Search For:

Displaying 1-44 out of 44 total
{\cal U}Boost: Boosting with the Universum
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Chunhua Shen,Peng Wang,Fumin Shen,Hanzi Wang
Issue Date:April 2012
pp. 825-832
It has been shown that the Universum data, which do not belong to either class of the classification problem of interest, may contain useful prior domain knowledge for training a classifier [1], [2]. In this work, we design a novel boosting algorithm that ...
 
StructBoost: Boosting Methods for Predicting Structured Output Variables
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Chunhua Shen,Guosheng Lin,Anton van den Hengel
Issue Date:August 2014
pp. 1
Boosting is a method for learning a single accurate predictor by linearly combining a set of less accurate weak learners. Recently, structured learning has found many applications in computer vision. Inspired by structured support vector machines (SSVM), h...
 
Efficient Pedestrian Detection by Directly Optimizing the Partial Area under the ROC Curve
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Sakrapee Paisitkriangkrai,Chunhua Shen,Anton Van Den Hengel
Issue Date:December 2013
pp. 1057-1064
Many typical applications of object detection operate within a prescribed false-positive range. In this situation the performance of a detector should be assessed on the basis of the area under the ROC curve over that range, rather than over the full curve...
 
Contextual Hypergraph Modeling for Salient Object Detection
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Xi Li,Yao Li,Chunhua Shen,Anthony Dick,Anton Van Den Hengel
Issue Date:December 2013
pp. 3328-3335
Salient object detection aims to locate objects that capture human attention within images. Previous approaches often pose this as a problem of image contrast analysis. In this work, we model an image as a hyper graph that utilizes a set of hyper edges to ...
 
A General Two-Step Approach to Learning-Based Hashing
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Guosheng Lin,Chunhua Shen,David Suter,Anton van den Hengel
Issue Date:December 2013
pp. 2552-2559
Most existing approaches to hashing apply a single form of hash function, and an optimization process which is typically deeply coupled to this specific form. This tight coupling restricts the flexibility of the method to respond to the data, and can resul...
 
Dictionary Learning and Sparse Coding on Grassmann Manifolds: An Extrinsic Solution
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Mehrtash Harandi,Conrad Sanderson,Chunhua Shen,Brian Lovell
Issue Date:December 2013
pp. 3120-3127
Recent advances in computer vision and machine learning suggest that a wide range of problems can be addressed more appropriately by considering non-Euclidean geometry. In this paper we explore sparse dictionary learning over the space of linear subspaces,...
 
Incremental Learning of 3D-DCT Compact Representations for Robust Visual Tracking
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Xi Li,A. Dick, Chunhua Shen,A. van den Hengel, Hanzi Wang
Issue Date:April 2013
pp. 863-881
Visual tracking usually requires an object appearance model that is robust to changing illumination, pose, and other factors encountered in video. Many recent trackers utilize appearance samples in previous frames to form the bases upon which the object ap...
 
Non-sparse linear representations for visual tracking with online reservoir metric learning
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Xi Li, Chunhua Shen, Qinfeng Shi,A. Dick,A. van den Hengel
Issue Date:June 2012
pp. 1760-1767
Most sparse linear representation-based trackers need to solve a computationally expensive l i -regularized optimization problem. To address this problem, we propose a visual tracker based on non-sparse linear representations, which admit an efficient clos...
 
Laplacian Margin Distribution Boosting for Learning from Sparsely Labeled Data
Found in: Digital Image Computing: Techniques and Applications
By Tao Wang,Xuming He,Chunhua Shen,Nick Barnes
Issue Date:December 2011
pp. 209-216
Boosting algorithms attract much attention in computer vision and image processing because of their strong performance in a variety of applications. Recent progress on the theory of boosting algorithms suggests a close link between good generalization and ...
 
On the Optimality of Sequential Forward Feature Selection Using Class Separability Measure
Found in: Digital Image Computing: Techniques and Applications
By Lei Wang,Chunhua Shen,Richard Hartley
Issue Date:December 2011
pp. 203-208
This paper studies sequential forward feature selection that uses the scatter-matrix-based class separability measure. We find that by adding a scale factor to each iteration of the conventional sequential selection, a sequential selection that guarantees ...
 
Graph mode-based contextual kernels for robust SVM tracking
Found in: Computer Vision, IEEE International Conference on
By Xi Li,Anthony Dick,Hanzi Wang,Chunhua Shen,Anton van den Hengel
Issue Date:November 2011
pp. 1156-1163
Visual tracking has been typically solved as a binary classification problem. Most existing trackers only consider the pairwise interactions between samples, and thereby ignore the higher-order contextual interactions, which may lead to the sensitivity to ...
 
