By Topic

2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)

17-22 June 2006

Go

Filter Results

Displaying Results 1 - 25 of 175
  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Cover

    Publication Year: 2006, Page(s): c1
    Request permission for commercial reuse | PDF file iconPDF (71 KB)
    Freely Available from IEEE
  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Title Page

    Publication Year: 2006, Page(s):i - iii
    Request permission for commercial reuse | PDF file iconPDF (29 KB)
    Freely Available from IEEE
  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Copyright

    Publication Year: 2006, Page(s): iv
    Request permission for commercial reuse | PDF file iconPDF (38 KB)
    Freely Available from IEEE
  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Table of contents

    Publication Year: 2006, Page(s):v - xv
    Request permission for commercial reuse | PDF file iconPDF (78 KB)
    Freely Available from IEEE
  • Message from the Program and General Chairs

    Publication Year: 2006, Page(s): xvi
    Request permission for commercial reuse | PDF file iconPDF (36 KB) | HTML iconHTML
    Freely Available from IEEE
  • Conference organization

    Publication Year: 2006, Page(s): xvii
    Request permission for commercial reuse | PDF file iconPDF (28 KB)
    Freely Available from IEEE
  • Program Committee

    Publication Year: 2006, Page(s): xviii
    Request permission for commercial reuse | PDF file iconPDF (21 KB)
    Freely Available from IEEE
  • Incremental learning of object detectors using a visual shape alphabet

    Publication Year: 2006, Page(s):3 - 10
    Cited by:  Papers (51)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (656 KB) | HTML iconHTML

    We address the problem of multiclass object detection. Our aims are to enable models for new categories to benefit from the detectors built previously for other categories, and for the complexity of the multiclass system to grow sublinearly with the number of categories. To this end we introduce a visual alphabet representation which can be learnt incrementally, and explicitly shares boundary frag... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiclass Object Recognition with Sparse, Localized Features

    Publication Year: 2006, Page(s):11 - 18
    Cited by:  Papers (173)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (688 KB) | HTML iconHTML

    We apply a biologically inspired model of visual object recognition to the multiclass object categorization problem. Our model modifies that of Serre, Wolf, and Poggio. As in that work, we first apply Gabor filters at all positions and scales; feature complexity and position/scale invariance are then built up by alternating template matching and max pooling operations. We refine the approach in se... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Unsupervised Learning of Categories from Sets of Partially Matching Image Features

    Publication Year: 2006, Page(s):19 - 25
    Cited by:  Papers (56)  |  Patents (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (992 KB) | HTML iconHTML

    We present a method to automatically learn object categories from unlabeled images. Each image is represented by an unordered set of local features, and all sets are embedded into a space where they cluster according to their partial-match feature correspondences. After efficiently computing the pairwise affinities between the input images in this space, a spectral clustering technique is used to ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiple Object Class Detection with a Generative Model

    Publication Year: 2006, Page(s):26 - 36
    Cited by:  Papers (87)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1680 KB) | HTML iconHTML

    In this paper we propose an approach capable of simultaneous recognition and localization of multiple object classes using a generative model. A novel hierarchical representation allows to represent individual images as well as various objects classes in a single, scale and rotation invariant model. The recognition method is based on a codebook representation where appearance clusters built from e... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The Layout Consistent Random Field for Recognizing and Segmenting Partially Occluded Objects

    Publication Year: 2006, Page(s):37 - 44
    Cited by:  Papers (87)  |  Patents (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (720 KB) | HTML iconHTML

    This paper addresses the problem of detecting and segmenting partially occluded objects of a known category. We first define a part labelling which densely covers the object. Our Layout Consistent Random Field (LayoutCRF) model then imposes asymmetric local spatial constraints on these labels to ensure the consistent layout of parts whilst allowing for object deformation. Arbitrary occlusions of t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Ultrasound-Specific Segmentation via Decorrelation and Statistical Region-Based Active Contours

    Publication Year: 2006, Page(s):45 - 53
    Cited by:  Papers (10)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2960 KB) | HTML iconHTML

    Segmentation of ultrasound images is often a very challenging task due to speckle noise that contaminates the image. It is well known that speckle noise exhibits an asymmetric distribution as well as significant spatial correlation. Since these attributes can be difficult to model, many previous ultrasound segmentation methods oversimplify the problem by assuming that the noise is white and/or Gau... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bilayer Segmentation of Live Video

    Publication Year: 2006, Page(s):53 - 60
    Cited by:  Papers (109)  |  Patents (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (624 KB) | HTML iconHTML

    This paper presents an algorithm capable of real-time separation of foreground from background in monocular video sequences. Automatic segmentation of layers from colour/contrast or from motion alone is known to be error-prone. Here motion, colour and contrast cues are probabilistically fused together with spatial and temporal priors to infer layers accurately and efficiently. Central to our algor... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Closed Form Solution to Natural Image Matting

    Publication Year: 2006, Page(s):61 - 68
    Cited by:  Papers (154)  |  Patents (22)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (848 KB) | HTML iconHTML

