Sciweavers

780 search results - page 16 / 156
» Learning Mid-Level Features For Recognition
Sort
View
CVPR
2011
IEEE
13 years 3 months ago
On Deep Generative Models with Applications to Recognition
The most popular way to use probabilistic models in vision is first to extract some descriptors of small image patches or object parts using well-engineered features, and then to...
Marc', Aurelio Ranzato, Joshua Susskind, Volodymyr...
CVPR
2010
IEEE
14 years 4 months ago
Exploring Features in a Bayesian Framework for Material Recognition
We are interested in identifying the material category, e.g. glass, metal, fabric, plastic or wood, from a single image of a surface. Unlike other visual recognition tasks in comp...
Ce Liu, Lavanya Sharan, Edward Adelson, Ruth Rosen...
CVPR
2005
IEEE
14 years 9 months ago
Object Recognition with Features Inspired by Visual Cortex
We introduce a novel set of features for robust object recognition. Each element of this set is a complex feature obtained by combining position- and scale-tolerant edgedetectors ...
Thomas Serre, Lior Wolf, Tomaso Poggio
CVPR
2009
IEEE
1096views Computer Vision» more  CVPR 2009»
15 years 2 months ago
How far can you get with a modern face recognition test set using only simple features?
In recent years, large databases of natural images have become increasingly popular in the evaluation of face and object recognition algorithms. However, Pinto et al. previously ...
Nicolas Pinto, James J. DiCarlo, David D. Cox
IROS
2007
IEEE
179views Robotics» more  IROS 2007»
14 years 1 months ago
Incremental learning for place recognition in dynamic environments
Abstract— Vision-based place recognition is a desirable feature for an autonomous mobile system. In order to work in realistic scenarios, visual recognition algorithms should be ...
Jie Luo, Andrzej Pronobis, Barbara Caputo, Patric ...