Sciweavers

821 search results - page 37 / 165
» Labeling images with a computer game
Sort
View
CVPR
2011
IEEE
13 years 3 months ago
FlowBoost - Appearance Learning from Sparsely Annotated Video
We propose a new learning method which exploits temporal consistency to successfully learn a complex appearance model from a sparsely labeled training video. Our approach consists...
Karim Ali, Francois Fleuret, David Hasler
ICCV
1995
IEEE
13 years 11 months ago
Segmented Shape Descriptions from 3-View Stereo
Abstract: We address the recovery of segmented, 3-0 descriptions of an object from intensity images. We use three views of an objectfrom slightly different viewpointsas our input. ...
Parag Havaldar, Gérard G. Medioni
ECCV
2004
Springer
14 years 1 months ago
Multi-label Image Segmentation for Medical Applications Based on Graph-Theoretic Electrical Potentials
Abstract. A novel method is proposed for performing multi-label, semi-automated image segmentation. Given a small number of pixels with user-defined labels, one can analytically (...
Leo Grady, Gareth Funka-Lea
ACCV
2007
Springer
14 years 1 days ago
Unsupervised Identification of Multiple Objects of Interest from Multiple Images: dISCOVER
Given a collection of images of offices, what would we say we see in the images? The objects of interest are likely to be monitors, keyboards, phones, etc. Such identification of t...
Devi Parikh, Tsuhan Chen
ICPR
2004
IEEE
14 years 9 months ago
Incorporating Prior Knowledge into SVM for Image Retrieval
SVM based image retrieval suffers from the scarcity of labelled samples. In this paper, this problem is solved by incorporating prior knowledge into SVM. Firstly, some prior knowl...
Lei Wang, Ping Xue, Kap Luk Chan