A Fast 2D Shape Recovery Approach by Fusing Features and Appearance (2009)
Jianke Zhu, Michael R. Lyu, Thomas S. Huang, Life Fellow
Abstract—In this paper, we present a fusion approach to solve the nonrigid shape recovery problem, which takes advantage of both the appearance information and the local features. We have two major...
EMOTION RECOGNITION FROM SPEECH VIA BOOSTED GAUSSIAN MIXTURE MODELS (2009)
Hao Tang, Stephen M. Chu, Mark Hasegawa-johnson, Thomas S. Huang
Gaussian mixture models (GMMs) and the minimum error rate classifier (i.e. Bayesian optimal classifier) are popular and effective tools for speech emotion recognition. Typically, GMMs are used to...
A Survey of Affect Recognition Methods: Audio, Visual, and Spontaneous Expressions (2009)
Zhihong Zeng, Ieee Computer Society, Maja Pantic, Senior Member, Glenn I. Roisman, Thomas S. Huang
Abstract—Automated analysis of human affective behavior has attracted increasing attention from researchers in psychology, computer science, linguistics, neuroscience, and related disciplines....
FEATURE ANALYSIS AND SELECTION FOR ACOUSTIC EVENT DETECTION (2009)
Xiaodan Zhuang, Xi Zhou, Thomas S. Huang, Mark Hasegawa-johnson
Speech perceptual features, such as Mel-frequency Cepstral Coefficients (MFCC), have been widely used in acoustic event detection. However, the different spectral structures between speech and...
Two-Stage Prosody Prediction for Emotional Text-to-Speech Synthesis (2009)
Hao Tang, Xi Zhou, Matthias Odisio, Mark Hasegawa-johnson, Thomas S. Huang
In this paper, we adopt a difference approach to prosody prediction for emotional text-to-speech synthesis, where the prosodic variations between emotional and neutral speech are decomposed into the...
A Novel Gaussianized Vector Representation for Natural Scene Categorization (2009)
Xi Zhou, Xiaodan Zhuang, Hao Tang, Mark Hasegawa-johnson, Thomas S. Huang
This paper presents a novel Gaussianized vector representation for scene images by an unsupervised approach. First, each image is encoded as an ensemble of orderless bag of features, and then a...
A PIECEWISE BÉZIER VOLUME DEFORMATION MODEL AND ITS APPLICATIONS IN FACIAL MOTION CAPTURE (2009)
Capturing real facial motions from videos enables automatic creation of dynamic models for facial animation. In this paper, we propose an explanation-based facial motion tracking algorithm based on a...
EFFICIENT ACCESS TO VIDEO CONTENT IN A UNIFIED FRAMEWORK (2009)
Yong Rui, Sean X. Zhou, Thomas S. Huang
Book contents ’ browsing and retrieval have been greatly facilitated by its Table-of-Contents (ToC) and Index, respectively. Unfortunately, today’s video lacks such powerful mechanisms. In this...
Zhihong Zeng, Yun Fu, Glenn I. Roisman, Zhen Wen, Yuxiao Hu, Thomas S. Huang
In this paper, we explore one-class classification application in recognizing emotional and nonemotional facial expressions occurred in a realistic human conversation setting--Adult Attachment...
Alok N. Choudhary, Mun K. Leung, Thomas S. Huang, Janak H. Patel, Security Classificationof, This Page
, Approved for public release; distribution unlimited
Models for Patch-Based Image Restoration (2009)
Mithun Das Gupta, Shyamsundar Rajaram, Nemanja Petrovic, Thomas S. Huang
We present a supervised learning approach for object-category specific restoration, recognition, and segmentation of images which are blurred using an unknown kernel. The novelty of this work is a...
Models for Patch-Based Image Restoration (2009)
Mithun Das Gupta, Shyamsundar Rajaram, Nemanja Petrovic, Thomas S. Huang
We present a supervised learning approach for object-category specific restoration, recognition, and segmentation of images which are blurred using an unknown kernel. The novelty of this work is a...
Visual Face Tracking and its Application to 3D Model-Based Video Coding (2008)
The MPEG4 standard supports the transmission and composition of facial animation with natural video by including a facial animation parameter (FAP) set that is defined based on the study of minimal...
Content-Based Image Retrieval by Feature Adaptation and Relevance Feedback (2008)
Anelia Grigorova, Senior Member, Charlie Dagli, Thomas S. Huang, Life Fellow
Abstract—The paper proposes an adaptive retrieval approach based on the concept of relevance-feedback, which establishes a link between high-level concepts and low-level features, using the...
Abstract Supporting Similarity Queries in MARS (2008)
Michael Ortega, Yong Rui, Kaushik Chakrabarti, Sharad Mehrotra, Thomas S. Huang
To address the emerging needs of applications that require access to and retrieval of multimedia objects, we are developing the Multimedia Analysis and Retrieval System (MARS) in our group at the...
Approved for Public Release. Distribution Unlimited. /4C/',,J. (2008)
Alok N. Choudhary, Mun K. Leung, Thomas S. Huang, Janak H. Patel
aml m UNCLA.5 S I F/LED SECURitY CL.ASS_FICAI'_ON O _ TInS PAGE I la. REPORT 'SECURITY CLASSIFICATION Unc lassi fled
Feature extraction and selection for image retrieval (2008)
Xiang Sean Zhou, Ira Cohen, Qi Tian, Thomas S. Huang
In this paper feature extraction process is analyzed and a new set of edge features is proposed. A revised edge-based structural feature extraction approach is introduced. A principle feature...
CHAPTER 1 MULTIMODAL EMOTION RECOGNITION (2008)
Nicu Sebe, Ira Cohen, Thomas S. 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...
GENERATIVE MODELS FOR COMPUTER VISION (2008)
Nebojsa Jojic, Thomas S. Huang, Brendan J. Frey
In order to build robust computer vision algorithms, scene models are necessary that are capable of capturing various aspects of the data at the same time. These models should be fairly simple, but...
Towards Authentic Emotion Recognition (2008)
Nicu Sebe, Yafei Sun, Erwin Bakker, Michael S. Lew, Ira Cohen, Thomas S. Huang
In human computer interaction, the ultimate goal is to have effortless and natural communication. In the research literature significant effort has been directed toward understanding the functional...
Factorization-based Non-rigid Shape Modeling and Tracking in Stereo-Motion (2008)
Yu Huang, Jilin Tu, Thomas S Huang
In recent years, researchers have tackled the topic of augmenting “structure from motion ” with stereo information. Unfortunately nearly all stereo-motion algorithms assume that the scene is...
NON-PARAMETRIC IMAGE SUPER-RESOLUTION USING MULTIPLE IMAGES (2008)
Mithun Das Gupta, Shyamsundar Rajaram, Nemanja Petrovic, Thomas S. Huang
In this paper, we present a novel learning based framework for performing super-resolution using multiple images. We model the image as an undirected graphical model over image patches in which the...
A FACTORIZATION METHOD IN STEREO MOTION FOR NON-RIGID OBJECTS (2008)
Yu Huang, Jilin Tu, Thomas S Huang
In this paper we propose a framework of factorization-based non-rigid shape modeling and tracking in stereo-motion. We construct a measurement matrix with the stereo-motion data captured from a...
Guest Editors ’ Introduction to the Special Section on Graphical Models in Computer Vision (2008)
James M. Rehg, Vladimir Pavlovic, Thomas S. Huang, William T. Freeman
THE last 10 years have witnessed rapid growth in the
A Survey of Affect Recognition Methods: Audio, Visual and Spontaneous Expressions (2008)
Zhihong Zeng, Maja Pantic, Glenn I. Roisman, Thomas S. Huang
Automated analysis of human affective behavior has attracted increasing attention from researchers in psychology, computer science, linguistics, neuroscience, and related disciplines. Promising...
A Realtime Shrug Detector (2008)
Huazhong Ning, Tony X. Han, Yuxiao Hu, Zhenqiu Zhang, Yun Fu, Thomas S. Huang
A realtime system for shrug detection is discussed in this paper. The system is automatically initialized by a face detector based on Ada-boost[14]. After frontal face is localized by the face...
Multicue HMM-UKF for realtime contour tracking (2008)
Yunqiang Chen, Yong Rui, Thomas S. Huang
We propose an HMM model for contour detection based on multiple visual cues in spatial domain and improve it by joint probabilistic matching to reduce background clutter. It is further integrated...
Two-Handed Gesture Tracking Incorporating Template Warping With Static Segmentation (2008)
Yu Huang, Thomas S. Huang, Heinrich Niemann
In this paper we present a template-based method of motion estimation which tracks two-handed-gestures. In our method the gesturing information of temporal motion and spatial luminance is fully...
Element Rearrangement for Tensor-Based Subspace Learning (2008)
Shuicheng Yan, Dong Xu, Stephen Lin, Thomas S. Huang, Shih-fu Chang
The success of tensor-based subspace learning depends heavily on reducing correlations along the column vectors of the mode-k flattened matrix. In this work, we study the problem of rearranging...
Conformal Embedding Analysis with Local Graph Modeling on the Unit Hypersphere (2008)
Yun Fu, Ming Liu, Thomas S. Huang
We present the Conformal Embedding Analysis (CEA) for feature extraction and dimensionality reduction. Incorporating both conformal mapping and discriminating analysis, CEA projects the...
Xiang Sean Zhou, Thomas S. Huang
We analyze the nature of the relevance feedback problem in a continuous representation space in the context of multimedia information retrieval. Emphasis is put on exploring the uniqueness of the...
