Thomas Huang

Face Age Estimation Using Patch-based Hidden Markov Model Supervectors (2009)

Xiaodan Zhuang, Xi Zhou, Mark Hasegawa-johnson, Thomas Huang

Recent studies in patch-based Gaussian Mixture Model (GMM) approaches for face age estimation present promising results. We propose using a hidden Markov model (HMM) supervector to represent face...

Dysarthric Speech Database for Universal Access Research (2009)

Heejin Kim, Mark Hasegawa-johnson, Adrienne Perlman, Jon Gunderson, Thomas Huang, Kenneth Watkin, ...

This paper describes a database of dysarthric speech produced by 19 speakers with cerebral palsy. Speech materials consist of 765 isolated words per speaker: 300 distinct uncommon words and 3...

General Terms (2008)

Maja Pantic, Nicu Sebe, Jeffrey F. Cohn, Thomas Huang

Social and emotional intelligence are aspects of human intelligence that have been argued to be better predictors than IQ for measuring aspects of success in life, especially in social interactions,...

Bimodal Emotion Recognition (2008)

Nicu Sebe, Erwin Bakker, Ira Cohen, Theo Gevers, Thomas Huang

Recent technological advances have enabled human users to interact with computers in ways previously unimaginable. Beyond the confines of the keyboard and mouse, new modalities for human-computer...

Dissertation: Geometric Principles of Visual Sensor Networks (2008)

Kun Huang, Yi Ma (advisor, Thomas Huang, Robert Fossum, Yizhou Yu

1. multiple-view geometry, feature matching and tracking 2. higher-level knowledge computing and photo editing 3. image segmentation and compression 4. video event detection and compression 5. object...

Audio-Visual Speaker Localization Using Graphical Models (2008)

Akash Kushal, Mandar Rahurkar, Li Fei-fei, Jean Ponce, Thomas Huang

In this work we propose an approach to combine audio and video modalities for person tracking using graphical models. We demonstrate a principled and intuitive framework for combining these...

CALIBRATING HEAD POSE ESTIMATION IN VIDEOS FOR MEETING ROOM EVENT ANALYSIS (2008)

Jilin Tu, Thomas Huang

In this paper, we study the calibration of head pose estimation in stereo camera setting for meeting room video event analysis. Head pose information infers the direction of attention of the subjects...

Fisher Analysis (MFA) and Local Discriminant Embedding (2008)

Deng Cai, Xiaofei He, Yuxiao Hu, Jiawei Han, Thomas Huang

Subspace learning based face recognition methods have attracted considerable interests in recently years, including

General Terms (2008)

Maja Pantic, Nicu Sebe, Jeffrey F. Cohn, Thomas Huang

Social and emotional intelligence are aspects of human intelligence that have been argued to be better predictors than IQ for measuring aspects of success in life, especially in social interactions,...

INDECISIVE CLASSIFIER (2008)

Zhenqiu Zhang, Xun Xu, Thomas Huang

Nearest neighbor classification expects the class conditional probabilities to be locally constant. The assumption becomes invalid in high dimension due to the curse-of-dimensionality. Severe bias...

Breaking the Clock Face HIP (2008)

Zhenqiu Zhang, Yong Rui, Thomas Huang, Cem Paya

Web services designed for human users are being abused by computer programs (bots). The bots steal thousands of free email accounts in a minute, participate in online polls to skew results, and...

BASIS PURSUIT FOR TRACKING (2008)

Roy Ruoyu Wang, Yunqiang Chen, Thomas Huang

This paper introduces a novel adaptive texture feature selection algorithm for tracking. Specifically, we provide a statistical wavelet basis paradigm to maximally separate statistical...

OVERVIEW: AN INTEGRATED FRAMEWORK FOR PERFORMANCE ENGINEERING AND RESOURCE-AWARE COMPILATION 1 (2008)

William H. S, Constantine Polychronopoulos, Thomas Huang, Tod Courtney, David Daly, Dan Deavours, ...

www.crhc.uiuc.edu/PERFORM/NSF.html Abstract ⎯ Design of next-generation computing and communication systems will be application-driven, and requires fundamental advances in 1) performance...