A scalable dual approach to semidefinite metric learning
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Chunhua Shen, Junae Kim, Lei Wang
Issue Date:June 2011
pp. 2601-2608
Distance metric learning plays an important role in many vision problems. Previous work of quadratic Mahalanobis metric learning usually needs to solve a semidefinite programming (SDP) problem. A standard interior-point SDP solver has a complexity of O(D$^...
 
Is face recognition really a Compressive Sensing problem?
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Qinfeng Shi,A. Eriksson,A. van den Hengel, Chunhua Shen
Issue Date:June 2011
pp. 553-560
Compressive Sensing has become one of the standard methods of face recognition within the literature. We show, however, that the sparsity assumption which underpins much of this work is not supported by the data. This lack of sparsity in the data means tha...
 
Real-time visual tracking using compressive sensing
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Hanxi Li, Chunhua Shen, Qinfeng Shi
Issue Date:June 2011
pp. 1305-1312
The $/ell _1$ tracker obtains robustness by seeking a sparse representation of the tracking object via $/ell _1$ norm minimization. However, the high computational complexity involved in the $/ell _1$ tracker may hamper its applications in real-time proces...
 
A generalized probabilistic framework for compact codebook creation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Lingqiao Liu, Lei Wang, Chunhua Shen
Issue Date:June 2011
pp. 1537-1544
Compact and discriminative visual codebooks are preferred in many visual recognition tasks. In the literature, a few researchers have taken the approach of hierarchically merging visual words of a initial large-size code-book, but implemented this idea wit...
 
A direct formulation for totally-corrective multi-class boosting
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Chunhua Shen, Zhihui Hao
Issue Date:June 2011
pp. 2585-2592
Boosting combines a set of moderately accurate weak classifiers to form a highly accurate predictor. Compared with binary boosting classification, multi-class boosting received less attention. We propose a novel multi-class boosting formulation here. Unlik...
 
Robust Face Recognition via Accurate Face Alignment and Sparse Representation
Found in: Digital Image Computing: Techniques and Applications
By Hanxi Li, Peng Wang, Chunhua Shen
Issue Date:December 2010
pp. 262-269
Due to its potential applications, face recognition has been receiving more and more research attention recently. In this paper, we present a robust real-time facial recognition system. The system comprises three functional components, which are face detec...
 
Rapid face recognition using hashing
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Qinfeng Shi, Hanxi Li, Chunhua Shen
Issue Date:June 2010
pp. 2753-2760
We propose a face recognition approach based on hashing. The approach yields comparable recognition rates with the random ℓ<inf>1</inf> approach [18], which is considered the state-of-the-art. But our method is much faster: it is up to 150 time...
 
On the Dual Formulation of Boosting Algorithms
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Chunhua Shen, Hanxi Li
Issue Date:December 2010
pp. 2216-2231
We study boosting algorithms from a new perspective. We show that the Lagrange dual problems of \ell_1-norm-regularized AdaBoost, LogitBoost, and soft-margin LPBoost with generalized hinge loss are all entropy maximization problems. By looking at the dual ...
 
A Two-Layer Night-Time Vehicle Detector
Found in: Digital Image Computing: Techniques and Applications
By Weihong Wang, Chunhua Shen, Jian Zhang, Sakrapee Paisitkriangkrai
Issue Date:December 2009
pp. 162-167
We present a two-layer night time vehicle detector in this work. At the first layer, vehicle headlight detection is applied to find areas (bounding boxes) where the possible pairs of headlights locate in the image, the Haar feature based AdaBoost framework...
 
Smooth Approximation of L_infinity-Norm for Multi-view Geometry
Found in: Digital Image Computing: Techniques and Applications
By Yuchao Dai, Hongdong Li, Mingyi He, Chunhua Shen
Issue Date:December 2009
pp. 339-346
Recently the $L_\infty$-norm optimization has been introduced to multi-view geometry to achieve global optimality. It is solved through solving a sequence of SOCP (second order cone programming) feasibility problems which needs sophisticated solvers and ti...
 
Efficiently training a better visual detector with sparse eigenvectors
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By S. Paisitkriangkrai, Chunhua Shen, Jian Zhang
Issue Date:June 2009
pp. 1129-1136
Face detection plays an important role in many vision applications. Since Viola and Jones proposed the first real-time AdaBoost based object detection system, much effort has been spent on improving the boosting method. In this work, we first show that fea...
 
Learning Cascaded Reduced-Set SVMs Using Linear Programming
Found in: Digital Image Computing: Techniques and Applications
By Junae Kim, Chunhua Shen, Lei Wang
Issue Date:December 2008
pp. 619-626
This paper proposes a simple and efficient detection framework that uses reduced-set kernels. We first describe our approach which reduces the number of kernels. A convex optimization method is used for calculating the reduced sets. Following this, we prop...
 