Yong Rui, Thomas S. Huang, Michael Ortega, Sharad Mehrotra
Abstract | Content-Based Image Retrieval (CBIR) has become one of the most active research areas in the past few years. Many visual feature representations have been explored and many systems built....
© World Scientific Publishing Company. IFACE: A 3D SYNTHETIC TALKING FACE (2008)
Pengyu Hong, Zhen Wen, Thomas S. Huang
We present the iFACE system, a visual speech synthesizer that provides a form of virtual face-to-face communication. The system provides an interactive tool for the user to customize a graphic head...
Facial tracking is a key step for face modeling, coding and animation. In this paper we present a robust method of facial tracking in stereo vision. We use an efficient representation of 3-D face...
Xi Zhou, Yun Fu, Ming Liu, Mark Hasegawa-johnson, Thomas S. Huang
Mismatch between training and testing data is a major error source for both Automatic Speech Recognition (ASR) and Automatic Speaker Identification (ASI). In this paper, we first present a...
DOI 10.1007/s00530-005-0177-4 REGULAR PAPER (2008)
Nicu Sebe, Ira Cohen, Fabio G. Cozman, Theo Gevers, Thomas S. Huang
Learning probabilistic classifiers for human–computer
EAVA: A 3D Emotive Audio-Visual Avatar (2008)
Hao Tang, Yun Fu, Jilin Tu, Thomas S. Huang, Mark Hasegawa-johnson
Emotive audio-visual avatars have the potential of significantly improving the quality of Human-Computer Interaction (HCI). In this paper, the various technical approaches of a novel framework...
Visualization, Estimation and User-Modeling for Interactive Browsing (2008)
Qi Tian, Baback Moghaddam, Thomas S. Huang
Abstract. We present a user-centric system for visualization and layout for content-based image retrieval and browsing. Image features (visual and/or semantic) are analyzed to display and group...
QUERY DRIVEN LOCALIZED LINEAR DISCRIMINANT MODELS FOR HEAD POSE ESTIMATION (2008)
Zhu Li, Yun Fu, Junsong Yuan, Thomas S. Huang, Ying Wu
Head pose appearances under the pan and tilt variations span a high dimensional manifold that has complex structures and local variations. For pose estimation purpose, we need to discover the...
Abstract Towards Self-Exploring Discriminating Features for Visual Learning (2008)
Many visual learning tasks are usually confronted by some common difficulties. One of them is the lack of supervised information, due to the fact that labeling could be tedious, expensive or even...
EXPLORING DISCRIMINATIVE LEARNING FOR TEXT-INDEPENDENT SPEAKER RECOGNITION (2008)
Ming Liu, Zhengyou Zhang, Mark Hasegawa-johnson, Thomas S. Huang
Speaker verification is a technology of verifying the claimed identity of a speaker based on the speech signal from the speaker (voice print). To learn the score of similarity between each pair of...
COMMON SPATIAL PATTERN DISCOVERY BY EFFICIENT CANDIDATE PRUNING (2008)
Junsong Yuan, Zhu Li, Yun Fu, Ying Wu, Thomas S. Huang
Automatically discovering common visual patterns in images is very challenging due to the uncertainties in the visual appearances of such spatial patterns and the enormous computational cost involved...
Abstract Visualization & Layout for Image Libraries (2008)
Baback Moghaddam, Qi Tian, Neal Lesh, Chia Shen, Thomas S. Huang
can enhance informal storytelling using personal digital data such as photos in a face-to-face social setting. In order to build a more intuitive browser for retrieval, navigation and story-telling,...
LEARNING BASED ON KERNEL DISCRIMINANT-EM ALGORITHM FOR IMAGE CLASSIFICATION (2008)
Qi Tian, Jie Yu, Ying Wu, Thomas S. Huang
In image classification and other learning-based object recognition tasks, it is often tedious and expensive to label large training data sets. Discriminant-EM (DEM) proposed a semi-supervised...
Articulate Hand Motion Capturing Based on a Monte Carlo Nelder-Mead Simplex Tracker (2008)
This paper presents an algorithm for tracking the articulate hand motion in monocular video sequences. The task is challenging due to the high degrees of freedom involved in the hand motion. The...
Frequency Domain Correspondence for Speaker Normalization (2008)
Ming Liu, Xi Zhou, Mark Hasegawa-johnson, Thomas S. Huang
Due to physiology and linguistic difference between speakers, the spectrum pattern for the same phoneme of two speakers can be quite dissimilar. Without appropriate alignment on the frequency axis,...
Ro Jaimes, Daniel Gatica-perez, Nicu Sebe, Thomas S. Huang
Human-centered computing studies the design, development, and deployment of mixed-initiative human-computer systems. HCC is emerging from the convergence of multiple disciplines that are concerned...
Computer Modeling, Analysis and Synthesis of Dressed Humans (2008)
Nebojsa Jojic, Jin Gu, Helen C. Shen, Thomas S. Huang
1 In this paper we present computer vision techniques for building dressed human models using images. In the first part of the paper we develop an algorithm for 3-D body reconstruction and texture...
Hierarchical Space-time Model Enabling Efficient Search for Human Actions (2008)
Huazhong Ning, Tony X. Han, Dirk B. Walther, Ming Liu, Thomas S. Huang
We propose a five-layer hierarchical space-time model (HSTM) for representing and searching human actions in videos. From a feature point of view, both invariance and selectivity are desirable...
Gregory A. Berry, Vladimir I. Pavlovi'c, Thomas S. Huang
To further the advances in Human Computer Intelligent Interaction (HCII), we employ an approach to integrate two modes of humancomputer communication to control a virtual environment. By using...
A NEW APPROACH TO INTEGRATE AUDIO AND VISUAL FEATURES OF SPEECH (2007)
Hao Pan, Zhi-pei Liang, Thomas S. Huang
This paper presents a novel fused-hidden Markov model (fused-HMM) to integrate the audio and visual features of speech. In this model, audio and visual HMMs built individually are fused together...
Sampling Based EM Algorithm (2007)
Ashutosh Garg, Ira Cohen, Thomas S. Huang
A sampling based EM algorithm is proposed. The algorithm tries to add some randomness to the likelihood function thereby increasing the chances of the convergence of the EM algorithm to the true...
Supporting Ranked Boolean Similarity Queries in MARS (2007)
Sharad Mehrotra, Thomas S. Huang
Abstract---To address the emerging needs of applications that require access to and retrieval of multimedia objects, we are developing the Multimedia Analysis and Retrieval System (MARS) [29]. In...
Thang C. Nguyen, David E. Goldberg, Thomas S. Huang
: We present a system that lets 3--D models evolve over time, eventually produce novel models that are more desirable than initial models. The algorithm starts with some crude models given by the...
Fractal-Based Image And Video Coding (2007)
Mohammad Gharavi-alkhansari, Thomas S. Huang
This chapter reviews the theoretical foundations and implementation issues of fractalbased image coding methods. The concepts of fractals, iterated function systems, and local iterated function...
Applying Semantic Association To Support Content-Based Video Retrieval (2007)
Yueting Zhuangy, Yong Rui, Thomas S. Huang, Sharad Mehrotra
The traditional approach to video retrieval is to first annotate the video by textual information (titles and key words) and then the queries will be searched based on this keyword set. Since...
Storage of Images and Video in Database Systems (2007)
Sergio D. Servetto, Kannan Ramchandran, Thomas S. Huang, Sergio Servetto
We consider the problem of constructing indices to image and video data analogous to those used in classical database systems, in order to speed up the retrieval of such data from physical storage...
Gregory A. Berry, Thomas S. Huang, Lalitha Devi, Yogesh Sethi, Rajeev Sharma
Although computer technology has dramatically changed in the last 20 years, human-computer interfaces have largely remained unchanged. The keyboard has been the most prevalent device, but with the...
Computer Modeling, Analysis and Synthesis of Dressed Humans (2007)
Nebojsa Jojic, Jin Gu, Ivan Mak, Helen C. Shen, Thomas S. Huang
1 In this paper we present a method for 3-D reconstruction of human bodies with application in CAD systems for garment design. The reconstruction scheme uses image information from several arbitrary...
Abstract A short version appeared in IWCIA 2001. Automatic Contextual Pattern Modeling (2007)
An object/scene usually consists of several primitives among which various contextual relations are defined. In this work, an object/scene is defined as a contextual pattern and is represented by an...
1 Feature Extraction and Selection for Image Retrieval (2007)
Xiang Sean Zhou, Ira Cohen, Qi Tian, Thomas S. Huang
In this paper feature extraction process is analyzed and a new set of edge features is proposed. A revised edge-based structural feature extraction approach is introduced. A principle feature...
Qi Tian, Baback Moghaddam, Thomas S. Huang
In this paper, we propose a technique to visualize a multitude of images on a 2-D screen based on their visual features (color, texture, structure, etc.). The resulting layout will automatically...
Multimodal Pattern Matching for Audio-Visual Query and (2007)
Retrieval Milind Naphade, Milind R. Naphade, Roy Wang, Thomas S. Huang
A necessary capability for content-based retrieval is to support the paradigm of query by example. In the past, there have been several attempts to use low-level features for video retrieval. None of...
Semi-Supervised Learning for Facial Expression (2007)
Recognition Ira Cohen, Ira Cohen, Nicu Sebe, Fabio G. Cozman, Thomas S. Huang
Automatic classification by machines is one of the basic tasks required in any pattern recognition and human computer interaction applications. In this paper, we discuss training probabilistic...
The State-of-the-Art in Human-Computer Interaction (2007)
Nicu Sebe, Michael S. Lew, Thomas S. Huang
Human computer interaction (HCI) lies at the crossroads of many scientific areas including artificial intelligence, computer vision, face recognition, motion tracking, etc. In recent years there has...
