2009 IEEE Conference on Computer Vision and Pattern Recognition

20-25 June 2009

Filter Results

Displaying Results 1 - 25 of 386
  • Table of contents

    Publication Year: 2009, Page(s):i - xxxvi
    Request permission for reuse | PDF file iconPDF (437 KB)
    Freely Available from IEEE
  • Message from the program and general chairs

    Publication Year: 2009, Page(s):xxxvii - xxxix
    Request permission for reuse | PDF file iconPDF (68 KB)
    Freely Available from IEEE
  • Corporate donors

    Publication Year: 2009, Page(s): xl
    Request permission for reuse | PDF file iconPDF (222 KB)
    Freely Available from IEEE
  • Organizing Committee

    Publication Year: 2009, Page(s):xli - xlvii
    Request permission for reuse | PDF file iconPDF (128 KB)
    Freely Available from IEEE
  • Robust multi-class transductive learning with graphs

    Publication Year: 2009, Page(s):381 - 388
    Cited by:  Papers (19)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (916 KB) | HTML iconHTML

    Graph-based methods form a main category of semi-supervised learning, offering flexibility and easy implementation in many applications. However, the performance of these methods is often sensitive to the construction of a neighborhood graph, which is non-trivial for many real-world problems. In this paper, we propose a novel framework that builds on learning the graph given labeled and unlabeled ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Manhattan-world stereo

    Publication Year: 2009, Page(s):1422 - 1429
    Cited by:  Papers (145)  |  Patents (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1424 KB) | HTML iconHTML Multimedia Media

    Multi-view stereo (MVS) algorithms now produce reconstructions that rival laser range scanner accuracy. However, stereo algorithms require textured surfaces, and therefore work poorly for many architectural scenes (e.g., building interiors with textureless, painted walls). This paper presents a novel MVS approach to overcome these limitations for Manhattan World scenes, i.e., scenes that consists ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dense 3D motion capture for human faces

    Publication Year: 2009, Page(s):1674 - 1681
    Cited by:  Papers (20)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (5766 KB) | HTML iconHTML Multimedia Media

    This paper proposes a novel approach to motion capture from multiple, synchronized video streams, specifically aimed at recording dense and accurate models of the structure and motion of highly deformable surfaces such as skin, that stretches, shrinks, and shears in the midst of normal facial expressions. Solving this problem is a key step toward effective performance capture for the entertainment... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiplicative nonnegative greph embedding

    Publication Year: 2009, Page(s):389 - 396
    Cited by:  Papers (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (840 KB) | HTML iconHTML

    In this paper, we study the problem of nonnegative graph embedding, originally investigated in [J. Yang et al., 2008] for reaping the benefits from both nonnegative data factorization and the specific purpose characterized by the intrinsic and penalty graphs. Our contributions are two-fold. On the one hand, we present a multiplicative iterative procedure for nonnegative graph embedding, which sign... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-label sparse coding for automatic image annotation

    Publication Year: 2009, Page(s):1643 - 1650
    Cited by:  Papers (34)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (591 KB) | HTML iconHTML

    In this paper, we present a multi-label sparse coding framework for feature extraction and classification within the context of automatic image annotation. First, each image is encoded into a so-called supervector, derived from the universal Gaussian Mixture Models on orderless image patches. Then, a label sparse coding based subspace learning algorithm is derived to effectively harness multi-labe... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient planar graph cuts with applications in Computer Vision

    Publication Year: 2009, Page(s):351 - 356
    Cited by:  Papers (28)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (785 KB) | HTML iconHTML

    We present a fast graph cut algorithm for planar graphs. It is based on the graph theoretical work and leads to an efficient method that we apply on shape matching and image segmentation. In contrast to currently used methods in computer vision, the presented approach provides an upper bound for its runtime behavior that is almost linear. In particular, we are able to match two different planar sh... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Projective least-squares: Global solutions with local optimization

    Publication Year: 2009, Page(s):1216 - 1223
    Cited by:  Papers (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1470 KB) | HTML iconHTML

    Work in multiple view geometry has focused on obtaining globally optimal solutions at the price of computational time efficiency. On the other hand, traditional bundle adjustment algorithms have been found to provide good solutions even though there may be multiple local minima. In this paper we justify this observation by giving a simple sufficient condition for global optimality that can be used... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image categorization with spatial mismatch kernels

    Publication Year: 2009, Page(s):397 - 404
    Cited by:  Papers (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (416 KB) | HTML iconHTML

    This paper presents a new class of 2D string kernels, called spatial mismatch kernels, for use with support vector machine (SVM) in a discriminative approach to the image categorization problem. We first represent images as 2D sequences of those visual keywords obtained by clustering all the blocks that we divide images into on a regular grid. Through decomposing each 2D sequence into two parallel... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Support Vector Machines in face recognition with occlusions

    Publication Year: 2009, Page(s):136 - 141
    Cited by:  Papers (18)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (792 KB) | HTML iconHTML

    Support vector machines (SVM) are one of the most useful techniques in classification problems. One clear example is face recognition. However, SVM cannot be applied when the feature vectors defining our samples have missing entries. This is clearly the case in face recognition when occlusions are present in the training and/or testing sets. When k features are missing in a sample vector of class ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Markerless Motion Capture with unsynchronized moving cameras

    Publication Year: 2009, Page(s):224 - 231
    Cited by:  Papers (64)  |  Patents (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (13203 KB) | HTML iconHTML Multimedia Media

