By Topic

2013 IEEE International Conference on Computer Vision

Date 1-8 Dec. 2013

Filter Results

Displaying Results 1 - 25 of 464
  • [Title page i]

    Publication Year: 2013, Page(s): i
    Request permission for commercial reuse | PDF file iconPDF (31 KB)
    Freely Available from IEEE
  • [Title page iii]

    Publication Year: 2013, Page(s): iii
    Request permission for commercial reuse | PDF file iconPDF (201 KB)
    Freely Available from IEEE
  • [Copyright notice]

    Publication Year: 2013, Page(s): iv
    Request permission for commercial reuse | PDF file iconPDF (366 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2013, Page(s):v - xxxiv
    Request permission for commercial reuse | PDF file iconPDF (220 KB)
    Freely Available from IEEE
  • Message from General Chairs

    Publication Year: 2013, Page(s):xxxv - xxxvi
    Request permission for commercial reuse | PDF file iconPDF (87 KB) | HTML iconHTML
    Freely Available from IEEE
  • Message from Program Chairs

    Publication Year: 2013, Page(s):xxxvii - xxxviii
    Request permission for commercial reuse | PDF file iconPDF (273 KB) | HTML iconHTML
    Freely Available from IEEE
  • Organizing Committee and Area Chairs

    Publication Year: 2013, Page(s):xxxix - xl
    Request permission for commercial reuse | PDF file iconPDF (324 KB)
    Freely Available from IEEE
  • Sponsors

    Publication Year: 2013, Page(s): xli
    Request permission for commercial reuse | PDF file iconPDF (274 KB)
    Freely Available from IEEE
  • HOGgles: Visualizing Object Detection Features

    Publication Year: 2013, Page(s):1 - 8
    Cited by:  Papers (44)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4221 KB) | HTML iconHTML

    We introduce algorithms to visualize feature spaces used by object detectors. The tools in this paper allow a human to put on 'HOG goggles' and perceive the visual world as a HOG based object detector sees it. We found that these visualizations allow us to analyze object detection systems in new ways and gain new insight into the detector's failures. For example, when we visualize the features for... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • How Do You Tell a Blackbird from a Crow?

    Publication Year: 2013, Page(s):9 - 16
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1051 KB) | HTML iconHTML

    How do you tell a blackbird from a crow? There has been great progress toward automatic methods for visual recognition, including fine-grained visual categorization in which the classes to be distinguished are very similar. In a task such as bird species recognition, automatic recognition systems can now exceed the performance of non-experts - most people are challenged to name a couple dozen bird... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Regionlets for Generic Object Detection

    Publication Year: 2013, Page(s):17 - 24
    Cited by:  Papers (61)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (491 KB) | HTML iconHTML Multimedia Media

    Generic object detection is confronted by dealing with different degrees of variations in distinct object classes with tractable computations, which demands for descriptive and flexible object representations that are also efficient to evaluate for many locations. In view of this, we propose to model an object class by a cascaded boosting classifier which integrates various types of features from ... View full abstract»

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

    Publication Year: 2013, Page(s):25 - 32
    Cited by:  Papers (18)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1093 KB) | HTML iconHTML Multimedia Media

    Many tasks in computer vision are formulated as graph matching problems. Despite the NP-hard nature of the problem, fast and accurate approximations have led to significant progress in a wide range of applications. Learning graph models from observed data, however, still remains a challenging issue. This paper presents an effective scheme to parameterize a graph model, and learn its structural att... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Shape Anchors for Data-Driven Multi-view Reconstruction

    Publication Year: 2013, Page(s):33 - 40
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2626 KB) | HTML iconHTML

    We present a data-driven method for building dense 3D reconstructions using a combination of recognition and multi-view cues. Our approach is based on the idea that there are image patches that are so distinctive that we can accurately estimate their latent 3D shapes solely using recognition. We call these patches shape anchors, and we use them as the basis of a multi-view reconstruction system th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Deterministic Fitting of Multiple Structures Using Iterative MaxFS with Inlier Scale Estimation

    Publication Year: 2013, Page(s):41 - 48
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (943 KB) | HTML iconHTML

    We present an efficient deterministic hypothesis generation algorithm for robust fitting of multiple structures based on the maximum feasible subsystem (MaxFS) framework. Despite its advantage, a global optimization method such as MaxFS has two main limitations for geometric model fitting. First, its performance is much influenced by the user-specified inlier scale. Second, it is computationally i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Constant Time Weighted Median Filtering for Stereo Matching and Beyond

    Publication Year: 2013, Page(s):49 - 56
    Cited by:  Papers (40)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1268 KB) | HTML iconHTML Multimedia Media

    Despite the continuous advances in local stereo matching for years, most efforts are on developing robust cost computation and aggregation methods. Little attention has been seriously paid to the disparity refinement. In this work, we study weighted median filtering for disparity refinement. We discover that with this refinement, even the simple box filter aggregation achieves comparable accuracy ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Refractive Structure-from-Motion on Underwater Images

