By Topic

2009 IEEE 12th International Conference on Computer Vision

Date Sept. 29 2009-Oct. 2 2009

Filter Results

Displaying Results 1 - 25 of 331
  • Table of contents

    Publication Year: 2009, Page(s):i - xvii
    Request permission for commercial reuse | PDF file iconPDF (1106 KB)
    Freely Available from IEEE
  • Preface

    Publication Year: 2009, Page(s): xviii
    Request permission for commercial reuse | PDF file iconPDF (566 KB) | HTML iconHTML
    Freely Available from IEEE
  • Message from the Program Chairs

    Publication Year: 2009, Page(s):xix - xx
    Request permission for commercial reuse | PDF file iconPDF (571 KB) | HTML iconHTML
    Freely Available from IEEE
  • Organizing Committee

    Publication Year: 2009, Page(s):xxi - xxix
    Request permission for commercial reuse | PDF file iconPDF (873 KB)
    Freely Available from IEEE
  • Corporate sponsors

    Publication Year: 2009, Page(s): xxx
    Request permission for commercial reuse | PDF file iconPDF (7245 KB)
    Freely Available from IEEE
  • Oral session 1: Segmentation I

    Publication Year: 2009, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (17 KB)
    Freely Available from IEEE
  • Decomposing a scene into geometric and semantically consistent regions

    Publication Year: 2009, Page(s):1 - 8
    Cited by:  Papers (163)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3076 KB) | HTML iconHTML

    High-level, or holistic, scene understanding involves reasoning about objects, regions, and the 3D relationships between them. This requires a representation above the level of pixels that can be endowed with high-level attributes such as class of object/region, its orientation, and (rough 3D) location within the scene. Towards this goal, we propose a region-based model which combines appearance a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Boundary ownership by lifting to 2.1D

    Publication Year: 2009, Page(s):9 - 16
    Cited by:  Papers (8)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1498 KB) | HTML iconHTML

    This paper addresses the “boundary ownership” problem, also known as the figure/ground assignment problem. Estimating boundary ownerships is a key step in perceptual organization: it allows higher-level processing to be applied on non-accidental shapes corresponding to figural regions. Existing methods for estimating the boundary ownerships for a given set of boundary curves model th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Curvature regularity for region-based image segmentation and inpainting: A linear programming relaxation

    Publication Year: 2009, Page(s):17 - 23
    Cited by:  Papers (23)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (543 KB) | HTML iconHTML

    We consider a class of region-based energies for image segmentation and inpainting which combine region integrals with curvature regularity of the region boundary. To minimize such energies, we formulate an integer linear program which jointly estimates regions and their boundaries. Curvature regularity is imposed by respective costs on pairs of adjacent boundary segments. By solving the associate... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Oral session 2: Human detection

    Publication Year: 2009, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (18 KB)
    Freely Available from IEEE
  • Human detection using partial least squares analysis

    Publication Year: 2009, Page(s):24 - 31
    Cited by:  Papers (165)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (827 KB) | HTML iconHTML Multimedia Media

    Significant research has been devoted to detecting people in images and videos. In this paper we describe a human detection method that augments widely used edge-based features with texture and color information, providing us with a much richer descriptor set. This augmentation results in an extremely high-dimensional feature space (more than 170,000 dimensions). In such high-dimensional spaces, c... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An HOG-LBP human detector with partial occlusion handling

    Publication Year: 2009, Page(s):32 - 39
    Cited by:  Papers (406)  |  Patents (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1030 KB) | HTML iconHTML Multimedia Media

    By combining Histograms of Oriented Gradients (HOG) and Local Binary Pattern (LBP) as the feature set, we propose a novel human detection approach capable of handling partial occlusion. Two kinds of detectors, i.e., global detector for whole scanning windows and part detectors for local regions, are learned from the training data using linear SVM. For each ambiguous scanning window, we construct a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Max-margin additive classifiers for detection

    Publication Year: 2009, Page(s):40 - 47
    Cited by:  Papers (53)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (420 KB) | HTML iconHTML

    We present methods for training high quality object detectors very quickly. The core contribution is a pair of fast training algorithms for piece-wise linear classifiers, which can approximate arbitrary additive models. The classifiers are trained in a max-margin framework and significantly outperform linear classifiers on a variety of vision datasets. We report experimental results quantifying tr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Oral session 3: Learning

    Publication Year: 2009, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (17 KB)
    Freely Available from IEEE
  • Kernel methods for weakly supervised mean shift clustering

