By Topic

Computer Vision (ICCV), 2011 IEEE International Conference on

Date 6-13 Nov. 2011

Filter Results

Displaying Results 1 - 25 of 362
  • Table of contents

    Publication Year: 2011 , Page(s): i - xxiv
    Request Permissions | PDF file iconPDF (214 KB)  
    Freely Available from IEEE
  • Message from Program Chairs

    Publication Year: 2011 , Page(s): xxv - xxix
    Request Permissions | PDF file iconPDF (152 KB)  
    Freely Available from IEEE
  • ICCV2011 Committees

    Publication Year: 2011 , Page(s): xxx - xxxvii
    Request Permissions | PDF file iconPDF (131 KB)  
    Freely Available from IEEE
  • Corporate sponsors

    Publication Year: 2011 , Page(s): xxxviii
    Request Permissions | PDF file iconPDF (151 KB)  
    Freely Available from IEEE
  • Oral session 1-1

    Publication Year: 2011 , Page(s): xxxix
    Request Permissions | PDF file iconPDF (42 KB)  
    Freely Available from IEEE
  • A graph-matching kernel for object categorization

    Publication Year: 2011 , Page(s): 1792 - 1799
    Cited by:  Papers (36)
    Multimedia
    Request Permissions | Click to expandAbstract | PDF file iconPDF (1160 KB) |  | HTML iconHTML  

    This paper addresses the problem of category-level image classification. The underlying image model is a graph whose nodes correspond to a dense set of regions, and edges reflect the underlying grid structure of the image and act as springs to guarantee the geometric consistency of nearby regions during matching. A fast approximate algorithm for matching the graphs associated with two images is pr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Domain adaptation for object recognition: An unsupervised approach

    Publication Year: 2011 , Page(s): 999 - 1006
    Cited by:  Papers (60)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (401 KB) |  | HTML iconHTML  

    Adapting the classifier trained on a source domain to recognize instances from a new target domain is an important problem that is receiving recent attention. In this paper, we present one of the first studies on unsupervised domain adaptation in the context of object recognition, where we have labeled data only from the source domain (and therefore do not have correspondences between object categ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Structured class-labels in random forests for semantic image labelling

    Publication Year: 2011 , Page(s): 2190 - 2197
    Cited by:  Papers (22)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (1667 KB) |  | HTML iconHTML  

    In this paper we propose a simple and effective way to integrate structural information in random forests for semantic image labelling. By structural information we refer to the inherently available, topological distribution of object classes in a given image. Different object class labels will not be randomly distributed over an image but usually form coherently labelled regions. In this work we ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Oral session 1-2 [breaker-page]

    Publication Year: 2011 , Page(s): xl
    Request Permissions | PDF file iconPDF (42 KB)  
    Freely Available from IEEE
  • Perturb-and-MAP random fields: Using discrete optimization to learn and sample from energy models

    Publication Year: 2011 , Page(s): 193 - 200
    Cited by:  Papers (7)
    Multimedia
    Request Permissions | Click to expandAbstract | PDF file iconPDF (1767 KB) |  | HTML iconHTML  

    We propose a novel way to induce a random field from an energy function on discrete labels. It amounts to locally injecting noise to the energy potentials, followed by finding the global minimum of the perturbed energy function. The resulting Perturb-and-MAP random fields harness the power of modern discrete energy minimization algorithms, effectively transforming them into efficient random sampli... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Discriminative learning of relaxed hierarchy for large-scale visual recognition

    Publication Year: 2011 , Page(s): 2072 - 2079
    Cited by:  Papers (15)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (2120 KB) |  | HTML iconHTML  

    In the real visual world, the number of categories a classifier needs to discriminate is on the order of hundreds or thousands. For example, the SUN dataset [24] contains 899 scene categories and ImageNet [6] has 15,589 synsets. Designing a multiclass classifier that is both accurate and fast at test time is an extremely important problem in both machine learning and computer vision communities. T... View full abstract»

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

    Publication Year: 2011 , Page(s): 1668 - 1675
    Cited by:  Papers (20)  |  Patents (1)
    Multimedia
    Request Permissions | Click to expandAbstract | PDF file iconPDF (727 KB) |  | HTML iconHTML  

    This paper introduces a new formulation for discrete image labeling tasks, the Decision Tree Field (DTF), that combines and generalizes random forests and conditional random fields (CRF) which have been widely used in computer vision. In a typical CRF model the unary potentials are derived from sophisticated random forest or boosting based classifiers, however, the pairwise potentials are assumed ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Oral session 1-3 [breaker-page]

    Publication Year: 2011 , Page(s): xli
    Request Permissions | PDF file iconPDF (42 KB)  
    Freely Available from IEEE
  • Strong supervision from weak annotation: Interactive training of deformable part models

    Publication Year: 2011 , Page(s): 1832 - 1839
    Cited by:  Papers (18)
    Multimedia
    Request Permissions | Click to expandAbstract | PDF file iconPDF (2097 KB) |  | HTML iconHTML  

