Search For:

Displaying 1-50 out of 75 total
Evaluation of Face Alignment Solutions Using Statistical Learning
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Xiangsheng Huang, Stan Z. Li, Yangsheng Wang
Issue Date:May 2004
pp. 213
In this paper, we propose a statistical learning approach for constructing an evaluation function for face alignment. A nonlinear classification function is learned from a set of positive (good alignment) and negative (bad alignment) training examples to e...
 
Pedestrian Attribute Classification in Surveillance: Database and Evaluation
Found in: 2013 IEEE International Conference on Computer Vision Workshops (ICCVW)
By Jianqing Zhu,Shengcai Liao,Zhen Lei,Dong Yi,Stan Z. Li
Issue Date:December 2013
pp. 331-338
Attributes are helpful to infer high-level semantic knowledge of pedestrians, thus improving the performance of pedestrian tracking, retrieval, re-identification, etc. However, current pedestrian databases are mainly for the pedestrian detection or trackin...
 
A robust eye localization method for low quality face images
Found in: Biometrics, International Joint Conference on
By Dong Yi, Zhen Lei,Stan Z. Li
Issue Date:October 2011
pp. 1-6
Eye localization is an important part in face recognition system, because its precision closely affects the performance of face recognition. Although various methods have already achieved high precision on the face images with high quality, their precision...
 
Low-resolution face recognition via Simultaneous Discriminant Analysis
Found in: Biometrics, International Joint Conference on
By Changtao Zhou, Zhiwei Zhang, Dong Yi,Zhen Lei,Stan Z. Li
Issue Date:October 2011
pp. 1-6
Low resolution (LR) is an important issue when handling real world face recognition problems. The performance of traditional recognition algorithms will drop drastically due to the loss of facial texture information in original high resolution (HR) images....
 
Illumination Invariant Face Recognition Using Near-Infrared Images
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Stan Z. Li, RuFeng Chu, ShengCai Liao, Lun Zhang
Issue Date:April 2007
pp. 627-639
Most current face recognition systems are designed for indoor, cooperative-user applications. However, even in thus-constrained applications, most existing systems, academic and commercial, are compromised in accuracy by changes in environmental illuminati...
 
Towards incremental and large scale face recognition
Found in: Biometrics, International Joint Conference on
By Junjie Yan, Zhen Lei, Dong Yi,Stan Z. Li
Issue Date:October 2011
pp. 1-6
Linear discriminant analysis with nearest neighborhood classifier (LDA + NN) has been commonly used in face recognition, but it often confronts with two problems in real applications: (1) it cannot incrementally deal with the information of training instan...
 
Multi-View Face Detection with FloatBoost
Found in: Applications of Computer Vision, IEEE Workshop on
By ZhenQiu Zhang1, MingJing Li, Stan Z. Li, HongJiang Zhang
Issue Date:December 2002
pp. 184
In this paper, a new boosting algorithm, called FloatBoost, is proposed to construct a strong face-nonface classifier. FloatBoost incorporates the idea of Floating Search into AdaBoost, and yields similar or higher classification accuracy than AdaBoost wit...
 
Part-based Face Recognition Using Near Infrared Images
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ke Pan, Shengcai Liao, Zhijian Zhang, Stan Z. Li, Peiren Zhang
Issue Date:June 2007
pp. 1-6
Recently, we developed NIR based face recognition for highly accurate face recognition under illumination variations [10]. In this paper, we present a part-based method for improving its robustness with respect to pose variations. An NIR face is decomposed...
 
A Theoretical Justification of Nearest Feature Line Method
Found in: Pattern Recognition, International Conference on
By Zonglin Zhou, Stan Z. Li, Kap Luk Chan
Issue Date:September 2000
pp. 2759
A novel pattern classification method, called the nearest feature line (NFL), has been proposed by one of authors recently. The NFL provides a better alternative to the popular nearest neighbor (NN) classifier when multiple prototypes per class are availab...
 
Efficient Object Matching Using Affine-Invariant Deformable Contour
Found in: Pattern Recognition, International Conference on
By Z. Xue, Stan Z. Li, E.K. Teoh
Issue Date:September 2000
pp. 1672
No summary available.
 
