A Research or Software Engineering Intern Position for Summer 2010.

Size: px

Start display at page:

Download "A Research or Software Engineering Intern Position for Summer 2010."

Bernadette Edwards
5 years ago
Views:

1 Henry Hao Tang Curriculum Vitae Beckman Institute for Advanced Science and Technology Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign (UIUC) H Mobile: (732) (preferred) T Office: (217) B haotang2@ifp.uiuc.edu Website: haotang2 Objective A Research or Software Engineering Intern Position for Summer Present Areas of Interest Multimedia Pattern recognition and machine learning Computer vision and computer graphics Speech processing Audiovisual biometrics Augmented reality and multimodal human-computer interaction Telepresence and immersive human-computer interaction Education PhD Candidate, University of Illinois at Urbana-Champaign, Department of Electrical and Computer Engineering, Urbana, IL, USA. Advisor: Prof. Thomas S. Huang. Expected graduation date: October Master of Science, Rutgers University, Department of Electrical and Computer Engineering, Piscataway, NJ, USA. Advisor: Prof. James L. Flanagan Master of Engineering, University of Science and Technology of China, Department of Electronic Engineering and Information Science, Hefei, Anhui, China Bachelor of Engineering, University of Science and Technology of China, Department of Electronic Engineering and Information Science, Hefei, Anhui, China. Employment History Intern at Microsoft Research, Spring 2010 Summer Intern at Fuji Xerox Palo Alto Laboratory, Inc. (FXPAL), Summer 2009 Teaching Assistant at University of Illinois at Urbana-Champaign, Spring 2009 Summer Intern at IBM T.J. Watson Research Center, Summer 2008 Teaching Assistant at University of Illinois at Urbana-Champaign, Spring 2008 Summer Intern at Microsoft Research, Summer 2007 Research Assistant at University of Illinois at Urbana-Champaign, 2005-Present Research Assistant at Rutgers University, Teaching Assistant at Rutgers University, /6

2 Teacher at University of Science and Technology of China, Founding member, senior software engineer, research director and research manager at Anhui USTC iflytek Co., Ltd. (Ke Da Xun Fei), Spring 2010 Summer 2009 Spring 2008, 2009 Summer 2008 Summer Present Honors & Awards Emerging Leader in Multimedia, IBM T.J. Watson Research Center, 2009 (awarded to 10 Ph.D. students from top universities nationwide) Best Student Paper Award, International Conference on Pattern Recognition, 2008 Star of Tomorrow, Microsoft Research Asia, 2007 (awarded to outstanding interns) National Scientific and Technological Progress Award, 2nd Prize, China, 2002 (conferred by The State Council of P.R. China) Scientific and Technological Progress Award of Anhui Province, 1st Prize, China, 2000 Scientific and Technological Achievement Award of Anhui Province, China, 2000 Work Experiences Intern, Microsoft Research, Redmond, WA, USA. Working on a large-scale telepresence project, focusing on audiovisual scene analysis using multiple web cameras and microphones. Intern, Fuji Xerox Palo Alto Laboratory, Inc. (FXPAL), Palo Alto, CA, USA. Designed and implemented a framework to support fine-grained and bimanual cross-media interactions with documents. Aimed at overcoming three challenges: 1) robust recognition of paper documents with occlusions; 2) accurate localization of documents and pointers; and 3) stabilization of pointer detection and tracking. Developed three applications (receipt processing, document manipulation, and map street view navigation) in C++ and C# (.NET). Teaching Assistant, Univ. of Illinois at Urbana-Champaign, ECE Dept., Urbana, IL, USA. Assisted Prof. Thomas Huang in teaching Multimedia Signal Processing". Prepared and graded machine problems and exams; Gave guest lectures on topics including 3D face processing, image warping, and artificial neural networks. Intern, IBM T.J. Watson Research Center, Yorktown Heights, NY, USA. Worked on the conceptually new research topic semi-supervised speaker clustering (mentored by Dr. Stephen M. Chu in the Human Language Technologies Group). Intern, Microsoft Research, Beijing, China. Solely designed, developed, and tested an expressive avatar research platform, programmed in C++/CLI (.NET managed/safe code) using Microsoft Visual Studio This platform was showcased by Microsoft at ICASSP 2008 in Las Vegas, NV in April Research Assistant, Univ. of Illinois at Urbana-Champaign, IFP Group, Urbana, IL, USA. Working on the following directions: A. Audiovisual Emotion Recognition and Synthesis: 1. Nonfrontal view facial expression recognition; 2. 3D facial expression recognition; 3. Emotion recognition from speech signals; 4. Emotional facial expression synthesis; 5. Emotional text-to-speech synthesis; 6. Motion capture and databases. B. Speaker Biometrics: 1. Audiovisual speaker identification; 2. Speaker diarization and clustering. C. Human-Computer Interaction: Emotive Audiovisual Avatars. D. Others: Video tracking, object recognition, event detection, etc Teaching Assistant, Rutgers University, English Department, New Brunswick, NJ, USA. Tutored undergraduate students from various departments with English 101 writing Research Assistant, Rutgers University, CAIP Center, Piscataway, NJ, USA. Participated in very low bit-rate speech coding research (a subcontract from Sarnoff Corp.). 2/6