Self-Calibrating Cameras Using Semidefinite Programming
Found in: Digital Image Computing: Techniques and Applications
By Chunhua Shen, Hongdong Li, Michael J. Brooks
Issue Date:December 2008
pp. 436-441
Novel methods are proposed for self-calibrating a pure-rotating camera using semidefinite programming (SDP). Key to the approach is the use of the positive-definiteness requirement for the dual image of the absolute conic (DIAC). The problem is couched wit...
 
Multi-view Human Motion Capture with an Improved Deformation Skin Model
Found in: Digital Image Computing: Techniques and Applications
By Yifan Lu, Lei Wang, Richard Hartley, Hongdong Li, Chunhua Shen
Issue Date:December 2008
pp. 420-427
Markerless human motion capture has received much attention in computer vision and computer graphics communities. A hierarchical skeleton template is frequently used to model the human body in literature, because it simplifies markerless human motion captu...
 
Boosting the Minimum Margin: LPBoost vs. AdaBoost
Found in: Digital Image Computing: Techniques and Applications
By Hanxi Li, Chunhua Shen
Issue Date:December 2008
pp. 533-539
LPBoost seemingly should have better generalization capability than AdaBoost according to the margin theory [12] because LPBoost optimizes the minimum margin directly. Thus far, however, there is no empirical comparison and theoretical explanation of LPBoo...
 
Feature Extraction Using Sequential Semidefinite Programming
Found in: Digital Image Computing: Techniques and Applications
By Chunhua Shen, Hongdong Li, Michael J. Brooks
Issue Date:December 2007
pp. 430-437
Many feature extraction approaches end up with a trace quotient formulation. Since it is difficult to directly solve the trace quotient problem, conventionally the trace quotient cost is replaced by an approximation such that the generalised eigen-decompos...
 
An Experimental Evaluation of Local Features for Pedestrian Classification
Found in: Digital Image Computing: Techniques and Applications
By Sakrapee Paisitkriangkrai, Chunhua Shen, Jian Zhang
Issue Date:December 2007
pp. 53-60
The ability to detect pedestrians is a first important step in many computer vision applications such as video surveillance. This paper presents an experimental study on pedestrian detection using state-of-the-art local feature extraction and support vecto...
 
Color Image Labelling Using Linear Programming
Found in: Digital Image Computing: Techniques and Applications
By Hongdong Li, Chunhua Shen, Zhiying Wen
Issue Date:December 2007
pp. 239-244
This paper describes a linear programming (LP) algorithm for labelling (segmenting) a color image into multiple regions. Compared with the recently-proposed semi-definite programming (SDP) relaxation based algorithm, our algorithm has a simpler mathematica...
 
Adaptive Object Tracking Based on an Effective Appearance Filter
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Hanzi Wang, David Suter, Konrad Schindler, Chunhua Shen
Issue Date:September 2007
pp. 1661-1667
We propose a similarity measure based on a Spatial-color Mixture of Gaussians (SMOG) appearance model for particle filters. This improves on the popular similarity measure based on color histograms because it considers not only the colors in a region but a...
 
Kernel-based Tracking from a Probabilistic Viewpoint
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Quang Anh Nguyen, Antonio Robles-Kelly, Chunhua Shen
Issue Date:June 2007
pp. 1-8
In this paper, we present a probabilistic formulation of kernel-based tracking methods based upon maximum likelihood estimation. To this end, we view the coordinates for the pixels in both, the target model and its candidate as random variables and make us...
 
Classification-Based Likelihood Functions for Bayesian Tracking
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By Chunhua Shen, Hongdong Li, Michael J. Brooks
Issue Date:November 2006
pp. 33
The success of any Bayesian particle filtering based tracker relies heavily on the ability of the likelihood function to discriminate between the state that fits the image well and those that do not. This paper describes a general framework for learning pr...
 
Enhanced Kernel-Based Tracking for Monochromatic and Thermographic Video
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By Quang Anh Nguyen, Antonio Robles-Kelly, Chunhua Shen
Issue Date:November 2006
pp. 28
In this paper, we present an enhanced kernel-based tracker for monochromatic and thermographic video. The technique presented here employs the image intensity and the Local Binary Pattern (LBP) to construct a two dimensional histogram representative of the...
 