Fusion of Face and Palmprint for Personal Identification Based on Ordinal Features
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Rufeng Chu, Shengcai Liao, Yufei Han, Zhenan Sun, Stan Z. Li, Tieniu Tan
Issue Date:June 2007
pp. 1-2
No summary available.
 
FloatBoost Learning and Statistical Face Detection
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Stan Z. Li, ZhenQiu Zhang
Issue Date:September 2004
pp. 1112-1123
A novel learning procedure, called FloatBoost, is proposed for learning a boosted classifier for achieving the minimum error rate. FloatBoost learning uses a backtrack mechanism after each iteration of AdaBoost learning to minimize the error rate directly,...
 
Generalized Quotient Image
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Haitao Wang, Stan Z. Li, Yangsheng Wang
Issue Date:July 2004
pp. 498-505
In this paper, we present a unified framework for modeling intrinsic properties of face images for recognition. It is based on the quotient image (QI) concept, in particular on the existing works of QI [1, 2], Spherical Harmonic[13, 14, 15], [16, 17], Imag...
 
Face Recognition Using Ada-Boosted Gabor Features
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Peng Yang, Shiguang Shan, Wen Gao, Stan Z. Li, Dong Zhang
Issue Date:May 2004
pp. 356
Face representation based on Gabor features has attracted much attention and achieved great success in face recognition area for the advantages of the Gabor features. However, Gabor features currently adopted by most systems are redundant and too high dime...
 
Nearest Manifold Approach for Face Recognition
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Junping Zhang, Stan Z. Li, Jue Wang
Issue Date:May 2004
pp. 223
Faces under varying illumination, pose and non-rigid deformation are empirically thought of as a highly nonlinear manifold in the observation space. How to discover intrinsic low-dimensional manifold is important to characterize meaningful face distributio...
 
Hierarchical Linear Combinations for Face Recognition
Found in: Pattern Recognition, International Conference on
By Stan Z Li, Juwei Lu, Kap Luk Chan, Jun Liu, Lei Wang
Issue Date:August 1998
pp. 1191
No summary available.
 
Nonlinear Mapping of Multi-View Face Patterns to a Gaussian Distribution in a Low Dimensional Space
Found in: Recognition, Analysis, & Tracking of Faces & Gestures in Real -Time Systems, IEEE ICCV Workshop on
By Stan Z. Li, Rong Xiao, ZeYu Li, HongJiang Zhang
Issue Date:August 2001
pp. 0047
Abstract: When face patterns are subject to changes in view and illumination and facial shape, their distribution is highly nonlinear and complex in any space linear to the original image space. In this paper, we investigate into a nonlinear mapping by whi...
 
Learning Low Dimensional Invariant Signature of 3-D Object under Varying View and Illumination from 2-D Appearances
Found in: Computer Vision, IEEE International Conference on
By Stan Z. Li, Jie Yan, XinWen Hou, ZeYu Li, Hongjiang Zhang
Issue Date:July 2001
pp. 635
In this paper, we propose an invariant signature representation for appearances of 3-D object under varying view and illumination, and a method for learning the signature from multi-view appearance examples. The signature, a nonlinear feature, provides a g...
 
Online Multiple Instance Joint Model for Visual Tracking
Found in: 2012 9th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
By Longyin Wen,Zhaowei Cai,Menglong Yang,Zhen Lei,Dong Yi,Stan Z. Li
Issue Date:September 2012
pp. 319-324
Although numerous online learning strategies have beenproposed to handle the appearance variation in visualtracking, the existing methods just perform well in certaincases since they lack effective appearance learning mechanism. In this paper, a joint mode...
 
Multi-pedestrian detection in crowded scenes: A global view
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Junjie Yan, Zhen Lei, Dong Yi,Stan Z. Li
Issue Date:June 2012
pp. 3124-3129
Recent state-of-the-art algorithms have achieved good performance on normal pedestrian detection tasks. However, pedestrian detection in crowded scenes is still challenging due to the significant appearance variation caused by heavy occlusions and complex ...
 
Face shape recovery from a single image using CCA mapping between tensor spaces
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Stan Z. Li
Issue Date:June 2008
pp. 1-7
In this paper, we propose a new approach for face shape recovery from a single image. A single near infrared (NIR) image is used as the input, and a mapping from the NIR tensor space to 3D tensor space, learned by using statistical learning, is used for th...
 
