Sciweavers

493 search results - page 35 / 99
» Generating Ambiguity in the Laboratory
Sort
View
CVPR
2003
IEEE
14 years 11 months ago
Learning Appearance and Transparency Manifolds of Occluded Objects in Layers
By mapping a set of input images to points in a lowdimensional manifold or subspace, it is possible to efficiently account for a small number of degrees of freedom. For example, i...
Brendan J. Frey, Nebojsa Jojic, Anitha Kannan
CVPR
2007
IEEE
14 years 11 months ago
Discovery of Collocation Patterns: from Visual Words to Visual Phrases
A visual word lexicon can be constructed by clustering primitive visual features, and a visual object can be described by a set of visual words. Such a "bag-of-words" re...
Junsong Yuan, Ying Wu, Ming Yang
KDD
2009
ACM
190views Data Mining» more  KDD 2009»
14 years 9 months ago
Named entity mining from click-through data using weakly supervised latent dirichlet allocation
This paper addresses Named Entity Mining (NEM), in which we mine knowledge about named entities such as movies, games, and books from a huge amount of data. NEM is potentially use...
Gu Xu, Shuang-Hong Yang, Hang Li
ICRA
2006
IEEE
110views Robotics» more  ICRA 2006»
14 years 3 months ago
Integration of Visual and Inertial Information for Egomotion: a Stochastic Approach
— We present a probabilistic framework for visual correspondence, inertial measurements and Egomotion. First, we describe a simple method based on Gabor filters to produce corre...
Justin Domke, Yiannis Aloimonos
DAGM
2004
Springer
14 years 2 months ago
Building a Motion Resolution Pyramid by Combining Velocity Distributions
Abstract. Velocity distributions are an enhanced representation of image velocity implying more velocity information than velocity vectors. Velocity distributions allow the represe...
Julian Eggert, Volker Willert, Edgar Körner