    We propose a framework for large scale learning and annotation of structured models. The system interleaves interactive labeling (where the current model is used to semi-automate the labeling of a new example) and online learning (where a newly labeled example is used to update the current model parameters). This framework is scalable to large datasets and complex image models and is shown to have... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Birdlets: Subordinate categorization using volumetric primitives and pose-normalized appearance

    Publication Year: 2011 , Page(s): 161 - 168
    Cited by:  Papers (35)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (7635 KB) |  | HTML iconHTML  

    Subordinate-level categorization typically rests on establishing salient distinctions between part-level characteristics of objects, in contrast to basic-level categorization, where the presence or absence of parts is determinative. We develop an approach for subordinate categorization in vision, focusing on an avian domain due to the fine-grained structure of the category taxonomy for this domain... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • From contours to 3D object detection and pose estimation

    Publication Year: 2011 , Page(s): 983 - 990
    Cited by:  Papers (18)
    Multimedia
    Request Permissions | Click to expandAbstract | PDF file iconPDF (9606 KB) |  | HTML iconHTML  

    This paper addresses view-invariant object detection and pose estimation from a single image. While recent work focuses on object-centered representations of point-based object features, we revisit the viewer-centered framework, and use image contours as basic features. Given training examples of arbitrary views of an object, we learn a sparse object model in terms of a few view-dependent shape te... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Oral session 2-1

    Publication Year: 2011 , Page(s): xlii
    Request Permissions | PDF file iconPDF (42 KB)  
    Freely Available from IEEE
  • What an image reveals about material reflectance

    Publication Year: 2011 , Page(s): 1076 - 1083
    Cited by:  Papers (9)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (4169 KB) |  | HTML iconHTML  

    We derive precise conditions under which material reflectance properties may be estimated from a single image of a homogeneous curved surface (canonically a sphere), lit by a directional source. Based on the observation that light is reflected along certain (a priori unknown) preferred directions such as the half-angle, we propose a semiparametric BRDF abstraction that lies between purely parametr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiplexed illumination for scene recovery in the presence of global illumination

    Publication Year: 2011 , Page(s): 691 - 698
    Cited by:  Papers (9)
    Multimedia
    Request Permissions | Click to expandAbstract | PDF file iconPDF (4211 KB) |  | HTML iconHTML  

    Global illumination effects such as inter-reflections and subsurface scattering result in systematic, and often significant errors in scene recovery using active illumination. Recently, it was shown that the direct and global components could be separated efficiently for a scene illuminated with a single light source. In this paper, we study the problem of direct-global separation for multiple lig... View full abstract»

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

    Publication Year: 2011 , Page(s): xliii
    Request Permissions | PDF file iconPDF (42 KB)  
    Freely Available from IEEE
  • Data-driven crowd analysis in videos

    Publication Year: 2011 , Page(s): 1235 - 1242
    Cited by:  Papers (25)
    Multimedia
    Request Permissions | Click to expandAbstract | PDF file iconPDF (6375 KB) |  | HTML iconHTML  

    In this work we present a new crowd analysis algorithm powered by behavior priors that are learned on a large database of crowd videos gathered from the Internet. The algorithm works by first learning a set of crowd behavior priors off-line. During testing, crowd patches are matched to the database and behavior priors are transferred. We adhere to the insight that despite the fact that the entire ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A “string of feature graphs” model for recognition of complex activities in natural videos

    Publication Year: 2011 , Page(s): 2595 - 2602
    Cited by:  Papers (16)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (1598 KB) |  | HTML iconHTML  

    Videos usually consist of activities involving interactions between multiple actors, sometimes referred to as complex activities. Recognition of such activities requires modeling the spatio-temporal relationships between the actors and their individual variabilities. In this paper, we consider the problem of recognition of complex activities in a video given a query example. We propose a new featu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning spatiotemporal graphs of human activities

    Publication Year: 2011 , Page(s): 778 - 785
    Cited by:  Papers (43)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (3338 KB) |  | HTML iconHTML  

    Complex human activities occurring in videos can be defined in terms of temporal configurations of primitive actions. Prior work typically hand-picks the primitives, their total number, and temporal relations (e.g., allow only followed-by), and then only estimates their relative significance for activity recognition. We advance prior work by learning what activity parts and their spatiotemporal re... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Human action recognition by learning bases of action attributes and parts

    Publication Year: 2011 , Page(s): 1331 - 1338
    Cited by:  Papers (28)
    Request Permissions | Click to expandAbstract | PDF file iconPDF (537 KB) |  | HTML iconHTML  

    In this work, we propose to use attributes and parts for recognizing human actions in still images. We define action attributes as the verbs that describe the properties of human actions, while the parts of actions are objects and poselets that are closely related to the actions. We jointly model the attributes and parts by learning a set of sparse bases that are shown to carry much semantic meani... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Oral session 2-3

    Publication Year: 2011 , Page(s): xliv
    Request Permissions | PDF file iconPDF (42 KB)  
    Freely Available from IEEE