Skin Detection: A Bayesian Network Approach (2007)
Nicu Sebe, Ira Cohen, Thomas S. Huang, Theo Gevers
The automated detection and tracking of humans in computer vision necessitates improved modeling of the human skin appearance. In this paper we propose a Bayesian network approach for skin detection....
Audio-Visual Affect Recognition (2007)
Zhihong Zeng, Jilin Tu, Ming Liu, Thomas S. Huang, Brian Pianfetti, Dan Roth, ...
Abstract—The ability of a computer to detect and appropriately respond to changes in a user’s affective state has significant implications to Human–Computer Interaction (HCI). In this paper, we...
Mithun Das Gupta, Shyamsundar Rajaram, Thomas S. Huang, Nemanja Petrovic, Recommended Richard, R. Schultz
We present a supervised learning-based approach for subpixel motion estimation which is then used to perform video superresolution. The novelty of this work is the formulation of the problem of...
Lipreading by locality discriminant graph (2007)
Yun Fu, Xi Zhou, Ming Liu, Mark Hasegawa-johnson, Thomas S. Huang
The major problem in building a good lipreading system is to extract effective visual features from enormous quantity of video sequences data. For appearance-based feature analysis in lipreading,...
Event Detection Using “Variable Module Graphs” for Home Care Applications (2007)
Amit Sethi, Mandar Rahurkar, Thomas S. Huang
Technology has reached new heights making sound and video capture devices ubiquitous and affordable. We propose a paradigm to exploit this technology for home care applications especially for...
Ordinal Regression Based Subpixel Shift Estimation for Video Super-Resolution (2007)
Mithun Das Gupta, Shyamsundar Rajaram, Thomas S. Huang, Nemanja Petrovic
We present a supervised learning-based approach for subpixel motion estimation which is then used to perform video super-resolution. The novelty of this work is the formulation of the problem of...
Event Detection Using “Variable Module Graphs” for Home Care Applications (2007)
Amit Sethi, Mandar Rahurkar, Thomas S. Huang
Technology has reached new heights making sound and video capture devices ubiquitous and affordable. We propose a paradigm to exploit this technology for home care applications especially for...
Ordinal Regression Based Subpixel Shift Estimation for Video Super-Resolution (2007)
Mithun Das Gupta, Shyamsundar Rajaram, Thomas S. Huang, Nemanja Petrovic
We present a supervised learning-based approach for subpixel motion estimation which is then used to perform video super-resolution. The novelty of this work is the formulation of the problem of...
Spontaneous Emotional Facial Expression Detection (2006)
Zhihong Zeng, Yun Fu, Glenn I. Roisman, Zhen Wen, Yuxiao Hu, Thomas S. Huang
Abstract — Change in a speaker’s emotion is a fundamental component in human communication. Automatic recognition of spontaneous emotion would significantly impact human-computer interaction and...
T.: Efficient Nonparametric Belief Propagation with Application to Articulated Body Tracking (2006)
Tony X. Han, Huazhong Ning, Thomas S. Huang
An efficient Nonparametric Belief Propagation (NBP) algorithm is developed in this paper. While the recently proposed nonparametric belief propagation algorithm has wide applications such as...
Total variation models for variable lighting face recognition (2006)
Terrence Chen, Student Member, Wotao Yin, Xiang Sean Zhou, Thomas S. Huang
IEEE Computer Society,
Learning-Based Nonparametric Image Super-Resolution (2006)
Shyamsundar Rajaram, Mithun Das Gupta, Nemanja Petrovic, Thomas S. Huang
We present a novel learning-based framework for zooming and recognizing images of digits obtained from vehicle registration plates, which have been blurred using an unknown kernel. We model the image...
Data Compression Panel Discussion, (2005)
Schwartz,Jay W., Davisson,Lee D., Huang,Thomas S., Ziv,Jacob
Data compression, in the paper, is used to denote the reducing of an input data set prior to transmission, as opposed to data reduction, the analytical processing of the set upon reception. Source...
Analyzing and capturing articulated hand motion in image sequences (2005)
Ying Wu, John Lin, Thomas S. Huang
Abstract—Capturing the human hand motion from video involves the estimation of the rigid global hand pose as well as the nonrigid finger articulation. The complexity induced by the high degrees of...
Terrence Chen, Wotao Yin, Xiang Sean Zhou, Dorin Comaniciu, Thomas S. Huang
We present a new algorithm for illumination normalization and uneven background correction in images, utilizing the recently proposed TV+L 1 model: minimizing the total variation of the output...
T.S.: Articulated body tracking using dynamic belief propagation (2005)
Abstract. An efficient articulated body tracking algorithm is proposed in this paper. Due to the high dimensionality of human-body motion, current articulated tracking algorithms based on sampling...
Locally Linear Embedded Eigenspace Analysis (2005)
The existing nonlinear local methods for dimensionality reduction yield impressive results in data embedding and manifold visualization. However, they also open up the problem of how to define a...
Facial Analysis from Continuous Video with Applications to Human-Computer Interface (2004)
Colmenarez, Antonio J., Xiong, Ziyou, Huang, Thomas S.
Computer vision algorithms for the analysis of video data are obtained from a camera aimed at the user of an interactive system. It is potentially useful to enhance the interface between users and...
Ira Cohen, Nicu Sebe, Marcelo C. Cirelo, Thomas S. Huang, Fabio G. Cozman, Fabio G. Cozman
Automatic classification is one of the basic tasks required in any pattern recognition and human computer interaction application. In this paper we discuss training probabilistic classifiers with...
Ira Cohen, Fabio G. Cozman, Nicu Sebe, Marcelo C. Cirelo, Thomas S. Huang
Automatic classification by machines is one of the basic tasks required in any pattern recognition and human computer inter-action applications. In this paper we discuss training probabilistic...
Authentic facial expression analysis (2004)
Nicu Sebe, Michael S. Lew, Ira Cohen, Yafei Sun, Theo Gevers, Thomas S. Huang
It is argued that for the computer to be able to interact with humans, it needs to have the communication skills of humans. One of these skills is the ability to understand the emotional state of the...
Toward an improved error metric (2004)
Qi Tian, Qing Xue, Jie Yu, Nicu Sebe, Thomas S. Huang
In many computer vision algorithms, the well known Euclidean or SSD (sum of the squared differences) metric is prevalent and justified from a maximum likelihood perspective when the additive noise is...
Aleksandar Ivanovic, Ar Ivanovi C, Thomas S. Huang
This paper presents a probabilistic framework for segmenting and tracking multiple non rigid foreground objects for video surveillance, using a static monocular camera. The algorithm combines...
Audio Segment Retrieval Using A Short Duration Example Query (2004)
Atulya Velivelli Chengxiang, Chengxiang Zhai, Thomas S. Huang
In this paper, we propose a general approach to audio segment retrieval using a synthesized HMM. The approach allows a user to query audio data by an example audio segment of a short duration and...
Ziyou Xiong, Regunathan Radhakrishnan, Ajay Divakaran, Thomas S. Huang, Ziyou Xiong, ...
We present a comparison of 6 methods for classification of sports audio. For the feature extraction we have two choices: MPEG-7 audio features and Mel-scale Frequency Cepstrum Coefficients (MFCC)....
Effective And Efficient Sports Highlights Extraction Using The (2004)
Minimum Description Length, Ziyou Xiong, Regunathan Radhakrishnan, Ajay Divakaran, Thomas S. Huang
In fitting the training data with Guassian Mixture Models (GMMs) of appropriate structures using the MDL criterion, we are able to improve audio classification accuracy with a large margin. With the...
3D Model-based hand tracking using stochastic direct search method (2004)
Tracking the articulated hand motion in a video sequence is a challenging problem in which the main difficulty arises from the complexity of searching for an optimal motion estimate in a high...
Robust visual tracking by integrating multiple cues based on co-inference learning (2004)
Abstract. Visual tracking can be treated as a parameter estimation problem that infers target states based on image observations from video sequences. A richer target representation would incur...
Bimodal HCI-related affect recognition (2004)
Zhihong Zeng, Jilin Tu, Ming Liu, Tong Zhang, Nicholas Rizzolo, Zhenqiu Zhang, ...
Perhaps the most fundamental application of affective computing would be Human-Computer Interaction (HCI) in which the computer is able to detect and track the user’s affective states, and make...
This paper presents the methodology and theory for automatic spatial pattern discovery from multiple attributed relational graph samples. The spatial pattern is modelled as a mixture of probabilistic...
Visualization & User-Modeling for Browsing Personal Photo Libraries (2004)
Baback Moghaddam, Qi Tian, Neal Lesh, Chia Shen, Thomas S. Huang
We present a user-centric system for visualization and layout for content-based image retrieval. Image features (visual and/or semantic) are used to display retrievals as thumbnails in a 2-D spatial...
Detection of documentary scene changes by audio-visual fusion (2004)
Atulya Velivelli, Chong-wah Ngo, Thomas S. Huang
Abstract. The concept of a documentary scene was inferred from the audio-visual characteristics of certain documentary videos. It was observed that the amount of information from the visual component...
Active morphable model: An efficient method for face analysis (2004)
Xun Xu, Changshui Zhang, Thomas S. Huang
Multidimensional Morphable Model is a powerful model to analyze and synthesize human faces. However, the stochastic gradient descent algorithm adopted to match the Morphable Model to a novel face...
Multi-Modal sensory Fusion with Application to Audio-Visual Speech Recognition (2003)
Chu, Stephen M., Huang, Thomas S.