Learning Feature Extraction and Classification for Tracking Multiple Objects: A Unified Framework
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By Xiaotong Yuan, Stan Z. Li
Issue Date:November 2006
pp. 22
A great challenge in tracking multiple objects is how to locate each object when they interact and form a group. We view it as a binary classification problem. It is important to base the classification on the currently most discriminative features. We der...
 
Separating Specular and Diffuse Reflection Components in the HSI Color Space
Found in: 2013 IEEE International Conference on Computer Vision Workshops (ICCVW)
By Jianwei Yang,Lixing Liu,Stan Z. Li
Issue Date:December 2013
pp. 891-898
In this paper, we propose to separate diffuse and specular reflection components for color images in the HSI color space. Under white illumination, pixels with the same diffuse chromaticity have the same hue. Meanwhile, specular pixels have lower saturatio...
 
Learn to Combine Multiple Hypotheses for Accurate Face Alignment
Found in: 2013 IEEE International Conference on Computer Vision Workshops (ICCVW)
By Junjie Yan,Zhen Lei,Dong Yi,Stan Z. Li
Issue Date:December 2013
pp. 392-396
In this paper, we present the details of our method in attending the 300 Faces in-the-wild (300W) challenge. We build our method on cascade regression framework, where a series of regressors are utilized to progressively refine the shape initialized by fac...
 
Water Filling: Unsupervised People Counting via Vertical Kinect Sensor
Found in: 2012 9th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
By Xucong Zhang,Junjie Yan,Shikun Feng,Zhen Lei,Dong Yi,Stan Z. Li
Issue Date:September 2012
pp. 215-220
People counting is one of the key components in video surveillance applications, however, due to occlusion, illumination, color and texture variation, the problem is far from being solved. Different from traditional visible camera based systems, we constru...
 
Spatio-temporal LBP Based Moving Object Segmentation in Compressed Domain
Found in: 2012 9th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
By Jianwei Yang,Shizheng Wang,Zhen Lei,Yanyun Zhao,Stan Z. Li
Issue Date:September 2012
pp. 252-257
With the increasing amount of surveillance data, moving object segmentation in the compressed domain has drawn broad attention from both academy and industry. In this paper, we propose a novel moving object segmentation method towards H.264 compressed surv...
 
Moving Cast Shadow Removal Based on Local Descriptors
Found in: Pattern Recognition, International Conference on
By Rui Qin, Shengcai Liao, Zhen Lei, Stan Z. Li
Issue Date:August 2010
pp. 1377-1380
Moving cast shadow removal is an important yet difficult problem in video analysis and applications. This paper presents a novel algorithm for detection of moving cast shadows, that based on a local texture descriptor called Scale Invariant Local Ternary P...
 
Online Principal Background Selection for Video Synopsis
Found in: Pattern Recognition, International Conference on
By Shikun Feng, Shengcai Liao, Zhiyong Yuan, Stan Z. Li
Issue Date:August 2010
pp. 17-20
Video synopsis provides a means for fast browsing of activities in video. Principal background selection (PBS) is an important step in video synopsis. Existing methods make PBS in an offline way and at a high memory cost. In this paper we propose a novel b...
 
Modeling pixel process with scale invariant local patterns for background subtraction in complex scenes
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Shengcai Liao, Guoying Zhao, Vili Kellokumpu, Matti Pietikainen, Stan Z. Li
Issue Date:June 2010
pp. 1301-1306
Background modeling plays an important role in video surveillance, yet in complex scenes it is still a challenging problem. Among many difficulties, problems caused by illumination variations and dynamic backgrounds are the key aspects. In this work, we de...
 
Half Quadratic Analysis for Mean Shift: with Extension to A Sequential Data Mode-Seeking Method
Found in: Computer Vision, IEEE International Conference on
By Xiaotong Yuan, Stan Z. Li
Issue Date:October 2007
pp. 1-8
Theoretical understanding and extension of mean shift procedure has received much attention recently [8, 18, 3]. In this paper, we present a theoretical exploration and an algorithm development on mean shift. In the theory part, we point out that convex pr...
 
