2014 IEEE Conference on Computer Vision and Pattern Recognition

23-28 June 2014

Filter Results

Displaying Results 1 - 25 of 550
  • [Front cover]

    Publication Year: 2014, Page(s): C4
    Request permission for commercial reuse | |PDF file iconPDF (875 KB)
    Freely Available from IEEE
  • [Title page i]

    Publication Year: 2014, Page(s): i
    Request permission for commercial reuse | |PDF file iconPDF (111 KB)
    Freely Available from IEEE
  • [Title page iii]

    Publication Year: 2014, Page(s): iii
    Request permission for commercial reuse | |PDF file iconPDF (146 KB)
    Freely Available from IEEE
  • [Copyright notice]

    Publication Year: 2014, Page(s): iv
    Request permission for commercial reuse | |PDF file iconPDF (122 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2014, Page(s):v - xxxvi
    Request permission for commercial reuse | |PDF file iconPDF (187 KB)
    Freely Available from IEEE
  • Message from the General and Program Chairs

    Publication Year: 2014, Page(s):xxxvii - xxxix
    Request permission for commercial reuse | |PDF file iconPDF (107 KB) | HTML iconHTML
    Freely Available from IEEE
  • Organizing Committee

    Publication Year: 2014, Page(s):xl - xli
    Request permission for commercial reuse | |PDF file iconPDF (114 KB)
    Freely Available from IEEE
  • Reviewers

    Publication Year: 2014, Page(s): xlii
    Request permission for commercial reuse | |PDF file iconPDF (98 KB)
    Freely Available from IEEE
  • Fast and Accurate Image Matching with Cascade Hashing for 3D Reconstruction

    Publication Year: 2014, Page(s):1 - 8
    Cited by:  Papers (25)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (1399 KB) | HTML iconHTML

    Image matching is one of the most challenging stages in 3D reconstruction, which usually occupies half of computational cost and inaccurate matching may lead to failure of reconstruction. Therefore, fast and accurate image matching is very crucial for 3D reconstruction. In this paper, we proposed a Cascade Hashing strategy to speed up the image matching. In order to accelerate the image matching, ... View full abstract»

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

    Publication Year: 2014, Page(s):9 - 16
    Cited by:  Papers (22)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (2218 KB) | HTML iconHTML

    The initial steps of many computer vision algorithms are interest point extraction and matching. In larger image sets the pairwise matching of interest point descriptors between images is an important bottleneck. For each descriptor in one image the (approximate) nearest neighbor in the other one has to be found and checked against the second-nearest neighbor to ensure the correspondence is unambi... View full abstract»

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

    Publication Year: 2014, Page(s):17 - 24
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (403 KB) | HTML iconHTML

    When do the visual rays associated with triplets of point correspondences converge, that is, intersect in a common point? Classical models of trinocular geometry based on the fundamental matrices and trifocal tensor associated with the corresponding cameras only provide partial answers to this fundamental question, in large part because of underlying, but seldom explicit, general configuration ass... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Critical Configurations for Radial Distortion Self-Calibration

    Publication Year: 2014, Page(s):25 - 32
    Cited by:  Papers (9)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (1554 KB) | HTML iconHTML

    In this paper, we study the configurations of motion and structure that lead to inherent ambiguities in radial distortion estimation (or 3D reconstruction with unknown radial distortions). By analyzing the motion field of radially distorted images, we solve for critical surface pairs that can lead to the same motion field under different radial distortions and possibly different camera motions. We... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Minimal Solvers for Relative Pose with a Single Unknown Radial Distortion

    Publication Year: 2014, Page(s):33 - 40
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (746 KB) | HTML iconHTML

    In this paper, we study the problems of estimating relative pose between two cameras in the presence of radial distortion. Specifically, we consider minimal problems where one of the cameras has no or known radial distortion. There are three useful cases for this setup with a single unknown distortion: (i) fundamental matrix estimation where the two cameras are uncalibrated, (ii) essential matrix ... View full abstract»

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

    Publication Year: 2014, Page(s):41 - 48
    Cited by:  Papers (23)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (1531 KB) | HTML iconHTML

    We address the problem of populating object category detection datasets with dense, per-object 3D reconstructions, bootstrapped from class labels, ground truth figure-ground segmentations and a small set of keypoint annotations. Our proposed algorithm first estimates camera viewpoint using rigid structure-from-motion, then reconstructs object shapes by optimizing over visual hull proposals guided ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spectral Graph Reduction for Efficient Image and Streaming Video Segmentation

    Publication Year: 2014, Page(s):49 - 56
    Cited by:  Papers (23)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (913 KB) | HTML iconHTML

    Computational and memory costs restrict spectral techniques to rather small graphs, which is a serious limitation especially in video segmentation. In this paper, we propose the use of a reduced graph based on superpixels. In contrast to previous work, the reduced graph is reweighted such that the resulting segmentation is equivalent, under certain assumptions, to that of the full graph. We consid... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Weakly Supervised Multiclass Video Segmentation