    Publication Year: 2013, Page(s):57 - 64
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (986 KB) | HTML iconHTML

    In underwater environments, cameras need to be confined in an underwater housing, viewing the scene through a piece of glass. In case of flat port underwater housings, light rays entering the camera housing are refracted twice, due to different medium densities of water, glass, and air. This causes the usually linear rays of light to bend and the commonly used pinhole camera model to be invalid. W... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Live Metric 3D Reconstruction on Mobile Phones

    Publication Year: 2013, Page(s):65 - 72
    Cited by:  Papers (34)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (6546 KB) | HTML iconHTML

    In this paper, we propose a complete on-device 3D reconstruction pipeline for mobile monocular hand-held devices, which generates dense 3D models with absolute scale on-site while simultaneously supplying the user with real-time interactive feedback. The method fills a gap in current cloud-based mobile reconstruction services as it ensures at capture time that the acquired image set fulfills desir... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Joint Subspace Stabilization for Stereoscopic Video

    Publication Year: 2013, Page(s):73 - 80
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1172 KB) | HTML iconHTML Multimedia Media

    Shaky stereoscopic video is not only unpleasant to watch but may also cause 3D fatigue. Stabilizing the left and right view of a stereoscopic video separately using a monocular stabilization method tends to both introduce undesirable vertical disparities and damage horizontal disparities, which may destroy the stereoscopic viewing experience. In this paper, we present a joint subspace stabilizatio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Video Synopsis by Heterogeneous Multi-source Correlation

    Publication Year: 2013, Page(s):81 - 88
    Cited by:  Papers (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1058 KB) | HTML iconHTML

    Generating coherent synopsis for surveillance video stream remains a formidable challenge due to the ambiguity and uncertainty inherent to visual observations. In contrast to existing video synopsis approaches that rely on visual cues alone, we propose a novel multi-source synopsis framework capable of correlating visual data and independent non-visual auxiliary information to better describe and ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • DCSH - Matching Patches in RGBD Images

    Publication Year: 2013, Page(s):89 - 96
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1240 KB) | HTML iconHTML

    We extend patch based methods to work on patches in 3D space. We start with Coherency Sensitive Hashing (CSH), which is an algorithm for matching patches between two RGB images, and extend it to work with RGBD images. This is done by warping all 3D patches to a common virtual plane in which CSH is performed. To avoid noise due to warping of patches of various normals and depths, we estimate a grou... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Scene Text Localization and Recognition with Oriented Stroke Detection

    Publication Year: 2013, Page(s):97 - 104
    Cited by:  Papers (35)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1615 KB) | HTML iconHTML

    An unconstrained end-to-end text localization and recognition method is presented. The method introduces a novel approach for character detection and recognition which combines the advantages of sliding-window and connected component methods. Characters are detected and recognized as image regions which contain strokes of specific orientations in a specific relative position, where the strokes are... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adapting Classification Cascades to New Domains

    Publication Year: 2013, Page(s):105 - 112
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1549 KB) | HTML iconHTML

    Classification cascades have been very effective for object detection. Such a cascade fails to perform well in data domains with variations in appearances that may not be captured in the training examples. This limited generalization severely restricts the domains for which they can be used effectively. A common approach to address this limitation is to train a new cascade of classifiers from scra... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Deep Learning Identity-Preserving Face Space

    Publication Year: 2013, Page(s):113 - 120
    Cited by:  Papers (43)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1536 KB) | HTML iconHTML Multimedia Media

    Face recognition with large pose and illumination variations is a challenging problem in computer vision. This paper addresses this challenge by proposing a new learning based face representation: the face identity-preserving (FIP) features. Unlike conventional face descriptors, the FIP features can significantly reduce intra-identity variances, while maintaining discriminative ness between identi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-stage Contextual Deep Learning for Pedestrian Detection

    Publication Year: 2013, Page(s):121 - 128
    Cited by:  Papers (29)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (695 KB) | HTML iconHTML

    Cascaded classifiers have been widely used in pedestrian detection and achieved great success. These classifiers are trained sequentially without joint optimization. In this paper, we propose a new deep model that can jointly train multi-stage classifiers through several stages of back propagation. It keeps the score map output by a classifier within a local region and uses it as contextual inform... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Unsupervised Random Forest Manifold Alignment for Lipreading

    Publication Year: 2013, Page(s):129 - 136
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (712 KB) | HTML iconHTML

    Lip reading from visual channels remains a challenging topic considering the various speaking characteristics. In this paper, we address an efficient lip reading approach by investigating the unsupervised random forest manifold alignment (RFMA). The density random forest is employed to estimate affinity of patch trajectories in speaking facial videos. We propose novel criteria for node splitting t... View full abstract»

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