In this work we consider the bimodal fusion problem in audio-visual speech recognition. A novel sensory fission architecture based on the coupled hidden Markov models (CHMMs) is presented. CHMMs are...
Multimodal Dialog Systems Research at Illinois (2003)
Levinson, Stephen E., Huang, Thomas S., Hasegawa-Johnson, Mark A., Chen, Ken, Chu, Stephen
Multimodal dialog systems research at the University of Illinois seeks to develop algorithms and systems capable of robustly extracting and adaptively combining information about the speech and...
Nakazato, Munehiro, Manola, Ljubomir, Huang, Thomas S.
In content-based image retrieval (CBIR), experimental (trial-and-error) query with relevance feedback is essential for successful retrieval. Unfortunately, the traditional user interfaces are not...
Face relighting with radiance environment maps (2003)
Zhen Wen, Zicheng Liu, Thomas S. Huang
A radiance environment map pre-integrates a constant surface reflectance with the lighting environment. It has been used to generate photo-realistic rendering at interactive speed. However, one of...
Tracking Articulated Hand Motion with Eigen Dynamics Analysis (2003)
This paper introduces the concept of eigen-dynamics and proposes an eigen dynamics analysis (EDA) method to learn the dynamics of natural hand motion from labelled sets of motion captured with a data...
Ira Cohen, Nicu Sebe, Fabio G. Cozman, Marcelo C. Cirelo, Thomas S. Huang
Understanding human emotions is one of the necessary skills for the computer to interact intelligently with human users. The most expressive way humans display emotions is through facial expressions....
Facial expression recognition from video sequences: Temporal and static modeling (2003)
Ira Cohen, Nicu Sebe, Larry Chen, Ashutosh Garg, Thomas S. Huang
Human-computer intelligent interaction (HCII) is an emerging field of science aimed at providing natural ways for humans to use computers as aids. It is argued that for the computer to be able to...
Facial expression recognition from video sequences: Temporal and static modeling (2003)
Ira Cohen, Nicu Sebe, Ashutosh Garg, Michael S. Lew, Thomas S. Huang
Recognizing human facial expression and emotion by computer is an interesting and challenging problem. In this paper we propose a method for recognizing emotions through facial expressions displayed...
Ira Cohen, Nicu Sebe, Fabio G. Cozman, Marcelo C. Cirelo, Thomas S. Huang
Understanding human emotions is one of the necessary skills for the computer to interact intelligently with human users. The most expressive way humans display emotions is through facial expressions....
Evaluation of expression recognition techniques (2003)
Ira Cohen, Nicu Sebe, Yafei Sun, Michael S. Lew, Thomas S. Huang
Abstract. The most expressive way humans display emotions is through facial expressions. In this work we report on several advances we have made in building a system for classification of facial...
Facial Expression Recognition from Video Sequences: Temporal and Static Modeling (2003)
Ira Cohen, Nicu Sebe, Ashutosh Garg, Lawrence S. Chen, Thomas S. Huang
The most expressive way humans display emotions is through facial expressions. In this work we report on several advances we have made in building a system for classification of facial expressions...
Ziyou Xiong, Regunathan Radhakrishnan, Ajay Divakaran, Thomas S. Huang
We developed a unified framework to extract highlights from three sports: baseball, golf and soccer by detecting some of the common audio events that are directly indicative of highlights. We used...
Frame-dependent multi-stream reliability indicators for audio-visual speech recognition (2003)
Ashutosh Garg, Gerasimos Potamianos, Chalapathy Neti, Thomas S. Huang
We investigate the use of local, frame-dependent reliability indicators of the audio and visual modalities, as a means of estimating stream exponents of multi-stream hidden Markov models for...
Evaluating groupbased relevance feedback for content-based image retrieval (2003)
Munehiro Nakazato, Charlie Dagli, Thomas S. Huang
We have been developing new relevance feedback algorithms for Content-based Image Retrieval (CBIR) that allow the user to achieve more flexible query. In conjunction with the new user interface,...
Image Understanding and Information Extraction. (2002)
Huang, Thomas S., Fu, King Sun
The objective of the research is to achieve a better understanding of image structure and to use this knowledge to develop techniques for image analysis and processing tasks, especially information...
Image Understanding and Information Extraction. (2002)
Huang, Thomas S., Fu, King Sun
The objective of this research is to achieve a better understanding of image structure and to use this knowledge to develop techniques for image analysis and processing tasks, especially information...
Image Understanding and Information Extraction. (2002)
This report summarizes the results of the research program on Image Understanding and Information Extraction at Purdue University supported by the Defense Advanced Research Projects Agency. The...
Image Understanding and Information Extraction. (2002)
This report summarizes the results of the research program on Image Understanding and Information Extraction at Purdue University. The report covers the period 1 April 1977 to 30 September 1977. The...
Multidimensional Signal Restoration and Band-Limited Extrapolation. I. (2002)
Sanz,Jorge L. C., Huang,Thomas S.
This technical report deals with signal restoration and extrapolation. First, we prove that time-limited deconvolution and time-limited time-variant linear restoration of multidimensional signals can...
Multidimensional Signal Restoration and Band-Limited Extrapolation. II. (2002)
Sanz,Jorge L. C., Huang,Thomas S.
This technical report consists of three parts. The central problem is the extrapolation of band-limited signals. In part I, several existing algorithms for band-limited extrapolation are compared:...
PDH: A human-Centric Interface for Image Libraries (2002)
Baback Moghaddam, Baback Moghaddam, Qi Tian, Qi Tian, Neal Lesh, Neal Lesh, ...
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 build a more intuitive...
Real-time Speech-driven Face Animation with Expressions Using Neural Networks (2002)
Pengyu Hong, Zhen Wen, Thomas S. Huang
Abstract — A real-time speech-driven synthetic talking face provides an effective multimodal communication interface in distributed collaboration environments. Nonverbal gestures such as facial...
A factor graph framework for semantic video indexing (2002)
Milind Ramesh Naphade, Igor V. Kozintsev, Thomas S. Huang
most challenging research issues in video data management. To go beyond low-level similarity and access video data content by semantics, we need to bridge the gap between the low-level representation...
Visualization, Estimation and User-Modeling for Interactive Browsing (2002)
Baback Moghaddam, Baback Moghaddam, Qi Tian, Qi Tian, Thomas S. Huang, Thomas S. Huang
We present a user-centric system for visualization and layout for content-based image retrieval and browsing. Image features (visual and/or semantic) are analyzed to display and group retrievals as...
Nonstationary color tracking for vision-based human-computer interaction (2002)
Ying Wu, Thomas S. Huang, Life Fellow
Abstract—Skin color offers a strong cue for efficient localization and tracking of human body parts in video sequences for vision-based human–computer interaction. Color-based target localization...
Capturing human hand motion in image sequences (2002)
John Lin, Ying Wu, Thomas S. Huang
Visually capturing human hand motion requires estimating the 3D hand global pose as well as its local finger articulations. This is a challenging task that requires a search in a high dimensional...
Learning in content-based image retrieval (2002)
Thomas S. Huang, Xiang Sean Zhou, Munehiro Nakazato, Ira Cohen
In this paper we address several aspects of the learning problem in content-based image retrieval (CBIR). First, we introduce the linear and kernel-based biased discriminant analysis, or BiasMap, to...
PDH: A human-Centric Interface for Image Libraries (2002)
Baback Moghaddam, Qi Tian, Neal Lesh, Chia Shen, Thomas S. Huang
can enhance informal storytelling using personal digital data such as photos in a face-to-face social setting. In order to build a more intuitive browser for retrieval, navigation and story-telling,...
T.S.: ImageGrouper: Search, annotate and organize images by groups (2002)
Munehiro Nakazato, Ljubomir Manola, Thomas S. Huang
Abstract. In Content-based Image Retrieval (CBIR), trial-and-error query is essential for successful retrieval. Unfortunately, the traditional user interfaces are not suitable for trying different...
Towards self-exploring discriminating features (2001)
Abstract. Many visual learning tasks are usually confronted by some common difficulties. One of them is the lack of supervised information, due to the fact that labeling could be tedious, expensive...
Contribution of this paper is the derivation of an algorithm that generalizes Bell & Sejnowski’s classic ICA to tackle nonlinear ICA and the introduction of a new and efficient form of...
Edge/structural features for content based image retrieval (2001)
Xiang Sean Zhou, Thomas S. Huang
This paper proposes structural features for content-based image retrieval (CBIR), especially edge/structure features extracted from edge maps. The feature vector is computed through a...
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...
A co-inference approach to robust visual tracking (2001)
Visual tracking could be treated as a parameter estimation problem of target representation based on observations in image sequences. A richer target representation would incur better chances of...
Capturing natural hand articulation (2001)
Ying Wu, John Y. Lin, Thomas S. Huang
Vision-based motion capturing of hand articulation is a challenging task, since the hand presents a motion of high degrees of freedom. Model-based approaches could be taken to approach this problem...
Video retrieval and relevance feedback in the Context of a post-integration model. MMSP2001 (2001)
Roy Wang, Milind R. Naphade, Thomas S. Huang
Abstract- Video can be viewed as the integration of several heterogeneous media interwoven in a temporally close-coupled fashion. To support the retrieval of video segments under the query-by-example...
Nemanja Petrovic, Ira Cohen, Brendan J. Frey, Ralf Koetter, Thomas S. Huang
Accurate calculation of the three dimensional shape of an object is one of the classic research areas of computer vision. Many of the existing methods are based on surface normal estimation, and...