On Constrained Sparse Matrix Factorization
Found in: Computer Vision, IEEE International Conference on
By Wei-Shi Zheng, Stan Z. Li, J. H. Lai, Shengcai Liao
Issue Date:October 2007
pp. 1-8
Various linear subspace methods can be formulated in the notion of matrix factorization in which a cost function is minimized subject to some constraints. Among them, constraints on sparseness have received much attention recently. Some popular constraints...
 
Real-time Object Classification in Video Surveillance Based on Appearance Learning
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Lun Zhang, Stan Z. Li, Xiaotong Yuan, Shiming Xiang
Issue Date:June 2007
pp. 1-8
Classifying moving objects to semantically meaningful categories is important for automatic visual surveillance. However, this is a challenging problem due to the factors related to the limited object size, large intra-class variations of objects in a same...
 
A Random Field Model for Improved Feature Extraction and Tracking
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By Xiaotong Yuan, Stan Z. Li
Issue Date:November 2006
pp. 37
This paper presents a novel method for illumination-invariant and contrast preserving feature extraction, aimed at improving performance of tracking under complex light condition. Features to be extracted are represented as a weight field. An energy functi...
 
A Near-infrared Image Based Face Recognition System
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Stan Z. Li, Lun Zhang, ShengCai Liao, XiangXin Zhu, RuFeng Chu, Meng Ao, Ran He
Issue Date:April 2006
pp. 455-460
In this paper, we present a near infrared (NIR) image based face recognition system. Firstly, we describe a design of NIR image capture device which minimizes influence of environmental lighting on face images. Both face and facial feature localization and...
 
Ordinal Palmprint Represention for Personal Identification
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Zhenan Sun, Tieniu Tan, Yunhong Wang, Stan Z. Li
Issue Date:June 2005
pp. 279-284
Palmprint-based personal identification, as a new member in the biometrics family, has become an active research topic in recent years. Although great progress has been made, how to represent palmprint for effective classification is still an open problem....
 
Nearest Intra-Class Space Classifier for Face Recognition
Found in: Pattern Recognition, International Conference on
By Wei Liu, Yunhong Wang, Stan Z. Li, Tieniu Tan
Issue Date:August 2004
pp. 495-498
In this paper, we propose a novel classification method, called nearest intra-class space (NICS), for face recognition. In our method, the distribution of face patterns of each person is represented by the intra-class space to capture all intra-class varia...
 
Boosting Local Feature Based Classifiers for Face Recognition
Found in: Computer Vision and Pattern Recognition Workshop
By Lei Zhang, Stan Z. Li, Zhi Yi Qu, Xiangsheng Huang
Issue Date:July 2004
pp. 87
In this paper, we present a method for face recognition using boosted Gabor feature based classifiers. Weak classifiers are constructed based on both magnitude and phase features derived from Gabor filters [Quadrature-phase simple-cell pairs are ap-propria...
 
Learning with Cascade for Classification of Non-Convex Manifolds
Found in: Computer Vision and Pattern Recognition Workshop
By Xiangsheng Huang, Stan Z. Li, Yangsheng Wang
Issue Date:July 2004
pp. 66
Images of a visual object, such as human face, reside in a complicated manifold in the high dimensional image space, when the object is subject to variations in pose, illumination, and other factors. Viola and Jones have successfully tackled difficult nonl...
 
Face Alignment Under Variable Illumination
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Yuchi Huang, Stephen Lin, Stan Z. Li, Hanqing Lu, Heung-Yeung Shum
Issue Date:May 2004
pp. 85
This paper presents an approach to face alignment under variable illumination, an obstacle largely ignored in previous 2D alignment work. To account for illumination variation, our method employs two forms of relatively lighting-invariant information. Edge...
 
Null Space-based Kernel Fisher Discriminant Analysis for Face Recognition
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Wei Liu, Yunhong Wang, Stan Z. Li, Tieniu Tan
Issue Date:May 2004
pp. 369
The null space-based LDA takes full advantage of the null space while the other methods remove the null space. It proves to be optimal in performance. From the theoretical analysis, we present the NLDA algorithm and the most suitable situation for NLDA. Ou...
 