    Publication Year: 2014, Page(s):57 - 64
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (1704 KB) | HTML iconHTML

    The desire of enabling computers to learn semantic concepts from large quantities of Internet videos has motivated increasing interests on semantic video understanding, while video segmentation is important yet challenging for understanding videos. The main difficulty of video segmentation arises from the burden of labeling training samples, making the problem largely unsolved. In this paper, we p... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Video Motion Segmentation Using New Adaptive Manifold Denoising Model

    Publication Year: 2014, Page(s):65 - 72
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (629 KB) | HTML iconHTML

    Video motion segmentation techniques automatically segment and track objects and regions from videos or image sequences as a primary processing step for many computer vision applications. We propose a novel motion segmentation approach for both rigid and non-rigid objects using adaptive manifold denoising. We first introduce an adaptive kernel space in which two feature trajectories are mapped int... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cut, Glue, & Cut: A Fast, Approximate Solver for Multicut Partitioning

    Publication Year: 2014, Page(s):73 - 80
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (850 KB) | HTML iconHTML

    Recently, unsupervised image segmentation has become increasingly popular. Starting from a superpixel segmentation, an edge-weighted region adjacency graph is constructed. Amongst all segmentations of the graph, the one which best conforms to the given image evidence, as measured by the sum of cut edge weights, is chosen. Since this problem is NP-hard, we propose a new approximate solver based on ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neural Decision Forests for Semantic Image Labelling

    Publication Year: 2014, Page(s):81 - 88
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (921 KB) | HTML iconHTML

    In this work we present Neural Decision Forests, a novel approach to jointly tackle data representation- and discriminative learning within randomized decision trees. Recent advances of deep learning architectures demonstrate the power of embedding representation learning within the classifier -- An idea that is intuitively supported by the hierarchical nature of the decision forest model where th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pulling Things out of Perspective

    Publication Year: 2014, Page(s):89 - 96
    Cited by:  Papers (48)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (2231 KB) | HTML iconHTML

    The limitations of current state-of-the-art methods for single-view depth estimation and semantic segmentations are closely tied to the property of perspective geometry, that the perceived size of the objects scales inversely with the distance. In this paper, we show that we can use this property to reduce the learning of a pixel-wise depth classifier to a much simpler classifier predicting only t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Event Detection Using Multi-level Relevance Labels and Multiple Features

    Publication Year: 2014, Page(s):97 - 104
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (574 KB) | HTML iconHTML

    We address the challenging problem of utilizing related exemplars for complex event detection while multiple features are available. Related exemplars share certain positive elements of the event, but have no uniform pattern due to the huge variance of relevance levels among different related exemplars. None of the existing multiple feature fusion methods can deal with the related exemplars. In th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Full-Angle Quaternions for Robustly Matching Vectors of 3D Rotations

    Publication Year: 2014, Page(s):105 - 112
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (741 KB) | HTML iconHTML

    In this paper we introduce a new distance for robustly matching vectors of 3D rotations. A special representation of 3D rotations, which we coin full-angle quaternion (FAQ), allows us to express this distance as Euclidean. We apply the distance to the problems of 3D shape recognition from point clouds and 2D object tracking in color video. For the former, we introduce a hashing scheme for scale an... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Human vs. Computer in Scene and Object Recognition

    Publication Year: 2014, Page(s):113 - 120
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (8109 KB) | HTML iconHTML

    Several decades of research in computer and primate vision have resulted in many models (some specialized for one problem, others more general) and invaluable experimental data. Here, to help focus research efforts onto the hardest unsolved problems, and bridge computer and human vision, we define a battery of 5 tests that measure the gap between human and machine performances in several dimension... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Semi-supervised Spectral Clustering for Image Set Classification

    Publication Year: 2014, Page(s):121 - 128
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (705 KB) | HTML iconHTML

    We present an image set classification algorithm based on unsupervised clustering of labeled training and unlabeled test data where labels are only used in the stopping criterion. The probability distribution of each class over the set of clusters is used to define a true set based similarity measure. To this end, we propose an iterative sparse spectral clustering algorithm. In each iteration, a p... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Look at the Driver, Look at the Road: No Distraction! No Accident!

    Publication Year: 2014, Page(s):129 - 136
    Cited by:  Papers (14)
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (1224 KB) | HTML iconHTML

    The paper proposes an advanced driver-assistance system that correlates the driver's head pose to road hazards by analyzing both simultaneously. In particular, we aim at the prevention of rear-end crashes due to driver fatigue or distraction. We contribute by three novel ideas: Asymmetric appearance-modeling, 2D to 3D pose estimation enhanced by the introduced Fermat-point transform, and adaptatio... View full abstract»

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