Sciweavers

ECCV
2008
Springer
14 years 12 months ago
Beyond Nouns: Exploiting Prepositions and Comparative Adjectives for Learning Visual Classifiers
Learning visual classifiers for object recognition from weakly labeled data requires determining correspondence between image regions and semantic object classes. Most approaches u...
Abhinav Gupta, Larry S. Davis
ECCV
2008
Springer
14 years 12 months ago
Grassmann Registration Manifolds for Face Recognition
Abstract. Motivated by image perturbation and the geometry of manifolds, we present a novel method combining these two elements. First, we form a tangent space from a set of pertur...
Yui Man Lui, J. Ross Beveridge
ECCV
2008
Springer
14 years 12 months ago
Localizing Objects with Smart Dictionaries
Abstract. We present an approach to determine the category and location of objects in images. It performs very fast categorization of each pixel in an image, a brute-force approach...
Brian Fulkerson, Andrea Vedaldi, Stefano Soatto
ECCV
2008
Springer
14 years 12 months ago
What Is a Good Nearest Neighbors Algorithm for Finding Similar Patches in Images?
Many computer vision algorithms require searching a set of images for similar patches, which is a very expensive operation. In this work, we compare and evaluate a number of neares...
Neeraj Kumar, Li Zhang, Shree K. Nayar
ECCV
2008
Springer
14 years 12 months ago
Semi-supervised On-Line Boosting for Robust Tracking
Abstract. Recently, on-line adaptation of binary classifiers for tracking have been investigated. On-line learning allows for simple classifiers since only the current view of the ...
Helmut Grabner, Christian Leistner, Horst Bischof
ECCV
2008
Springer
14 years 12 months ago
Scale Invariant Action Recognition Using Compound Features Mined from Dense Spatio-temporal Corners
Abstract. The use of sparse invariant features to recognise classes of actions or objects has become common in the literature. However, features are often "engineered" to...
Andrew Gilbert, John Illingworth, Richard Bowden
ECCV
2008
Springer
14 years 12 months ago
Multiple Component Learning for Object Detection
Abstract. Object detection is one of the key problems in computer vision. In the last decade, discriminative learning approaches have proven effective in detecting rigid objects, a...
Boris Babenko, Pietro Perona, Piotr Dollár,...
ECCV
2008
Springer
14 years 12 months ago
A Lattice-Preserving Multigrid Method for Solving the Inhomogeneous Poisson Equations Used in Image Analysis
Abstract. The inhomogeneous Poisson (Laplace) equation with internal Dirichlet boundary conditions has recently appeared in several applications ranging from image segmentation [1,...
Leo Grady
ECCV
2008
Springer
14 years 12 months ago
Floor Fields for Tracking in High Density Crowd Scenes
Abstract. This paper presents an algorithm for tracking individual targets in high density crowd scenes containing hundreds of people. Tracking in such a scene is extremely challen...
Saad Ali, Mubarak Shah
ECCV
2008
Springer
14 years 12 months ago
Brain Hallucination
Abstract. In this paper, we investigate brain hallucination, or generating a high resolution brain image from an input low-resolution image, with the help of another high resolutio...
François Rousseau