Sciweavers

208 search results - page 20 / 42
» A general boosting-based framework for active object recogni...
Sort
View
IBPRIA
2003
Springer
14 years 25 days ago
Multiple Segmentation of Moving Objects by Quasi-simultaneous Parametric Motion Estimation
Abstract. This paper presents a new framework for the motion segmentation and estimation task on sequences of two grey images without a priori information of the number of moving r...
Raúl Montoliu, Filiberto Pla
CVPR
2005
IEEE
14 years 9 months ago
MosaicShape: Stochastic Region Grouping with Shape Prior
A method that combines shape-based object recognition and image segmentation is proposed for shape retrieval from images. Given a shape prior represented in a multiscale curvature...
Jingbin Wang, Erdan Gu, Margrit Betke
CVPR
2009
IEEE
15 years 2 months ago
What's It Going to Cost You?: Predicting Effort vs. Informativeness for Multi-Label Image Annotations
Active learning strategies can be useful when manual labeling effort is scarce, as they select the most informative examples to be annotated first. However, for visual category ...
Sudheendra Vijayanarasimhan (University of Texas a...
CVPR
2005
IEEE
14 years 9 months ago
Bayesian Object Detection in Dynamic Scenes
Detecting moving objects using stationary cameras is an important precursor to many activity recognition, object recognition and tracking algorithms. In this paper, three innovati...
Yaser Sheikh, Mubarak Shah
ECCV
2008
Springer
14 years 9 months ago
Implementing Decision Trees and Forests on a GPU
We describe a method for implementing the evaluation and training of decision trees and forests entirely on a GPU, and show how this method can be used in the context of object rec...
Toby Sharp