    In this work we present an approach for markerless motion capture (MoCap) of articulated objects, which are recorded with multiple unsynchronized moving cameras. Instead of using fixed (and expensive) hardware synchronized cameras, this approach allows us to track people with off-the-shelf handheld video cameras. To prepare a sequence for motion capture, we first reconstruct the static background ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Coupled Spectral Regression for matching heterogeneous faces

    Publication Year: 2009, Page(s):1123 - 1128
    Cited by:  Papers (26)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (384 KB) | HTML iconHTML

    Face recognition algorithms need to deal with variable lighting conditions. Near infrared (NIR) image based face recognition technology has been proposed to effectively overcome this difficulty. However, it requires that the enrolled face images be captured using NIR images whereas many applications require visual (VIS) images for enrollment templates. To take advantage of NIR face images for illu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning color and locality cues for moving object detection and segmentation

    Publication Year: 2009, Page(s):320 - 327
    Cited by:  Papers (10)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (3039 KB) | HTML iconHTML

    This paper presents an algorithm for automatically detecting and segmenting a moving object from a monocular video. Detecting and segmenting a moving object from a video with limited object motion is challenging. Since existing automatic algorithms rely on motion to detect the moving object, they cannot work well when the object motion is sparse and insufficient. In this paper, we present an unsup... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiple instance fFeature for robust part-based object detection

    Publication Year: 2009, Page(s):405 - 412
    Cited by:  Papers (22)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (615 KB) | HTML iconHTML

    Feature misalignment in object detection refers to the phenomenon that features which fire up in some positive detection windows do not fire up in other positive detection windows. Most often it is caused by pose variation and local part deformation. Previous work either totally ignores this issue, or naively performs a local exhaustive search to better position each feature. We propose a learning... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • (De) focusing on global light transport for active scene recovery

    Publication Year: 2009, Page(s):2969 - 2976
    Cited by:  Papers (15)  |  Patents (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (6774 KB) | HTML iconHTML

    Most active scene recovery techniques assume that a scene point is illuminated only directly by the illumination source. Consequently, global illumination effects due to inter-reflections, sub-surface scattering and volumetric scattering introduce strong biases in the recovered scene shape. Our goal is to recover scene properties in the presence of global illumination. To this end, we study the in... View full abstract»

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

    Publication Year: 2009, Page(s):1682 - 1689
    Cited by:  Papers (9)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (352 KB) | HTML iconHTML

    In this paper, we investigate how to incorporate spatial and/or temporal contextual information into classical histogram features with the aim of boosting visual classification performance. Firstly, we show that the stationary distribution derived from the normalized histogram-bin co-occurrence matrix characterizes the row sums of the original histogram-bin co-occurrence matrix. This underlying ra... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognizing human group activities with localized causalities

    Publication Year: 2009, Page(s):1470 - 1477
    Cited by:  Papers (21)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1003 KB) | HTML iconHTML

    The aim of this paper is to address the problem of recognizing human group activities in surveillance videos. This task has great potentials in practice, however was rarely studied due to the lack of benchmark database and the difficulties caused by large intra-class variations. Our contributions are two-fold. Firstly, we propose to encode the group-activities with three types of localized causali... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Shape evolution for rigid and nonrigid shape registration and recovery

    Publication Year: 2009, Page(s):164 - 171
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1244 KB) | HTML iconHTML

    This paper addresses the problem of rigid and nonrigid shape registration and recovery in the presence of shape deformation, missing parts and/or overlapping of multiple shapes. A novel shape evolution approach based on truncated warping transformation formulated in an Energy-Minimization-Curve-Evolution framework is proposed to solve this problem. We deterministically model the rigid and nonrigid... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image categorization by learning with context and consistency

    Publication Year: 2009, Page(s):2719 - 2726
    Cited by:  Papers (6)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (383 KB) | HTML iconHTML

    This paper presents a novel semi-supervised learning method which can make use of intra-image semantic context and inter-image cluster consistency for image categorization with less labeled data. The image representation is first formed with the visual keywords generated by clustering all the blocks that we divide images into. The 2D spatial Markov chain model is then proposed to capture the seman... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Constrained clustering via spectral regularization

    Publication Year: 2009, Page(s):421 - 428
    Cited by:  Papers (15)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (1556 KB) | HTML iconHTML

    We propose a novel framework for constrained spectral clustering with pairwise constraints which specify whether two objects belong to the same cluster or not. Unlike previous methods that modify the similarity matrix with pairwise constraints, we adapt the spectral embedding towards an ideal embedding as consistent with the pairwise constraints as possible. Our formulation leads to a small semide... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • SIFT-Rank: Ordinal description for invariant feature correspondence

    Publication Year: 2009, Page(s):172 - 177
    Cited by:  Papers (15)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (548 KB) | HTML iconHTML

    This paper investigates ordinal image description for invariant feature correspondence. Ordinal description is a meta-technique which considers image measurements in terms of their ranks in a sorted array, instead of the measurement values themselves. Rank-ordering normalizes descriptors in a manner invariant under monotonic deformations of the underlying image measurements, and therefore serves a... View full abstract»

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

    Publication Year: 2009, Page(s):429 - 436
    Cited by:  Papers (59)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (636 KB) | HTML iconHTML

    This paper presents a novel discriminative learning method, called manifold discriminant analysis (MDA), to solve the problem of image set classification. By modeling each image set as a manifold, we formulate the problem as classification-oriented multi-manifolds learning. Aiming at maximizing “manifold margin”, MDA seeks to learn an embedding space, where manifolds with different class labels ar... View full abstract»

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