    Interactive digital matting, the process of extracting a foreground object from an image based on limited user input, is an important task in image and video editing. From a computer vision perspective, this task is extremely challenging because it is massively ill-posed - at each pixel we must estimate the foreground and the background colors, as well as the foreground opacity ("alpha matte") fro... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computing Exact Discrete Minimal Surfaces: Extending and Solving the Shortest Path Problem in 3D with Application to Segmentation

    Publication Year: 2006, Page(s):69 - 78
    Cited by:  Papers (7)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (680 KB) | HTML iconHTML

    Shortest path algorithms on weighted graphs have found widespread use in the computer vision literature. Although a shortest path may be found in a 3D weighted graph, the character of the path as an object boundary in 2D is not preserved in 3D. An object boundary in three dimensions is a (2D) surface. Therefore, a discrete minimal surface computation is necessary to extend shortest path approaches... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recursive estimation of generative models of video

    Publication Year: 2006, Page(s):79 - 86
    Cited by:  Papers (11)  |  Patents (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1136 KB) | HTML iconHTML

    In this paper we present a generative model and learning procedure for unsupervised video clustering into scenes. The work addresses two important problems: realistic modeling of the sources of variability in the video and fast transformation invariant frame clustering. We suggest a solution to the problem of computationally intensive learning in this model by combining the recursive model estimat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Principled Hybrids of Generative and Discriminative Models

    Publication Year: 2006, Page(s):87 - 94
    Cited by:  Papers (49)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (5672 KB) | HTML iconHTML

    When labelled training data is plentiful, discriminative techniques are widely used since they give excellent generalization performance. However, for large-scale applications such as object recognition, hand labelling of data is expensive, and there is much interest in semi-supervised techniques based on generative models in which the majority of the training data is unlabelled. Although the gene... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Applying Ensembles of Multilinear Classifiers in the Frequency Domain

    Publication Year: 2006, Page(s):95 - 102
    Cited by:  Papers (3)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1128 KB) | HTML iconHTML

    Ensemble methods such as bootstrap, bagging or boosting have had a considerable impact on recent developments in machine learning, pattern recognition and computer vision. Theoretical and practical results alike have established that, in terms of accuracy, ensembles of weak classifiers generally outperform monolithic solutions. However, this comes at the cost of an extensive training process. The ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Conic Section Classifier and its Application to Image Datasets

    Publication Year: 2006, Page(s):103 - 108
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (272 KB) | HTML iconHTML

    Many problems in computer vision involving recognition and/or classification can be posed in the general framework of supervised learning. There is however one aspect of image datasets, the high-dimensionality of the data points, that makes the direct application of off-the-shelf learning techniques problematic. In this paper, we present a novel concept class and a companion tractable algorithm fo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Accelerated Kernel Feature Analysis

    Publication Year: 2006, Page(s):109 - 116
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (528 KB) | HTML iconHTML

    A fast algorithm, Accelerated Kernel Feature Analysis (AKFA), that discovers salient features evidenced in a sample of n unclassified patterns, is presented. Like earlier kernel-based feature selection algorithms, AKFA implicitly embeds each pattern into a Hilbert space, H, induced by a Mercer kernel. An ell-dimensional linear subspace of H is iteratively constructed by maximizing a variance condi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Escaping local minima through hierarchical model selection: Automatic object discovery, segmentation, and tracking in video

    Publication Year: 2006, Page(s):117 - 124
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (384 KB) | HTML iconHTML

    Recently, the generative modeling approach to video segmentation has been gaining popularity in the computer vision community. For example, the flexible sprites framework has been studied in, among other references, [11,13,14,24]. In general, detailed generative models are vulnerable to intractability of inference and local minima problems when approximations are made (see, e.g., [25]). Recent app... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Kernel Uncorrelated and Orthogonal Discriminant Analysis: A Unified Approach

    Publication Year: 2006, Page(s):125 - 131
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (264 KB) | HTML iconHTML

    Several kernel algorithms have recently been proposed for nonlinear discriminant analysis. However, these methods mainly address the singularity problem in the high dimensional feature space. Less attention has been focused on the properties of the resulting discriminant vectors and feature vectors in the reduced dimensional space. In this paper, we present a new formulation for kernel discriminan... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Selecting Principal Components in a Two-Stage LDA Algorithm

    Publication Year: 2006, Page(s):132 - 137
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (320 KB) | HTML iconHTML

    Linear Discriminant Analysis (LDA) is a well-known and important tool in pattern recognition with potential applications in many areas of research. The most famous and used formulation of LDA is that given by the Fisher-Rao criterion, where the problem reduces to a simple simultaneous diagonalization of two symmetric, positive-definite matrices, A and B; i.e. B^-1 AV = VA. Here, A defines the metr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning Non-Metric Partial Similarity Based on Maximal Margin Criterion

    Publication Year: 2006, Page(s):168 - 145
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (5832 KB) | HTML iconHTML

    The performance of many computer vision and machine learning algorithms critically depends on the quality of the similarity measure defined over the feature space. Previous works usually utilize metric distances which are ofen epistemologically different from the perceptual distance of human beings. In this paper a novel non-metric partial similarity measure is introduced, which is born to automat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.