3 Teacher, University of Science and Technology of China, Hefei, Anhui, China. Taught and assisted in teaching various undergraduate classes in electrical engineering Founding Member, Senior Software Engineer, Research Director, and Research Manager, Anhui USTC iflytek Co., Ltd. (Ke Da Xun Fei), Hefei, Anhui, China. Conducted R&D of practical text-to-speech (TTS) technologies and products. Major projects include: 1. Corpus-Based Chinese-English Mixed-Lingual Text-to-Speech Synthesis; 2. Corpus-Based Cantonese Text-to-Speech Synthesis; 3. Distributed Speech Synthesis; 4. An Intelligent Chinese Speech Platform; 5. The KD-Series Chinese Text-to-Speech Systems; 6. The Uni-Brain Intelligent Chinese Platform; 7. The Tian-Yin-Hua-Wang System. Journal Book Chapter Conference Recent Publications (2005 Present) [1] Hao Tang, Mark Hasegawa-Johnson, Thomas Huang, A Novel Vector Representation of Stochastic Signals for Pattern Recognition, submitted to IEEE Signal Processing Letters [2] Hao Tang, Stephen Chu, Mark Hasegawa-Johnson, Thomas Huang, Semi-supervised Speaker Clustering, submitted to IEEE Transactions on Multimedia (T-MM) (round 1 revision) [3] Xi Zhou, Xiaodan Zhuang, Hao Tang, Mark Hasegawa-Johnson, Thomas Huang, Novel Gaussianized Vector Representation for Improved Natural Scene Categorization, Pattern Recognition Letters, December, 2009 [4] Thomas Huang, Mark Hasegawa-Johnson, Stephen Chu, Zhihong Zeng, and Hao Tang, Sensitive Talking Heads, IEEE Signal Processing Magazine 26(4):67-72, July 2009 [5] Hao Tang, Yun Fu, Jilin Tu, Mark Hasegawa-Johnson, and Thomas S. Huang, Humanoid Audio-Visual Avatar with Emotive Text-To-Speech Synthesis, IEEE Transactions on Multimedia (T-MM), Volume: 10, Issue: 6, pp , October, 2008 [1] Yun Fu, Hao Tang, Jilin Tu, Hai Tao, and Thomas S. Huang, Human-Centered Face Computing in Multimedia Interaction and Communication, C.W. Chen, Z. Li, and S. Liang (Eds.), Intelligent Multimedia Communication: Techniques and Applications, Springer-Verlag, 2010 [1] Hao Tang, Mark Hasegawa-Johnson, Thomas Huang, HMM-based Affect Recognition from Non-frontal Facial Images with Universal Background Modeling, submitted to 2010 International Conference on Image Processing (ICIP 10) [2] Vuong Le, Hao Tang, Liangliang Cao, Thomas Huang, Accurate and Efficient Reconstruction of 3D Faces from Stereo Images, submitted to 2010 International Conference on Image Processing (ICIP 10) [3] Kai-Hsiang Lin, Hao Tang, Thomas Huang, Robust License Plate Detection Using Image Saliency, submitted to 2010 International Conference on Image Processing (ICIP 10) [4] Hao Tang, Mark Hasegawa-Johnson, Thomas Huang, Non-frontal View Facial Expression Recognition Based on Ergodic Hidden Markov Model Supervectors, submitted to 2010 International Conference on Multimedia & Expo (ICME 10) [5] Wenming Zheng, Hao Tang, Zhouchen Lin, Thomas Huang, Emotion Recognition from Arbitrary View Facial Images, submitted to 2010 International Conference on Computer Vision and Pattern Recognition (CVPR 10) 3/6

