang, T.S. (2004), "Semi-supervised Learning of Classifiers: Theory, Algorithms and Their Applications to Human-Computer Interaction", IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(12), pp. 1553–1567.
  • Pan, H., Levinson, S.E., Huang, T.S., and Liang, Z.P. (2004), “A Fused HMM Model with Application to Bimodal Speech Processing,” IEEE Transactions On Signal Processing, 52/3, pp. 573– 581.
  • Zhou, X.S. and Huang, T.S. (2003), "Relevance Feedback in Image Retrieval: A Comprehensive Review," ACM Multimedia Systems Journal, pp. 536–544.
  • Bruckstein, A.M., Holt, R.J., Huang, T.S., and Netravali, A.N. (2000), "New Devices for 3D Pose Estimation: Mantis Eyes, Agam Paintings, Sundials, and Other Space Fiducials," International Journal of Computer Vision, pp. 131–139.
  • Lew, M.S., Wong, K., and Huang, T.S. (1994), "Learning and Feature Selection in Stereo Matching," IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 869–881.
  • Arun, K., Huang, T.S., and Blostein, S.D. (1987), "Least-Squares Fitting of Two 3-D Point Sets, IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 698–700.
  • R. Y. Tsai and T.S. Huang, (1984) "Uniqueness and estimation of three-dimensional motion parameters of rigid objects with curved surfaces" IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 13–27.

Honors and Outstanding Achievements[edit]

Huang has received numerous honors and awards in his career, including:[2]

See also[edit]


  1. ^ a b "Beckman Institute Directory: Thomas S. Huang". Beckman Institute for Advanced Science & Technology. Retrieved May 28, 2010.  (English)
  2. ^ "Thomas S. Huang". ECE Illinois, Department of Electrical and Computer Engineering. Retrieved May 28, 2010.  (English)
  3. ^ "IEEE Jack S. Kilby Signal Processing Medal Recipients" (PDF). IEEE. Retrieved February 27, 2011. 
  4. ^ "IEEE Jack S. Kilby Signal Processing Medal Recipients - 2001 - Thomas S. Huang and Arun N. Netravali". IEEE. Retrieved February 27, 2011.