Optimal radial contour tracking by dynamic programming (2001)
Yunqiang Chen, Thomas S. Huang, N. Mathews Ave
A common problem in most active contour methods is that the recursive searching scheme can only return a local optimal solution. Furthermore, the internal energy of the snake is not strong enough to...
Spatial visualization for content-based image retrieval (2001)
Baback Moghaddam, Qi Tian, Thomas S. Huang
In traditional content-based image retrieval (CBIR), the retrieved images are displayed in order of decreasing similarities from the query and can be considered as a 1-D display. In this paper, a...
Spatial Visualization for Content-Based Image Retrieval (2001)
Thomas S. Huang, Baback Moghaddam, Baback Moghaddam, Qi Tian, Qi Tian, Thomas S. Huang
In traditional content-based image retrieval (CBIR), the retrieved images are displayed in order of decreasing similarities from the query and can be considered as a 1-D display. In this paper, a...
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...
Semantic Filtering of Video Content (2001)
Milind Naphade And, Milind R. Naphade, Thomas S. Huang
Semantic filtering of multimedia content is a challenging problem. The gap that exists between low-level media features and high-level semantics of multimedia is di#cult to bridge. We propose a...
ICA-based Probabilistic Local Appearance Models (2001)
Xiang Sean Zhou, 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...
Spatial visualization for content-based image retrieval (2001)
Baback Moghaddam, Qi Tian, Thomas S. Huang
In traditional content-based image retrieval (CBIR), the retrieved images are displayed in order of decreasing similarities from the query and can be considered as a 1-D display. In this paper ∗ ,...
Display Optimization for Image Browsing (2001)
Qi Tian, Baback Moghaddam, Thomas S. Huang
Abstract. ∗ In this paper, we propose a technique to visualize a multitude of images on a 2-D screen based on their visual features (color, texture, structure, etc.). The resulting layout will...
Edge-based structural features for content-based image retrieval (2001)
Xiang Sean Zhou, Thomas S. Huang
This paper proposes structural features for content-based image retrieval (CBIR), especially edge/structure features extracted from edge maps. The feature vector is computed through a...
Thomas S. Huang, Xiang Sean Zhou
Various relevance feedback techniques have been applied in content-based image retrieval. This paper gives a brief review on existing techniques: from early heuristic-based feature weighting schemes...
One-class svm for learning in image retrieval (2001)
Yunqiang Chen, Xiang Zhou, Thomas S. Huang
Relevance feedback schemes using linear/quadratic estimators have been applied in content-based image retrieval to significantly improve retrieval performance. One major difficulty in relevance...
Optimal radial contour tracking by dynamic programming (2001)
Yunqiang Chen, Thomas S. Huang
A common problem in most active contour methods is that the recursive searching scheme can only return a local optimal solution. Furthermore, the internal energy of the snake is not strong enough to...
Ziyou Xiong, Xiang Zhou, William M. Pottengerý, Thomas S. Huang
A content-based image retrieval(CBIR) system has been constructed to integrate relevance feedback with triangle-inequality based algorithms. The system offers typically 20 to 30 times faster...
Combine user defined region-of-interest and spatial layout for image retrieval (2000)
Qi Tian, Ying Wu, Thomas S. Huang
Content-Based Image Retrieval (CBIR) is one of the most active research areas in recent years. Many visual feature representations have been explored and many systems built. However, in most of...
Emotion recognition from facial expressions using multilevel HMM (2000)
Ira Cohen, Ashutosh Garg, Thomas S. Huang
Human-computer intelligent interaction (HCII) is an emerging field of science aimed at providing natural ways for humans to use computers as aids. It is argued that for the computer to be able to...
Constructing finite state machines for fast gesture recognition (2000)
Pengyu Hong, Matthew Turk, Thomas S. Huang
This paper proposes an approach to 2D gesture recognition that models each gesture as a Finite State Machine (FSM) in spatial-temporal space. The model construction works in a semi-automatic way. The...
Ziyou Xiong, Xiang Zhou, William M. Pottengery, Thomas S. Huang
A content-based image retrieval(CBIR) system has been constructed to integrate relevance feedback with triangle-inequality based algorithms. The system offers typically 20 to 30 times faster...
Gesture modeling and recognition using finite state machines (2000)
Pengyu Hong, Matthew Turk, Thomas S. Huang
This paper proposes a state based approach to gesture learning and recognition. Using spatial clustering and temporal alignment, each gesture is defined to be an ordered sequence of states in...
Multimodal speaker detection using error feedback dynamic Bayesian networks (2000)
Vladimir Pavlović, Ashutosh Garg, James M. Rehg, Thomas S. Huang
Design and development of novel human-computer interfaces poses a challenging problem: actions and intentions of users have to be inferred from sequences of noisy and ambiguous multi-sensory data...
Ying Wu, Qiong Liu, Thomas S. Huang
This paper describes an adaptive self-organizing color segmentation algorithm and a transductive learning algorithm used to localize human hand in video sequences. The color distribution at each time...
View-independent recognition of hand postures (2000)
Since human hand is highly articulated and deformable, hand posture recognition is a challenging example in the research of view-independent object recognition. Due to the di#culties of the...
Combine user defined region-of-interest and spatial layout for image retrieval (2000)
Qi Tian, Ying Wu, Thomas S. Huang
Content-Based Image Retrieval (CBIR) is one of the most active research areas in recent years. Many visual feature representations have been explored and many systems built. However, in most of...
Update relevant image weights for content-based image retrieval using support vector machines (2000)
Qi Tian, Pengyu Hong, Thomas S. Huang
Relevance feedback [1] has been a powerful tool for interactive Content-Based Image Retrieval (CBIR). During the retrieval process, the user selects the most relevant images and provides a weight of...
Discriminant-em algorithm with application to image retrieval (2000)
Ying Wu, Qi Tian, Thomas S. Huang
In many vision applications, the practice of supervised learning faces several di#culties, one of which is that insu#cient labeled training data result in poor generalization. In image retrieval, we...
Incorporate discriminant analysis with EM algorithm in image retrieval (2000)
Qi Tian, Ying Wu, Thomas S. Huang
One of the difficulties of Content-Based Image Retrieval (CBIR) is the gap between high-level concepts and low-level image features, e.g., color and texture. Relevance feedback was proposed [1] to...
Incorporate Support Vector Machines to Content-based Image Retrieval with Relevant Feedback (2000)
Pengyu Hong, Qi Tian, Thomas S. Huang
By using relevance feedback [6], Content-Based Image Retrieval (CBIR) allows the user to retrieve images interactively. The user can select the most relevant images and provide a weight of preference...
Improving Visual Matching (2000)
Michael S. Lew, Nicu Sebe, Thomas S. Huang
Many visual matching algorithms can be described in terms of the features and the inter-feature distance or metric. The most commonly used metric is the sum of squared differences (SSD), which is...
Color tracking by transductive learning (2000)
One of the di#culties of color tracking is that color changes in di#erent lighting conditions, and static color models would be inadequate to capture the nonstationary color distribution over time....
Integrating unlabeled images for image retrieval based on relevance feedback (2000)
Ying Wu, Qi Tian, Thomas S. Huang
Retrieval techniques based on pure similarity metrics are often suffered from the scales of image features. An alternative approach is to learn a mapping based on queries and relevance feedback by...
Discriminant-em algorithm with application to image retrieval (2000)
Ying Wu, Qi Tian, Thomas S. Huang
In many vision applications, the practice of supervised learning faces several di#culties, one of which is that insu#cient labeled training data result in poor generalization. In image retrieval, we...
Self-Supervised learning for visual tracking and recognition of human hand (2000)
Due to the large variation and richness of visual inputs, statistical learning gets more and more concerned in the practice of visual processing such as visual tracking and recognition. Statistical...
A Unified Framework for Video Browsing and Retrieval (2000)
this paper we focus our attention on the links between Index entities and shots. Shots are the building blocks of the ToC. Other links are generalizable from the shot link.
Multimodal Speaker Detection using Error Feedback Dynamic Bayesian Networks (2000)
Vladimir Pavlovic, Ashutosh Garg, James M. Rehg, Thomas S. Huang
Design and development of novel human-computer interfaces poses a challenging problem: actions and intentions of users have to be inferred from sequences of noisy and ambiguous multi-sensory data...
Nebojsa Jojic, Nemanja Petrovic, Brendan J. Frey, Thomas S. Huang
Submitted to the IEEE Conference on Computer Vision and Pattern Recognition, 2000. In this paper we describe a novel generative model for video analysis called the transformed hidden Markov model...
Improving Visual Matching (2000)
Michael S. Lew, Nicu Sebe, Thomas S. Huang
Many visual matching algorithms can be described in terms of the features and the inter-feature distance or metric. The most commonly used metric is the sum of squared differences (SSD), which is...
Combine user defined region-of-interest and spatial layout for image retrieval (2000)
Qi Tian, Ying Wu, Thomas S. Huang
Content-Based Image Retrieval (CBIR) is one of the most active research areas in recent years. Many visual feature representations have been explored and many systems built. However, in most of...
Incorporate discriminant analysis with EM algorithm in image retrieval (2000)
Qi Tian, Ying Wu, Thomas S. Huang
One of the difficulties of Content-Based Image Retrieval (CBIR) is the gap between high-level concepts and low-level image features, e.g., color and texture. Relevance feedback was proposed [1] to...
Incorporate discriminant analysis with EM algorithm in image retrieval (2000)
One of the difficulties of Content-Based Image Retrieval (CBIR) is the gap between high-level concepts and low-level image features, e.g., color and texture. Relevance feedback was proposed [1] to...