Machine Understanding of Human Behavior � (2008)

Maja Pantic, Alex Pentl, Anton Nijholt, Thomas Huang

A widely accepted prediction is that computing will move to the background, weaving itself into the fabric of our everyday living spaces and projecting the human user into the foreground. If this...

Transductive Regression Piloted by Inter-Manifold Relations (2008)

Huan Wang, Shuicheng Yan, Thomas Huang, Jianzhuang Liu, Xiaoou Tang

In this paper, we present a novel semisupervised regression algorithm working on multiclass data that may lie on multiple manifolds. Unlike conventional manifold regression algorithms that do not...

-D Reconstruction of Multipart Self-Occluding Objects (2007)

Nebojsa Jojic, Jin Gu, Helen C. Shen, Thomas Huang

. In this paper we present a method for reconstruction of multipart objects from several arbitrary views using deformable superquadrics as the models of the object's parts. Two visual cues are...

BASIS PURSUIT FOR TRACKING (2007)

Roy Ruoyu Wang, Yunqiang Chen, Thomas Huang

This paper introduces a novel adaptive texture feature selection algorithm for tracking. Specifically, we provide a statistical wavelet basis paradigm to maximally separate statistical...

Memory-based moving object extraction for video indexing (2007)

Roy Ruoyu Wang, Pengyu Hong, Thomas Huang

Extracting moving objects from a video shot provides a good low-level representation of videos. It provides object trajectory, color, shape characteristics. Combined with specific domain knowledge,...

2 (2007)

Baback Moghaddam, Qi Tian, Neal Lesh, Chia Shen, Thomas Huang

Abstract. In this paper, we present visualization and layout algorithms that can enhance informal storytelling using personal digital data such as photos in a face-to-face social setting. In order to...

Feature Article Applications of Video-Content Analysis and Retrieval Managing (2007)

Nevenka Dimitrova, Hong-jiang Zhang, Behzad Shahraray, Ibrahim Sezan, Thomas Huang, Avideh Zakhor

multimedia data requires more than collecting the data into storage archives and delivering it via networks to homes or offices. We survey technologies and applications for video-content analysis and...

Incremental spectral clustering with application to monitoring of evolving blog communities (2007)

Huazhong Ning, Wei Xu, Yun Chi, Yihong Gong, Thomas Huang

In recent years, spectral clustering method has gained attentions because of its superior performance compared to other traditional clustering algorithms such as K-means algorithm. The existing...

HMM-based acoustic event detection with AdaBoost feature selection (2007)

Xi Zhou, Xiaodan Zhuang, Ming Liu, Hao Tang, Mark Hasegawa-johnson, Thomas Huang

Abstract. Because of the spectral difference between speech and acoustic events, we propose using Kullback-Leibler distance to quantify the discriminant capability of all speech feature components in...

A Convergent Solution to Tensor Subspace Learning (2007)

Huan Wang, Shuicheng Yan, Thomas Huang, Xiaoou Tang

Recently, substantial efforts have been devoted to the subspace learning techniques based on tensor representation, such as 2DLDA [Ye et al., 2004], DATER [Yan et al., 2005] and Tensor Subspace...

Human Computing and Machine Understanding of Human Behavior: A Survey (2006)

Maja Pantic, Alex Pentl, Anton Nijholt, Thomas Huang

A widely accepted prediction is that computing will move to the background, weaving itself into the fabric of our everyday living spaces and projecting the human user into the foreground. If this...

T.: Head Pose Estimation in Seminar Rooms Using Multi View Face Detectors (2006)

Zhenqiu Zhang, Yuxiao Hu, Ming Liu, Thomas Huang

Head pose estimation in low resolution is a challenge problem. Traditional pose estimation algorithms, which assume faces have been well aligned before pose estimation, would face much difficulty in...

Human Computing and Machine Understanding of Human Behavior: A Survey (2006)

Maja Pantic, Alex Pentl, Anton Nijholt, Thomas Huang

A widely accepted prediction is that computing will move to the background, weaving itself into the fabric of our everyday living spaces and projecting the human user into the foreground. If this...

HMM-Based and SVM-Based Recognition of the Speech of Talkers with Spastic Dysarthria (2006)

Mark Hasegawa-johnson, Jonathan Gunderson, Adrienne Perlman, Thomas Huang

This paper studies the speech of three talkers with spastic dysarthria caused by cerebral palsy. All three subjects share the symptom of low intelligibility, but causes differ. First, all subjects...