4 [6] Hao Tang, Mark Hasegawa-Johnson, Thomas Huang, Toward Robust Learning of the Gaussian Mixture State Emission Densities for Hidden Markov Models, submitted to 2010 International Conference on Acoustics, Speech, and Signal Processing (ICASSP 10) (accepted) [7] Wenming Zheng, Hao Tang, Zhouchen Lin, Thomas Huang, A Novel Approach to Expression Recognition from Non-frontal Face Images, 2009 International Conference on Computer Vision (ICCV 09), Kyoto, Japan, September, 2009 [8] Hao Tang, Stephen Chu and Thomas Huang, Spherical Discriminant Analysis in Semisupervised Speaker Clustering, North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT) 2009 Conference, Boulder, CO, June, 2009 [9] Stephen M. Chu, Hao Tang, Thomas S. Huang, Locality Preserving Speaker Clustering, 2009 International Conference on Multimedia & Expo (ICME 09), New York, NY, June, 2009 [10] Hao Tang, Stephen M. Chu, Mark Hasegawa-Johnson, Thomas S. Huang, Emotion Recognition from Speech via Boosted Gaussian Mixture Models, 2009 International Conference on Multimedia & Expo (ICME 09), New York, NY, June, 2009 [11] Stephen M. Chu, Hao Tang, Thomas S. Huang, Fishervoice and Semi-supervised Speaker Clustering, 2009 International Conference on Acoustics, Speech, and Signal Processing (ICASSP 09), Taipei, Taiwan, April, 2009 [12] Hao Tang, Stephen M. Chu, Thomas S. Huang, Generative Model-based Speaker Clustering via Mixture of von Mises-Fisher Distributions, 2009 International Conference on Acoustics, Speech, and Signal Processing (ICASSP 09), Taipei, Taiwan, April, 2009 [13] Hao Tang and Thomas S. Huang, Boosting Gaussian Mixture Models via Discriminant Analysis, 2008 IEEE International Conference on Pattern Recognition (ICPR 08), Tempa, FL, December, 2008 [14] Xi Zhou, Xiaodan Zhuang, Hao Tang, Mark Hasegawa-Johnson, Thomas Huang, A Novel Gaussianized Vector Representation for Natural Scene Categorization, 2008 IEEE International Conference on Pattern Recognition (ICPR 08), Tempa, FL, December, 2008 (IBM Best Student Paper Award) [15] Hao Tang and Thomas S. Huang, MPEG4 Performance-Driven Avatar via Robust Facial Motion Tracking, 2008 IEEE International Conference on Image Processing (ICIP 08), San Diego, CA, October, 2008 [16] Jianchao Yang, Hao Tang, Yi Ma, Thomas Huang, Face Hallucination via Sparse Coding, 2008 IEEE International Conference on Image Processing (ICIP 08), San Diego, CA, October, 2008 [17] Hao Tang, Xi Zhou, Matthias Odisio, Mark Hasegawa-Johnson, and Thomas S. Huang, Two- Stage Prosody Prediction for Emotional Text-to-Speech Synthesis, INTERSPEECH 2008, Brisbane, Australia, September, 2008 [18] Hao Tang and Thomas S. Huang, 3D Facial Expression Recognition Based on Properties of Line Segments Connecting Facial Feature Points, 2008 IEEE International Conference on Automatic Face and Gesture Recognition (FG 08), Amsterdam, The Neitherlands, September, 2008 [19] Hao Tang and Thomas S. Huang, 3D Facial Expression Recognition Based on Automatically Selected Features, 2008 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 08) (Workshop on 3D Face Processing), Anchorage, Alaska, June, /6