Incorporate Support Vector Machines to Content-based Image Retrieval with Relevant Feedback (2000)
Pengyu Hong, Qi Tian, Thomas S. Huang
By using relevance feedback [6], Content-Based Image Retrieval (CBIR) allows the user to retrieve images interactively. The user can select the most relevant images and provide a weight of preference...
Combine user defined region-of-interest and spatial layout for image retrieval (2000)
Qi Tian, Ying Wu, Thomas S. Huang
Content-Based Image Retrieval (CBIR) is one of the most active research areas in recent years. Many visual feature representations have been explored and many systems built. However, in most of...
Update relevant image weights for content-based image retrieval using support vector machines (2000)
Qi Tian, Pengyu Hong, Thomas S. Huang
Relevance feedback [1] has been a powerful tool for interactive Content-Based Image Retrieval (CBIR). During the retrieval process, the user selects the most relevant images and provides a weight of...
CBIR: From Low-Level Features to HighLevel Semantics (2000)
Xiang Sean Zhou, Thomas S. Huang
The performance of a content-based image retrieval (CBIR) system is inherently constrained by the features adopted to represent the images in the database. Use of low-level features can not give...
Multimodal speaker detection using error feedback dynamic Bayesian networks (2000)
Vladimir Pavlović, Ashutosh Garg, James M. Rehg, Thomas S. Huang
Design and development of novel human-computer interfaces poses a challenging problem: actions and intentions of users have to be inferred from sequences of noisy and ambiguous multi-sensory data...
A factor graph framework for semantic indexing and retrieval in video (2000)
Milind R. Naphade, Igor Kozintsev, Thomas S. Huang, Kannan Ramch, Computer Engineering
Image retrieval: Current techniques, promising directions and open issues (1999)
This paper provides a comprehensive survey of the technical achievements in the research area of image retrieval, especially content-based image retrieval, an area that has been so active and...
Compression of MPEG-4 Facial Animation Parameters for Transmission of Talking Heads (1999)
Hai Tao, Homer H. Chen, Wei Wu, Thomas S. Huang
Abstract—The emerging MPEG-4 standard supports the transmission and composition of facial animation with natural video. The new standard will include a facial animation parameter (FAP) set that is...
Facial analysis from continuous video with application to human-computer interface (1999)
Antonio Jose Colmenarez, Ph. D, Thomas S. Huang
This thesis is about computer vision algorithms for the analysis of video data involving faces. This kind of video, obtained for example from a camera aimed to the user of some interactive system, is...
Exploiting the dependencies in information fusion (1999)
Hao Pan, Zhi-pei Liang, Thomas S. Huang
This paper presents a novel approach for multisensory information fusion in the Bayesian inference framework. Specically, under the maximum entropy principle, a formula is derived for estimating the...
Image retrieval: Current techniques, promising directions and open issues (1999)
Yong Rui, Thomas S. Huang, Shih-fu Chang
This paper provides a comprehensive survey of the technical achievements in the research area of Image Retrieval, especially Content-Based Image Retrieval, an area so active and prosperous in the...
A Multimedia Information Retrieval Model Based On Semantic And Visual Content (1999)
Yueting Zhuang, Sharad Mehrotra, Thomas S. Huang
Unlike text-based information retrieval model, information retrieval based on multimedia lacks a good IR model. In this paper, the goal is to present a retrieval model based on both semantic and...
A Multimedia Information Retrieval Model Based on Semantic and Visual Content (1999)
Yueting Zhuang, Sharad Mehrotra, Thomas S. Huang
Unlike text-based information retrieval model, information retrieval based on multimedia lacks a good IR model. In this paper, the goal is to present a retrieval model based on both semantic and...
Tracking Articulated Structures inStereo Image Sequences (1999)
Nebojsa Jojic, Thomas S. Huang
In this paper, we present an algorithm for real time 3-D tracking of articulated structures in stereo image sequences. These sequences can be captured by an inexpensive commercially available system...
Capturing Articulated Human Hand Motion: A Divide-and-Conquer Approach (1999)
The use of human hand as a natural interface device serves as a motivating force for research in the modeling, analyzing and capturing of the motion of articulated hand. Model-based hand motion...
A Novel Relevance Feedback Technique in Image Retrieval (1999)
The relevance feedback based approach to image retrieval has been an active research direction in the past few years. Many parameter estimation techniques have been proposed for relevance feedback....
Adaptive Learning Algorithm for SVM Applied to Feature Tracking (1999)
Ashutosh Garg, Ira Cohen, Thomas S. Huang
The framework of Support Vector Machines is becoming extremely popular in the field of statistical pattern classification. Kalman filters have been used for long for doing tracking. In this paper we...
Human Hand Modeling, Analysis and Animation in the Context of HCI (1999)
The use of human hand as a natural interface device serves as a motivating force for research in visual analysis of highly articulated hand movement. Since hand motion covers a huge domain, the scope...
Robust Real-time Human Hand Localization by Self-Organizing Color Segmentation (1999)
Ying Wu, Qiong Liu, Thomas S. Huang
In Proc. of ICCV99 Workshop RATFG-RTS, Greece, 1999 This paper describes a robust tracking algorithm used to localize human hand in video sequences. The localization system relies mainly on an...
Embedded Face and Facial Expression Recognition (1999)
Antonio Colmenarez, Brendan Frey, Thomas S. Huang
A framework for embedded recognition of faces and facial expressions is described. Faces are modeled based on the appearances and positions of facial features. Hidden states are used to represent...
Detection and Tracking of Faces and Facial Features (1999)
Antonio Colmenarez, Brendan Frey, Thomas S. Huang
We describe a real-time system for face and facial feature detection and tracking in continuous video. The core of this system consists of a set of novel facial feature detectors based on our...
Time-Series Classification Using Mixed-State Dynamic Bayesian Networks (1999)
Vladimir Pavlovic, Brendan J. Frey, Thomas S. Huang
We present a novel mixed-state dynamic Bayesian network (DBN) framework for modeling and classifying timeseries data such as object trajectories. A hidden Markov model (HMM) of discrete actions is...
A Probabilistic Framework for Embedded Face and Facial Expression Recognition (1999)
Antonio Colmenarez, Brendan Frey, Thomas S. Huang
We present a Bayesian recognition framework in which a model of the whole face is enhanced by models of facial feature position and appearances. Face recognition and facial expression recognition are...
Image retrieval: Current techniques, promising directions and open issues (1999)
This paper provides a comprehensive survey of the technical achievements in the research area of image retrieval, especially content-based image retrieval, an area that has been so active and...
Information retrieval beyond the text document (1999)
Yong Rui, Michael Ortega, Thomas S. Huang, Sharad Mehrotra
With the expansion of the Internet, searching for information goes beyond the boundary of physic libraries. Millions of documents of various media types, such as text, image, video, audio, graphics,...
Input/Output and Imaging Technologies II. Taipei, Taiwan, 26-27 July 2000 (1998)
Liu, Yung Sheng, Huang, Thomas S.
This second conference on Input/Output and Imaging Technologies, part of the International Optoelectronics Symposium Held in Taipei, Taiwan on 26-28 July 2000 in conjunction with Photonics Taiwan...
Browsing and retrieving video content in a unified framework (1998)
Yong Rui, Thomas S. Huang, Sharad Mehrotra
Abstract- In this paper, we rst review the recent research progress in video analysis, representation, browsing, and retrieval. Motivated by the mechanism used to access book's content, we then...
Face Detection and Recognition (1998)
Antonio J. Colmenarez, Thomas S. Huang
Abstract. Two of the most important aspects in the general research framework of face recognition by computer are addressed here: face and facial feature detection, and face recognition-- or rather...
Relevance Feedback: A Power Tool for Interactive Content-Based Image Retrieval (1998)
Yong Rui Thomas, Thomas S. Huang, Michael Ortega, Sharad Mehrotra
Content-Based Image Retrieval (CBIR) has become one of the most active research areas in the past few years. Many visual feature representations have been explored and many systems built. While these...
Applying Semantic Association To Support Content-Based Video Retrieval (1998)
Yueting Zhuang, Yong Rui, Thomas S. Huang, Sharad Mehrotra
The traditional approach to video retrieval is to #rst annotate the video by textual information #titles and key words# and then the queries will be searched based on this keyword set. Since...
Information Retrieval Beyond the Text Document (1998)
Yong Rui, Michael Ortega, Thomas S. Huang, Sharad Mehrotra
With the expansion of the Internet, searching for information goes beyond the boundary of physical libraries. Millions of documents of various media types, suchas text, image, video, audio, graphics,...
Supporting Ranked Boolean Similarity Queries in MARS (1998)
Michael Ortega, Yong Rui, Kaushik Chakrabarti, Kriengkrai Porkaew, Thomas S. Huang, Sharad Mehrotra Y
To address the emerging needs of applications that require access to and retrieval of multimedia objects, we are developing the Multimedia Analysis and Retrieval System (MARS) [29]. In this paper, we...
Relevance Feedback Techniques in Interactive Content-Based Image Retrieval (1998)
Yong Rui Thomas, Thomas S. Huang, Sharad Mehrotra
Content-Based Image Retrieval #CBIR# has become one of the most active research areas in the past few years. Many visual feature representations have been explored and many systems built. While these...
Adaptive Key Frame Extraction Using Unsupervised Clustering (1998)
Yueting Zhuang, Yong Rui, Thomas S. Huang, Sharad Mehrotra
Key frame extraction has been recognized as one of the important research issues in video information retrieval. Although progress has been made in key frame extraction, the existing approaches are...