Data processing pipeline with transaction-oriented data sharing (2005)

Huang, Thomas, Preheim, Larry

This paper makes three contributions to the area of modern science data processing systems. First, the paper describes the science data processing pipeline, developed at the Multi-mission Image...

VACE multimodal meeting corpus (2005)

Lei Chen, R. Travis Rose, Ying Qiao, Irene Kimbara, Fey Parrill, Tony Xu Han, ...

Abstract. In this paper, we report on the infrastructure we have developed to support our research on multimodal cues for understanding meetings. With our focus on multimodality, we investigate the...

VACE multimodal meeting corpus (2005)

Lei Chen, R. Travis Rose, Fey Parrill, Xu Han, Jilin Tu, Mary Harper, ...

Abstract. In this paper, we report on the infrastructure we have developed to support our research on multimodal cues for understanding meetings. With our focus on multimodality, we investigate the...

T.S.: Online updating appearance generative mixture model for meanshift tracking (2005)

Jilin Tu, Thomas Huang, Elec Engr Dept

Abstract. This paper proposes an appearance generative mixture model based on key frames for meanshift tracking. Meanshift tracking algorithm tracks object by maximizing the similarity between the...

AVICAR: Audio-visual speech corpus in a car environment (2004)

Bowon Lee, Mark Hasegawa-johnson, Camille Goudeseune, Suketu Kamdar, Sarah Borys, Ming Liu, ...

We describe a large audio-visual speech corpus recorded in a car environment, as well as the equipment and procedures used to build this corpus. Data are collected through a multi-sensory array...

Joint Design of Data Analysis Algorithms and User Interface for Video Applications (2003)

Jojic, Nebojsa, Basu, Sumit, Petrovic, Nemanja, Frey, Brendan, Huang, Thomas

The graphical modeling paradigm provides a way of representing data through hidden causes of variability which can be estimated from the data in an unsupervised manner. Recently, a lot of research...

Component architecture: The software architecture for mission requirements, paper presented at (2003)

Thomas Huang

Software reuse is a common strategy in developing complex systems and has proven successful in reducing labor and maintenance costs. However, simply reusing modules will not produce a system that is...

Joint Design of Data Analysis Algorithms and User (2003)

Interface For Video, Nebojsa Jojic, Sumit Basu, Thomas Huang, Nemanja Petrovic, Brendan Frey

The graphical modeling paradigm provides a way of representing data through hidden causes of variability which can be estimated from the data in an unsupervised manner. Recently a lot of research has...

Visualization and layout for personal photo libraries (2003)

Baback Moghaddam, Qi Tian, Neal Lesh, Chia Shen, Thomas Huang

Abstract. In this paper, we present visualization and layout algorithms that can enhance informal storytelling using personal digital data such as photos in a face-to-face social setting. In order to...

Facial expression recognition: a clustering-based approach (2003)

Xue-wen Chen, Thomas Huang

This paper describes a new clustering based feature extraction method for facial expression recognition. We demonstrate the effectiveness of this method and compare it with commonly used principal...

The uptake of tocopherols by RAW 264.7 macrophages (2002)

Gao, Rong, Stone, William L, Huang, Thomas, Papas, Andreas M, Qui, Min

Abstract Background Alpha-Tocopherol and gamma-tocopherol are the two major forms of vitamin E in human plasma and the primary lipid soluble antioxidants. The dietary intake of gamma-tocopherol is...

Generative and discriminative face modeling for detection (2002)

Ruoyu Roy Wang, Thomas Huang

This paper reports a new image model combining self mutual information based generative modelling and fisherdiscriminant based discriminative modelling. Past work on face modelling have focused...

Parametric contour tracking using unscented kalman filter (2002)

Yunqiang Chen, Thomas Huang

This paper presents an efficient method to integrate various spatial-temporal constraints to regularize the contour tracking. Specifically, the global shape prior, contour smoothness and object...

Fertilization and embryo development in a mouse ICSI model using human and mouse sperm after immobilization in polyvinylpyrrolidone (2002)

Mizuno, Kaoruko, Hoshi, Kazuhiko, Huang, Thomas

BACKGROUND: For human ICSI, sperm are normally immobilized immediately prior to injection. However, there are some situations when only sperm of questionable viability are available. There are few...