Subspace Analysis and Optimization for AAM Based Face Alignment
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Ming Zhao, Chun Chen, Stan Z. Li, Jiajun Bu
Issue Date:May 2004
pp. 290
Active Appearance Models (AAM) is very powerful for extracting objects, e.g. faces, from images. It is composed of two parts: the AAM subspace model and the AAM search. While these two parts are closely correlated, existing efforts treated them separately ...
 
Multi-Modal Face Tracking Using Bayesian Network
Found in: Analysis and Modeling of Faces and Gestures, IEEE International Workshop on
By Fang Liu, Xueyin Lin, Stan Z Li, Yuanchun Shi
Issue Date:October 2003
pp. 135
This paper presents a Bayesian network based multi-modal fusion method for robust and real-time face tracking. The Bayesian network integrates a prior of second order system dynamics, and the likelihood cues from color, edge and face appearance. While diff...
 
Illumination Modeling and Normalization for Face Recognition
Found in: Analysis and Modeling of Faces and Gestures, IEEE International Workshop on
By Haitao Wang, Stan Z. Li, Yangsheng Wang, Weiwei Zhang
Issue Date:October 2003
pp. 104
In this paper, we present a general framework for face modeling under varying lighting conditions. First, we show that a face lighting subspace can be constructed based on three or more training face images illuminated by non-coplanar lights. The lighting ...
 
Learning to Detect Multi-View Faces in Real-Time
Found in: Development and Learning, International Conference on
By Stan Z. Li, Long Zhu, ZhenQiu Zhang, HongJiang Zhang
Issue Date:June 2002
pp. 172
In this paper, we present a system which learns to detect multi-view faces. The system uses a coarse-to-fine, simple-to-complex architecture called detector-pyramid. A new boosting algorithm, called FloatBoost, is proposed to construct a strong face-nonfac...
 
Multi-View Face Alignment Using Direct Appearance Models
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Stan Z. Li, HongJiang Zhang, Yan ShuiCheng, QianSheng Cheng
Issue Date:May 2002
pp. 0324
Alignment makes face distribution statistically more compact than un-aligned faces and provides a good basis for face modeling, recognition and synthesis. In this paper, we present a method for multi-view face alignment using a new model called direct appe...
 
Learning Representative Local Features for Face Detection
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Xiangrong Chen, Lie Gu, Stan Z Li, Hong-Jiang Zhan
Issue Date:December 2001
pp. 1126
This paper describes a face detection approach via learning local features. The key idea is that local features, being manifested by a collection of pixels in a local r-gion, are learnt from the training set instead of arbitrarily defined. The learning pro...
 
Learning Spatially Localized, Parts-Based Representation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Stan Z. Li, Xin Wen Hou, HongJiang Zhang, QianSheng Cheng
Issue Date:December 2001
pp. 207
In this paper, we propose a novel method, called local non-negative matrix factorization (LNMF), for learning spatially localized, parts-based subspace representation of visual patterns. An objective function is defined to impose localization constraint, i...
 
Direct Appearance Models
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By XinWen Hou, Stan Z. Li, HongJiang Zhang, QianSheng Cheng
Issue Date:December 2001
pp. 828
Active appearance model (AAM), which makes ingenious use of both shape and texture constraints, is a powerful tool for face modeling, alignment and facial feature extraction under shape deformations and texture variations. However, as we will show through ...
 
Learning Probabilistic Distribution Model for Multi-View Face Detection
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Lie Gu, Stan Z Li, Hong-Jiang Zhang
Issue Date:December 2001
pp. 116
Modeling subspaces of a distribution of interest in high dimensional spaces is a challenging problem in pattern analysis. In this paper, we present a novel framework for pose invariant face detection through multi-view face distribution modeling. The appro...
 
CONTENT-BASED AUDIO SEGMENTATION CONTENT-BASED AUDIO SEGMENTATION
Found in: Multimedia and Expo, IEEE International Conference on
By Lie Lu, Stan Z. Li, Hong-Jiang Zhang
Issue Date:August 2001
pp. 191
Audio exists at everywhere, but is often out-of-order. It is necessary to arrange them into regularized classes in order to use them more easily. It is also useful, especially in video content analysis, to segment an audio stream according to audio types. ...
 
 1  2 Next >>