An LMI Approach for Reliable PTZ Camera Self-Calibration
Found in: Advanced Video and Signal Based Surveillance, IEEE Conference on
By Hongdong Li, Chunhua Shen
Issue Date:November 2006
pp. 79
PTZ (Pan-Tilt-Zoom) cameras are widely used for large-area video surveillance. For many visual tracking and video analysis tasks, an accurate camera calibration is very important. Traditional off-line camera calibration algorithms are often not satisfactor...
 
Fast Global Kernel Density Mode Seeking with Application to Localisation and Tracking
Found in: Computer Vision, IEEE International Conference on
By Chunhua Shen, Michael J. Brooks, Anton van den Hengel
Issue Date:October 2005
pp. 1516-1523
<p>We address the problem of seeking the global mode of a density function using the mean shift algorithm. Mean shift, like other gradient ascent optimisation methods, is susceptible to local maxima, and hence often fails to find the desired global m...
 
2D Articulated Tracking with Dynamic Bayesian Networks
Found in: Computer and Information Technology, International Conference on
By Chunhua Shen, Anton van den Hengel, Anthony Dick, Michael J. Brooks
Issue Date:September 2004
pp. 130-136
We present a novel method for tracking the motion of an articulated structure in a video sequence. The analysis of articulated motion is challenging because of the potentially large number of degrees of freedom (DOFs) of an articulated body. For particle f...
 
Inductive Hashing on Manifolds
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Fumin Shen,Chunhua Shen,Qinfeng Shi,Anton van den Hengel,Zhenmin Tang
Issue Date:June 2013
pp. 1562-1569
Learning based hashing methods have attracted considerable attention due to their ability to greatly increase the scale at which existing algorithms may operate. Most of these methods are designed to generate binary codes that preserve the Euclidean distan...
 
A Hierarchical Word-Merging Algorithm with Class Separability Measure
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Lei Wang, Luping Zhou, Chunhua Shen, Lingqiao Liu, Huan Liu
Issue Date:March 2014
pp. 417-435
In image recognition with the bag-of-features model, a small-sized visual codebook is usually preferred to obtain a low-dimensional histogram representation and high computational efficiency. Such a visual codebook has to be discriminative enough to achiev...
 
Context-Aware Hypergraph Construction for Robust Spectral Clustering
Found in: IEEE Transactions on Knowledge and Data Engineering
By Xi Li,Weiming Hu,Chunhua Shen,Anthony Dick,Zhongfei Mark Zhang
Issue Date:July 2013
pp. 1
Spectral clustering is a powerful tool for unsupervised data analysis. In this paper, we propose a context-aware hypergraph similarity measure (CAHSM), which leads to robust spectral clustering in the case of noisy data. We construct three types of hypergr...
 
Part-Based Visual Tracking with Online Latent Structural Learning
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Rui Yao,Qinfeng Shi,Chunhua Shen,Yanning Zhang,Anton van den Hengel
Issue Date:June 2013
pp. 2363-2370
Despite many advances made in the area, deformable targets and partial occlusions continue to represent key problems in visual tracking. Structured learning has shown good results when applied to tracking whole targets, but applying this approach to a part...
 
A Fast Semidefinite Approach to Solving Binary Quadratic Problems
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Peng Wang,Chunhua Shen,Anton van den Hengel
Issue Date:June 2013
pp. 1312-1319
Many computer vision problems can be formulated as binary quadratic programs (BQPs). Two classic relaxation methods are widely used for solving BQPs, namely, spectral methods and semi definite programming (SDP), each with their own advantages and disadvant...
 
Learning Compact Binary Codes for Visual Tracking
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Xi Li,Chunhua Shen,Anthony Dick,Anton van den Hengel
Issue Date:June 2013
pp. 2419-2426
A key problem in visual tracking is to represent the appearance of an object in a way that is robust to visual changes. To attain this robustness, increasingly complex models are used to capture appearance variations. However, such models can be difficult ...
 
Bilinear Programming for Human Activity Recognition with Unknown MRF Graphs
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Zhenhua Wang,Qinfeng Shi,Chunhua Shen,Anton van den Hengel
Issue Date:June 2013
pp. 1690-1697
Markov Random Fields (MRFs) have been successfully applied to human activity modelling, largely due to their ability to model complex dependencies and deal with local uncertainty. However, the underlying graph structure is often manually specified, or auto...
 
A survey of appearance models in visual object tracking
Found in: ACM Transactions on Intelligent Systems and Technology (TIST)
By Anthony Dick, Anton Van Den Hengel, Chunhua Shen, Weiming Hu, Xi Li, Zhongfei Zhang
Issue Date:September 2013
pp. 1-48
Visual object tracking is a significant computer vision task which can be applied to many domains, such as visual surveillance, human computer interaction, and video compression. Despite extensive research on this topic, it still suffers from difficulties ...
     
 1