Sciweavers

1283 search results - page 160 / 257
» Object Initialization in X10
Sort
View
CVPR
2009
IEEE
17 years 4 days 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
2009
IEEE
1390views Computer Vision» more  CVPR 2009»
17 years 4 days ago
Stacks of Convolutional Restricted Boltzmann Machines for Shift-Invariant Feature Learning
In this paper we present a method for learning classspecific features for recognition. Recently a greedy layerwise procedure was proposed to initialize weights of deep belief ne...
Mohammad Norouzi (Simon Fraser University), Mani R...
CVPR
2003
IEEE
16 years 7 months ago
Representation and Detection of Deformable Shapes
We describe some techniques that can be used to represent and detect deformable shapes in images. The main difficulty with deformable template models is the very large or infinite...
Pedro F. Felzenszwalb
CVPR
2004
IEEE
16 years 7 months ago
A Variational Approach to Scene Reconstruction and Image Segmentation from Motion-Blur Cues
In this paper we are interested in the joint reconstruction of geometry and photometry of scenes with multiple moving objects from a collection of motion-blurred images. We make s...
Paolo Favaro, Stefano Soatto
CVPR
2004
IEEE
16 years 7 months ago
Dynamic Geodesic Snakes for Visual Tracking
Visual tracking using active contours is usually accomplished in a static framework. The active contour tracks the object of interest in a given frame of an image sequence, and th...
Marc Niethammer, Allen Tannenbaum