ICA-based Probabilistic Local Appearance Models (2001)

Xiang Zhou, Thomas Huang, Xiang Sean Zhou, Baback Moghaddam, Baback Moghaddam, Thomas S. Huang

This paper proposes a novel image modeling scheme for object detection and localization. Object appearance is modeled by the joint distribution of k-tuple salient point feature vectors which are...

ICA-based Probabilistic Local Appearance Models (2001)

Xiang Zhou, Thomas Huang, Xiang Sean Zhou, Baback Moghaddam, Baback Moghaddam, Thomas S. Huang

This paper proposes a novel image modeling scheme for object detection and localization. Object appearance is modeled by the joint distribution of k-tuple salient point feature vectors which are...

On probabilistic semantic video indexing (2000)

Milind R. Naphade, Igor Kozintsev, Thomas Huang

We propose a novel probabilistic framework for semantic video indexing. We define probabilistic multimedia objects (multijects) to map low-level media features to high-level semantic labels. A...

Interactive and incremental learning via a mixture of supervised and unsupervised learning strategies (2000)

Qiong Liu, Stephen Levinson, Ying Wu, Thomas Huang

Machine learning paradigms are generally separated into supervised learning and unsupervised learning. Both of these paradigms have their own advantages in practice. But existing algorithms of these...

Interactive and incremental learning via a mixture of supervised and unsupervised learning strategies (2000)

Qiong Liu, Stephen Levinson, Ying Wu, Thomas Huang

Machine learning paradigms are generally separated into supervised learning and unsupervised learning. Both of these paradigms have their own advantages in practice. But existing algorithms of these...

Optimizing Learning in Image Retrieval (2000)

Yong Rui, Thomas Huang

Combining learning with vision techniques in interactive image retrieval has been an active research topic during the past few years. However, existing learning techniques either are based on...

Interactive and incremental learning via a mixture of supervised and unsupervised learning strategies (2000)

Qiong Liu, Stephen Levinson, Ying Wu, Thomas Huang

Machine learning paradigms are generally separated into supervised learning and unsupervised learning. Both of these paradigms have their own advantages in practice. But existing algorithms of these...

10th Workshop �Theoretical Foundations of Computer Vision" Multi-Image Search, Filtering, Reasoning and (2000)

Alfred Bruckstein, Thomas Huang, Reinhard Klette, Songde Ma, R. Klette, Y. Aloimonos, ...

Many problems in computer vision involve multiple images. These could be im-ages taken by multiple cameras of the same scene, video sequences or multispectral images, etc. This workshop was concerned...

Detection and Estimation of Pointing Gestures in Dense Disparity Maps (2000)

Nebojsa Jojic, Barry Brumitt, Brian Meyers, Steve Harris, Thomas Huang

In this paper we describe a real-time system for detecting pointing gestures and estimating the direction of pointing using stereo cameras. Previously, similar systems where implemented using...

Optimizing learning in image retrieval (2000)

Yong Rui, Thomas Huang

Combining learning with vision techniques in interactive image retrieval has been an active research topic during the past few years. However, existing learning techniques either are based on...

Design and implementation of DOSS /--by Thomas Huang. (1999)

Huang, Thomas.

Thesis (M.S.)--California State University, Northridge, 1999.

HETEROJUNCTION DEVICES. (1998)

Anderson,Richard L., Zeidenbergs,Girtz, Huang,Thomas, Boyce,David, Davis,Mark

Heterojunctions were prepared by depositing Si epitaxially onto GaAs and GaP substrates using silicon-tellurium compounds as transporting agents. The experimental results are in agreement with the...

3-D reconstruction of multipart self-occluding objects (1998)

Jojic, Nebojsa, Gu, Jin, Shen, Helen C., Huang, Thomas

In this paper we present a method for reconstruction of multipart objects from several arbitrary views using deformable superquadrics as the models of the object's parts. Two visual cues are used:...

Event-coupled hidden Markov models (1998)

Trausti T. Kristjansson, Brendan J. Frey, Thomas Huang

Inferences from time-series data can be greatly enhanced by taking into account multiple modalities. In some cases, such as audio of speech and the corresponding video of lip gestures, the different...