5 [20] Hao Tang, Yuxiao Hu, Yun Fu, Mark Hasegawa-Johnson, and Thomas S. Huang, Real-Time Conversion from a Single 2D Face Image to a 3D Text-Driven Emotive Audio-Visual Avatar, 2008 IEEE International Conference on Multimedia & Expo (ICME 08), Hannover, Germany, June 2008 [21] Yuxiao Hu, Hao Tang, and Thomas S. Huang, Camera and Microphone Array for 3D Audiovisual Face Data Collection, 2008 International Conference on Acoustics, Speech, and Signal Processing (ICASSP 08), Las Vegas, Nevada, March, 2008 [22] Hao Tang, Zhixiong Chen, and Thomas S. Huang, Comparison of Algorithms for Speaker Identification under Adverse Far-Field Recording Conditions with Extremely Short Utterances, Proc IEEE International Conference On Networking, Sensing and Control (ICNSC 08), pp , Sanya, China, April, 2008 [23] Hao Tang, Yun Fu, Jilin Tu, Thomas S. Huang, and Mark Hasegawa-Johnson, EAVA: A 3D Emotive Audio-Visual Avatar, 2008 IEEE Workshop on Applications of Computer Vision (WACV 08), Copper Mountain, CO, January, 2008 [24] Xi Zhou, Xiaodan Zhuang, Ming Liu, Hao Tang, Mark Hasgeawa-Johnson, and Thomas Huang, HMM-Based Acoustic Event Detection with AdaBoost Feature Selection, Proc. CLEAR Evaluation and Workshop (Classification of Events, Activities, and Relationships), Baltimore, MD, May, 2007 [25] Huazhong Ning, Ming Liu, Hao Tang, and Thomas Huang, A Spectral Learning Approach to Speaker Diarization, Proc. Ninth International Conference on Spoken Language Processing (ICSLP 06), Pittsburgh, PA, September, 2006 [26] Ming Liu, Hao Tang, Huazhong Ning, and Thomas Huang, Person Identification Based on Multichannel and Multimodality Fusion, Proc. CLEAR Evaluation and Workshop (Classification of Events, Activities, and Relationships), Southampton, UK, April, 2006 [27] Hao Tang and Thomas Huang, Improved Graphical Model for Audiovisual Object Tracking, Proc IEEE International Conference on Multimedia & Expo (ICME 06), pp , Toronto, Canada, July, 2006 [28] Zhixiong Chen and Hao Tang, Sparse Bayesian Approach to Classification, Proc IEEE International Conference on Networking, Sensing and Control (ICNSC 05), pp , Tucson, AZ, March, 2005 Patents Hao Tang and Bo Yin, A Data Exchange Format for Speech Synthesis, # , granted, China, 2005 Hao Tang and Bo Yin, A Distributed Speech Synthesis System, # X, granted, China, 2002 Hao Tang and Bo Yin, A Distributed Speech Synthesis Method, # , granted, China, 2002 Professional Activities Reviewer, IEEE Trans. on Pattern Analysis and Machine Intelligence (T-PAMI) Reviewer, IEEE Trans. on Audio, Speech and Language Processing (T-ASLP) Reviewer, IEEE Trans. on Circuits and Systems for Video Technology (T-CSVT) Reviewer, International Journal of Image and Graphics 5/6

6 Reviewer, Neurocomputing Reviewer, IEEE Signal Processing Letters Reviewer, Pattern Recognition Student Member, Institute of Mathematical Statistics (IMS) Student Member, IEEE Computer Skills Languages Tools Platforms Experiences C, C++, C++/CLI, C#, Java, MATLAB, Python, etc. MFC,.NET, OpenGL, OpenCV, HTK, Attila (IBM HMM/ASR Toolkit), etc. Windows, Unix/Linux (professional level). Over 15 years of programming experience in C and C++. 5 years of work experience as a senior software engineer at a high-tech company. Graduate Courses (grade & title) University of Illinois at Urbana-Champaign A+ Mathematical Models of Language A+ Random Processes A Image Processing A Computer Vision A+ Fundamentals of Speech Processing A Pattern Recognition A Machine Learning A+ Digital Signal Processing I B+ Digital Signal Processing II A Image and Neuroimage Processing A Fundamentals of Engineering Acoustics A Electromagnetic Waves and Radiating Systems Rutgers University A Digital Signals and Filters A Optimum Signal Processing A Digital Speech Processing A Advanced Topics in DSP A Computer Vision A Parallel and Distributed Computing A Data Structures and Algorithms A Numerical Analysis A Linear Algebra and Applications A Digital Spectral Analysis A Random Signals and Systems 6/6

Changjiang Yang. Computer Vision, Pattern Recognition, Machine Learning, Robotics, and Scientific Computing.

Changjiang Yang. Computer Vision, Pattern Recognition, Machine Learning, Robotics, and Scientific Computing. Changjiang Yang Mailing Address: Department of Computer Science University of Maryland College Park, MD 20742 Lab Phone: (301)405-8366 Cell Phone: (410)299-9081 Fax: (301)314-9658 Email: yangcj@cs.umd.edu