    Publication Year: 2009, Page(s):48 - 55
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2606 KB) | HTML iconHTML

    Mean shift clustering is a powerful unsupervised data analysis technique which does not require prior knowledge of the number of clusters, and does not constrain the shape of the clusters. The data association criteria is based on the underlying probability distribution of the data points which is defined in advance via the employed distance metric. In many problem domains, the initially designed ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Finding shareable informative patterns and optimal coding matrix for multiclass boosting

    Publication Year: 2009, Page(s):56 - 63
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (162 KB) | HTML iconHTML

    A multiclass classification problem can be reduced to a collection of binary problems using an error-correcting coding matrix that specifies the binary partitions of the classes. The final classifier is an ensemble of base classifiers learned on binary problems and its performance is affected by two major factors: the qualities of the base classifiers and the coding matrix. Previous studies either... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning with dynamic group sparsity

    Publication Year: 2009, Page(s):64 - 71
    Cited by:  Papers (38)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (208 KB) | HTML iconHTML

    This paper investigates a new learning formulation called dynamic group sparsity. It is a natural extension of the standard sparsity concept in compressive sensing, and is motivated by the observation that in some practical sparse data the nonzero coefficients are often not random but tend to be clustered. Intuitively, better results can be achieved in these cases by reasonably utilizing both clus... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Oral session 4: Geometry

    Publication Year: 2009, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (17 KB)
    Freely Available from IEEE
  • Building Rome in a day

    Publication Year: 2009, Page(s):72 - 79
    Cited by:  Papers (243)  |  Patents (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2524 KB) | HTML iconHTML

    We present a system that can match and reconstruct 3D scenes from extremely large collections of photographs such as those found by searching for a given city (e.g., Rome) on Internet photo sharing sites. Our system uses a collection of novel parallel distributed matching and reconstruction algorithms, designed to maximize parallelism at each stage in the pipeline and minimize serialization bottle... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Reconstructing building interiors from images

    Publication Year: 2009, Page(s):80 - 87
    Cited by:  Papers (79)  |  Patents (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (7102 KB) | HTML iconHTML Multimedia Media

    This paper proposes a fully automated 3D reconstruction and visualization system for architectural scenes (interiors and exteriors). The reconstruction of indoor environments from photographs is particularly challenging due to texture-poor planar surfaces such as uniformly-painted walls. Our system first uses structure-from-motion, multi-view stereo, and a stereo algorithm specifically designed fo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Is dual linear self-calibration artificially ambiguous?

    Publication Year: 2009, Page(s):88 - 95
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1447 KB) | HTML iconHTML Multimedia Media

    This purely theoretical work investigates the problem of artificial singularities in camera self-calibration. Self-calibration allows one to upgrade a projective reconstruction to metric and has a concise and well-understood formulation based on the Dual Absolute Quadric (DAQ), a rank-3 quadric envelope satisfying (nonlinear) ‘spectral constraints’: it must be positive of rank 3. The... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Globally optimal affine epipolar geometry from apparent contours

    Publication Year: 2009, Page(s):96 - 103
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1730 KB) | HTML iconHTML

    We study the problem of estimating the epipolar geometry from apparent contours of smooth curved surfaces with affine camera models. Since apparent contours are viewpoint dependent, the only true image correspondences are projections of the frontier points, i.e., surface points whose tangent planes are also their epipolar planes. However, frontier points are unknown a priori and must be estimated ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Oral session 5: Activity

    Publication Year: 2009, Page(s): 1
    Request permission for commercial reuse | PDF file iconPDF (17 KB)
    Freely Available from IEEE
  • Activity recognition using the velocity histories of tracked keypoints

    Publication Year: 2009, Page(s):104 - 111
    Cited by:  Papers (143)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1253 KB) | HTML iconHTML

    We present an activity recognition feature inspired by human psychophysical performance. This feature is based on the velocity history of tracked keypoints. We present a generative mixture model for video sequences using this feature, and show that it performs comparably to local spatio-temporal features on the KTH activity recognition dataset. In addition, we contribute a new activity recognition... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Quasi-periodic event analysis for social game retrieval

    Publication Year: 2009, Page(s):112 - 119
    Cited by:  Papers (20)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (963 KB) | HTML iconHTML Multimedia Media

    A new problem of retrieving social games from unstructured videos is proposed. Social games are characterized by repetitions (with variations) of alternating turns between two players. We define games as quasi-periodic motion patterns in video based on their repetitiveness property. We have developed an algorithm to extract such patterns from video. The patterns extracted by our method, from video... View full abstract»

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