Sciweavers

821 search results - page 46 / 165
» Labeling images with a computer game
Sort
View
MM
2005
ACM
243views Multimedia» more  MM 2005»
14 years 1 months ago
Image region entropy: a measure of "visualness" of web images associated with one concept
We propose a new method to measure “visualness” of concepts, that is, what extent concepts have visual characteristics. To know which concept has visually discriminative power...
Keiji Yanai, Kobus Barnard
CVPR
2001
IEEE
14 years 10 months ago
Handling Occlusions in Dense Multi-view Stereo
While stereo matching was originally formulated as the recovery of 3D shape from a pair of images, it is now generally recognized that using more than two images can dramatically ...
Sing Bing Kang, Richard Szeliski, Jinxiang Chai
CVPR
2006
IEEE
14 years 10 months ago
Multi-Target Tracking - Linking Identities using Bayesian Network Inference
Multi-target tracking requires locating the targets and labeling their identities. The latter is a challenge when many targets, with indistinct appearances, frequently occlude one...
Peter Nillius, Josephine Sullivan, Stefan Carlsson
ICPR
2004
IEEE
14 years 9 months ago
Hand Gesture Recognition: Self-Organising Maps as a Graphical User Interface for the Partitioning of Large Training Data Sets
Gesture recognition is a difficult task in computer vision due to the numerous degrees of freedom of a human hand. Fortunately, human gesture covers only a small part of the theor...
Axel Saalbach, Gunther Heidemann, Holger Bekel, In...
COGSCI
2002
99views more  COGSCI 2002»
13 years 8 months ago
Learning words from sights and sounds: a computational model
This paper presents an implemented computational model of word acquisition which learns directly from raw multimodal sensory input. Set in an information theoretic framework, the ...
Deb Roy, Alex Pentland