Sciweavers

868 search results - page 148 / 174
» Learning Object Representations Using Sequential Patterns
Sort
View
CVPR
2011
IEEE
13 years 6 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...
MM
2004
ACM
178views Multimedia» more  MM 2004»
14 years 3 months ago
A bootstrapping framework for annotating and retrieving WWW images
Most current image retrieval systems and commercial search engines use mainly text annotations to index and retrieve WWW images. This research explores the use of machine learning...
HuaMin Feng, Rui Shi, Tat-Seng Chua
NIPS
2001
13 years 11 months ago
Global Coordination of Local Linear Models
High dimensional data that lies on or near a low dimensional manifold can be described by a collection of local linear models. Such a description, however, does not provide a glob...
Sam T. Roweis, Lawrence K. Saul, Geoffrey E. Hinto...
ECCV
2008
Springer
14 years 11 months ago
Compressive Sensing for Background Subtraction
Abstract. Compressive sensing (CS) is an emerging field that provides a framework for image recovery using sub-Nyquist sampling rates. The CS theory shows that a signal can be reco...
Volkan Cevher, Aswin C. Sankaranarayanan, Marco F....
IROS
2007
IEEE
146views Robotics» more  IROS 2007»
14 years 4 months ago
Capturing robot workspace structure: representing robot capabilities
— Humans have at some point learned an abstraction of the capabilities of their arms. By just looking at the scene they can decide which places or objects they can easily reach a...
Franziska Zacharias, Christoph Borst, Gerd Hirzing...