Browsing and Retrieving Video Content in a Unified Framework (1998)
Yong Rui, Thomas S. Huang, Sharad Mehrotra
In this paper, we #rst review the recent research progress in video analysis, representation, browsing, and retrieval. Motivated by the mechanism used to access book's content, we then...
Relevance Feedback: A Power Tool for Interactive Content-Based Image Retrieval (1998)
Yong Rui, Thomas S. Huang, Michael Ortega, Sharad Mehrotra
Content-Based Image Retrieval #CBIR# has become one of the most active research areas in the past few years. Many visual feature representations have been explored and many systems built. While these...
Constructing Table-of-Content for Videos (1998)
Yong Rui Thomas, Thomas S. Huang, Sharad Mehrotra
A fundamental task in video analysis is to extract structures from the video to facilitate user's access (browsing and retrieval). Motivated by the important role that Table-of-Content (ToC)...
Information Retrieval Beyond the Text Document (1998)
Yong Rui, Michael Ortega, Thomas S. Huang, Sharad Mehrotra
With the expansion of the Internet, searching for information goes beyond the boundary of physical libraries. Millions of documents of various media types, such as text, image, video, audio,...
Constructing Table-of-Content for Videos (1998)
Yong Rui, Thomas S. Huang, Sharad Mehrotra
A fundamental task in video analysis is to extract structures from the video to facilitate user's access #browsing and retrieval#. Motivated by the important role that Table-of-Content #ToC#...
Exploring Video Structure beyond the Shots (1998)
Yong Rui, Thomas S. Huang, Sharad Mehrotra
While existing shot-based video analysis approaches provide users with better access to the video than the raw data stream does, they are still not sufficient for meaningful video browsing and...
Supporting Ranked Boolean Similarity Queries in MARS (1998)
Michael Ortega, Yong Rui, Kaushik Chakrabarti, Kriengkrai Porkaew, Thomas S. Huang, Sharad Mehrotra
To address the emerging needs of applications that require access to and retrieval of multimedia objects, we are developing the Multimedia Analysis and Retrieval System (MARS) [29]. In this paper, we...
Supporting Ranked Boolean Similarity Queries in MARS (1998)
Michael Ortega, Yong Rui, Kaushik Chakrabarti, Alex Warshavsky, Sharad Mehrotra, Thomas S. Huang
To address the emerging needs of applications that require access to and retrieval of multimedia objects, we are developing the Multimedia Analysis and Retrieval System (MARS) in our group at the...
Relevance Feedback: A Power Tool for Interactive Content-Based Image Retrieval (1998)
Yong Rui, Thomas S. Huang, Michael Ortega, Sharad Mehrotra
Content-Based Image Retrieval (CBIR) has become one of the most active research areas in the past few years. Many visual feature representations have been explored and many systems built. While these...
Constructing Table-of-Content for Videos (1998)
Yong Rui, Thomas S. Huang, Sharad Mehrotra
A fundamental task in video analysis is to extract structures from the video to facilitate user's access (browsing and retrieval). Motivated by the important role that Table-of-Content (ToC)...
Exploring Video Structure Beyond The Shots (1998)
Yong Rui, Thomas S. Huang, Sharad Mehrotra
While existing shot-based video analysis approaches provide users with better access to the video than the raw data stream does, they are still not sufficient for meaningful video browsing and...
A Modified Fourier Descriptor for Shape Matching in MARS (1998)
Yong Rui, Alfred C. She, Thomas S. Huang
We propose a Modified Fourier Descriptor and a new distance measure for describing and comparing closed planar curves. Our method accounts for spatial discretization of shapes, an issue seldom...
Adaptive Key Frame Extraction Using Unsupervised Clustering (1998)
Yueting Zhuang, Yong Rui, Thomas S. Huang, Sharad Mehrotra
Key frame extraction has been recognized as one of the important research issues in video information retrieval. Although progress has been made in key frame extraction, the existing approaches are...
Browsing and Retrieving Video Content in a Unified Framework (1998)
Yong Rui, Thomas S. Huang, Sharad Mehrotra
In this paper, we first review the recent research progress in video analysis, representation, browsing, and retrieval. Motivated by the mechanism used to access book's content, we then present...
Pattern Detection with Information-Based Maximum Discrimination and Error Bootstrapping (1998)
Antonio J. Colmenarez, Thomas S. Huang
We have previously introduced a visual learning technique based on information-theoretic entropy. In that approach, positive and negative examples of a class of visual patterns were analyzed to...
Bimodal Emotion Recognition by Man and Machine (1998)
Thomas S. Huang, Lawrence S. Chen, Hai Tao, Tsutomu Miyasato, Ryohei Nakatsu
In this paper, we report preliminary results of recognizing emotions using both speech and video by machine. We applied automatic feature analysis and extraction algorithms to the same data used by...
Digital Image/Video Library And Mpeg-7: Standardization And Research Issues (1998)
Yong Rui, Thomas S. Huang, Shih-fu Chang
Much research activity and interest has emerged recently in two closely related areas: Digital Image/Video Library (DIVL) and MPEG-7. In this paper, we review the critical research issues in DIVL...
Mixtures of Local Linear Subspaces for Face Recognition (1998)
Brendan J. Frey, Antonio Colmenarez, Thomas S. Huang
Traditional subspace methods for face recognition compute a measure of similarity between images after projecting them onto a fixed linear subspace that is spanned by some principal component vectors...
A Region-Based Representation of Images in MARS (1998)
Sergio D. Servetto, Yong Rui, Kannan Ramchandran, Thomas S. Huang, Sergio Servetto
We study the problem of representing images within a multimedia Database Management System (DBMS), in order to support fast retrieval operations without compromising storage efficiency. To achieve...
A Region-Based Representation of Images in MARS (1998)
Sergio D. Servetto, Y. Rui, K. Ramchandran, T.S. Huang, Yong Rui, Kannan Ramchandran, ...
. We study the problem of representing images within a multimedia Database Management System (DBMS), in order to support fast retrieval operations without compromising storage efficiency. To achieve...
Connected Vibrations: A Modal Analysis Approach for Non-rigid Motion Tracking (1998)
A new framework is presented in this paper for tracking non-rigid motion in image sequences. This method models non-rigid motions as the deformations of connected 2D membrane patches. Local...
Relevance feedback techniques in interactive content-based image retrieval (1998)
Yong Rui, Thomas S. Huang, Sharad Mehrotra
Content-Based Image Retrieval (CBIR) has become one of the most active research areas in the past few years. Many visual feature representations have been explored and many systems built. While these...
Supporting ranked Boolean similarity queries in MARS (1998)
Michael Ortega, Yong Rui, Kaushik Chakrabarti, Alex Warshavsky, Sharad Mehrotra, Thomas S. Huang
To address the emerging needs of applications that require access to and retrieval of multimedia objects, we are developing the Multimedia Analysis and Retrieval System (MARS) in our group at the...
A Modified Fourier Descriptor for Shape Matching in MARS (1998)
Yong Rui, Alfred C. She, Thomas S. Huang
We propose a Modified Fourier Descriptor and a new distance measure for describing and comparing closed planar curves. Our method accounts for spatial discretization of shapes, an issue seldom...
Supporting content-based queries over images in MARS (1997)
Sharad Mehrotra, Yong Rui, Michael Ortega-binderberger, Thomas S. Huang
While advances in technology allow us to generate, transmit, and store large amounts of digital images, video, and audio, research in indexing and retrieval of multimedia information is still at its...
A system/graph theoretical analysis of attractor coders (1997)
This paper provides links between the young #eld of attractor coding and the well#established #elds of systems theory and graph theory. Attractor decoders are modeled as linear systems whose...
Face detection with information-based maximum discrimination (1997)
Antonio J. Colmenarez, Thomas S. Huang
In this paper we present a visual learning technique that maximizes the discrimination between positive and negative examples in a training set. We demonstrate our technique in the context of face...
3d model-based head tracking (1997)
Antonio Colmenarez, Ricardo Lopez, Thomas S. Huang
This paper introduces a new approach to feature-based head tracking and pose estimation. Head tracking and pose estimation find their most important applications in motion analysis for model-based...
Supporting similarity queries in MARS (1997)
Michael Ortega, Yong Rui, Kaushik Chakrabarti, Sharad Mehrotra, Thomas S. Huang
To address the emerging needs of applications that require access to and retrieval of multimedia objects, we are developing the Multimedia Analysis and Retrieval System (MARS) in our group at the...
MARS and Its Applications to MPEG-7 (1997)
Yong Rui, Thomas S. Huang, Sharad Mehrotra
: To address the emerging needs of access to and retrieval of multimedia objects in many applications, we have started a Multimedia Analysis and Retrieval Systems project at the University of...
Multimedia Analysis and Retrieval System (1997)
Sharad Mehrotra, Yong Rui, Kaushik Chakrabarti, Micheal Ortega, Thomas S. Huang
Introduction With the advances in storage technology and the advent of the World Wide Web, there has been an explosion in the amount and complexity of digital information being generated, analyzed,...
Content-Based Image Retrieval With Relevance Feedback In Mars (1997)
Yong Rui, Thomas S. Huang, Sharad Mehrotra
Technology advances in the areas of Image processing #IP# and Information Retrieval #IR# have evolved separately for a long time. However, successful content-based image retrieval systems require the...
Automatic Matching Tool Selection Using Relevance Feedback In Mars (1997)
Yong Rui, Thomas S. Huang, Sharad Mehrotra, Michael Ortega
For a given visual feature, due to the diversity of human's subjective judgment, a visual information retrieval system that supports a single prefixed similarity measure will result in poor...
Supporting Content-based Queries over Images in MARS (1997)
Sharad Mehrotra, Yong Rui, Michael Ortega-Binderberger, Thomas S. Huang
This paper summarizes the retrieval subsystem of MARS and its support for content-based queries over image features. Detailed discussion of the algorithms used can be found in #2#. Content-based...
Supporting Similarity Queries in MARS (1997)
Michael Ortega, Yong Rui, Kaushik Chakrabarti, Sharad Mehrotra, Thomas S. Huang
To address the emerging needs of applications that require access to and retrieval of multimedia objects, we are developing the Multimedia Analysis and Retrieval System #MARS# in our group at the...
Supporting Similarity Queries in MARS (1997)
Michael Ortega Yong, Yong Rui, Kaushik Chakrabarti, Sharad Mehrotra, Thomas S. Huang
To address the emerging needs of applications that require access to and retrieval of multimedia objects, we are developing the Multimedia Analysis and Retrieval System (MARS) in our group at the...
A relevance feedback architecture for content-based multimedia information retrieval systems (1997)
Yong Rui, Thomas S. Huang, Sharad Mehrotra, Michael Ortega
Content-based multimedia information retrieval (MIR) has become one of the most active research areas in the past few years. Many retrieval approaches based on extracting and representing visual...
Supporting Similarity Queries in MARS (1997)
Michael Ortega, Yong Rui, Kaushik Chakrabarti, Sharad Mehrotra, Thomas S. Huang
To address the emerging needs of applications that require access to and retrieval of multimedia objects, we are developing the Multimedia Analysis and Retrieval System (MARS) in our group at the...
Content-Based Image Retrieval With Relevance Feedback In Mars (1997)
Yong Rui, Thomas S. Huang, Sharad Mehrotra
Technology advances in the areas of Image processing (IP) and Information Retrieval (IR) have evolved separately for a long time. However, successful content-based image retrieval systems require the...
Image Retrieval: Past, Present, And Future (1997)
Yong Rui, Thomas S. Huang, Shih-fu Chang
This paper provides a comprehensive survey of the technical achievements in the research area of Image Retrieval, especially Content-Based Image Retrieval, an area so active and prosperous in the...
Supporting Content-based Queries over Images in MARS (1997)
Sharad Mehrotra, Yong Rui, Michael Ortega-Binderberger, Thomas S. Huang
This paper summarizes the retrieval subsystem of MARS and its support for content-based queries over image features. Detailed discussion of the algorithms used can be found in [2]. Content-based...
Resolution Enhancement of Images Using Fractal Coding (1997)
Robert Denardo, Yoichi Tenda, Thomas S. Huang
The code generated by fractal coding of a digital image provides a resolution-independent representation of the image as this code can be decoded to generate a digital image at any resolution. When...
Multimedia Analysis and Retrieval System (1997)
Sharad Mehrotra, Yong Rui, Kaushik Chakrabarti, Micheal Ortega, Thomas S. Huang
Introduction With the advances in storage technology and the advent of the World Wide Web, there has been an explosion in the amount and complexity of digital information being generated, analyzed,...
Automated Image Registration by Maximization of a Region Similarity Metric (1997)
Zhi-Pei Liang, Hao Pan, Richard L. Magin, Narendra Ahuja, Thomas S. Huang
This paper presents a robust algorithm for automated registration of images related by rigid-body transformations. This algorithm uses a new region-based similarity metric, which enables accurate...
Automatic Matching Tool Selection Using Relevance Feedback In Mars (1997)
Yong Rui, Thomas S. Huang, Sharad Mehrotra, Michael Ortega
For a given visual feature, due to the diversity of human's subjective judgment, a visual information retrieval system that supports a single prefixed similarity measure will result in poor...
Visual Interpretation of Hand Gestures for Human-Computer Interaction: A Review (1997)
Vladimir I. Pavlovic, Rajeev Sharma, Thomas S. Huang
The use of hand gestures provides an attractive alternative to cumbersome interface devices for human-computer interaction (HCI). In particular, visual interpretation of hand gestures can help in...
Color Image Edge Detection Using Cluster Analysis (1997)
A color image edge detection algorithm is proposed in this paper based on the idea that use global color information to guide local gradient computation. Major chromatic components of an image are...
Estimating Cloth Draping Parameters from Range Data (1997)
Nebojsa Jojic, Thomas S. Huang
In this paper we present a computer vision algorithm for estimating cloth parameters for modeling. In an analysis-by-synthesis manner, the algorithm compares the drape of the model with the range...
Image Retrieval: Past, Present, And Future (1997)
Yong Rui, Thomas S. Huang, Shih-Fu Chang
This paper provides a comprehensive survey of the technical achievements in the research area of Image Retrieval, especially Content-Based Image Retrieval, an area so active and prosperous in the...
Supporting content-based queries over images in MARS (1997)
Sharad Mehrotra, Yong Rui, Michael Ortega-binderberger, Thomas S. Huang
While advances in technology allow us to generate, transmit, and store large amounts of digital images, video, and audio, research in indexing and retrieval of multimedia information is still at its...
Fractal video coding by matching pursuit (1996)
Mohammad Gharavi-alkhansari, Thomas S. Huang
Fractal image and video coders use redundancies present in di#erent scales of natural images for compression. Motion compensation, on the other hand, is a powerful method for exploiting similarities...
Maximum Likelihood Face Detection (1996)
Antonio J. Colmenarez, Thomas S. Huang
In this paper we present a visual learning approach that uses non-parametric probability estimators. We use entropy analysis over the training set in order to select the features that best represent...
Automated Region Segmentation Using Attraction-Based Grouping In Spatial-Color-Texture Space (1996)
Yong Rui, Alfred C. She, Thomas S. Huang
Recently much attention has been paid to Image Content-Based Retrieval Systems (CBRS). One important goal in CBRS is to extract local low level image features such as color, texture and shape, to...
Automated Region Segmentation Using Attraction-Based Grouping In Spatial-Color-Texture Space (1996)
Yong Rui, Alfred C. She, Thomas S. Huang
Recently much attention has been paid to Image ContentBased Retrieval Systems (CBRS). One important goal in CBRS is to extract local low level image features such as color, texture and shape, to...
Modified Fourier descriptors for shape representation -- a practical approach (1996)
Yong Rui, Alfred C. She, Thomas S. Huang
We propose a Modified Fourier Descriptor and a new distance metric for describing and comparing closed planar curves. Our method accounts for the effects of spatial discretization of shapes, an issue...
Fractal Image Coding Using Rate-Distortion Optimized Matching Pursuit (1996)
Mohammad Gharavi-Alkhansari, Thomas S. Huang
Matching pursuit is a general and flexible method for solving an optimization problem that is of interest in signal analysis, coding, control theory and statistics. In this paper, principles of...
Gestural Interface to a Visual Computing Environment for Molecular Biologists (1996)
Vladimir Pavlovic, Rajeev Sharma, Thomas S. Huang
In recent years there has been tremendous progress in 3D, immersive display and virtual reality (VR) technologies. Scientific visualization of data is one of many applications that has benefited from...
Speech/Gesture Interface to a Visual Computing Environment for Molecular Biologists (1996)
Rajeev Sharma, Thomas S. Huang, Vladimir I. Pavlovi'c, Yunxin Zhao, Zion Lo, Stephen Chu, ...
Recent progress in 3-D, immersive display and virtual reality (VR) technologies has made possible many exciting applications, for example, interactive visualization of complex scientific data. To...
Frontal view face detection (1995)
Antonio J. Colmenarez, Thomas S. Huang
This paper presents a symmetry measurement based on the correlation coefficient. This symmetry measurement is used to locate the center line of faces, and afterward, to decide whether the face view...
Hand Gesture Modeling, Analysis, and Synthesis (1995)
Thomas S. Huang, Vladimir I. Pavlovic
Hand gestures are a form of communication among people. Yet we still limit human-computer interaction to cumbersome mice movements. The use of hand gestures in the field of human-computer interaction...
Fractal-Based Techniques For A Generalized Image Coding Method (1994)
Mohammad Gharavi-alkhansari, Thomas S. Huang
This paper presents a new generalized image block coding algorithm which covers fractal techniques, block transform techniques, and vector quantization as its special cases. The coding is performed...
Generalized Image Coding Using Fractal-Based Methods (1994)
Mohammad Gharavi-alkhansari, Thomas S. Huang
A new general method is proposed for image coding which exploits similarities, possibly with scaling, among different parts of the image. The coding is performed by approximating each image block...
Vision-Based Gesture Recognition: A Review
Ying Wu, Thomas S. Huang, N. Mathews
The use of gesture as a natural interface serves as a motivating force for research in modeling, analyzing and recognition of gestures. In particular, human computer intelligent interaction needs...
Relevance Feedback Techniques in Interactive Content-Based Image Retrieval
Yong Rui, Thomas S. Huang, Sharad Mehrotra
Content-Based Image Retrieval (CBIR) has become one of the most active research areas in the past few years. Many visual feature representations have been explored and many systems built. While these...
Modified Fourier Descriptors for Shape Representation - A Practical Approach
Yong Rui, Alfred C. She, Thomas S. Huang
We propose a Modified Fourier Descriptor and a new distance metric for describing and comparing closed planar curves. Our method accounts for the effects of spatial discretization of shapes, an issue...
On Analysis of Cloth Drape Range Data
Nebojsa Jojic, Thomas S. Huang
. In this paper we present an algorithm for analysis of the range data of cloth drapes. The goal of the analysis is estimation of parameters for modeling and the geometry of the underlying object. In...