Sciweavers

1601 search results - page 84 / 321
» Learning Gaussian processes from multiple tasks
Sort
View
150
Voted
ICCV
2007
IEEE
16 years 5 months ago
The Joint Manifold Model for Semi-supervised Multi-valued Regression
Many computer vision tasks may be expressed as the problem of learning a mapping between image space and a parameter space. For example, in human body pose estimation, recent rese...
Ramanan Navaratnam, Andrew W. Fitzgibbon, Roberto ...
114
Voted
MODELLIERUNG
2004
15 years 4 months ago
Modeling Socio-Technical Processes in e-Commerce Scenarios
: We consider socio-technical processes, i.e. processes where machines as well as humans participate. Typical examples occur in sales processes in e-commerce. Three modeling tasks ...
Michael M. Richter, Armin Stahl
122
Voted
ACL
2010
15 years 1 months ago
Inducing Domain-Specific Semantic Class Taggers from (Almost) Nothing
This research explores the idea of inducing domain-specific semantic class taggers using only a domain-specific text collection and seed words. The learning process begins by indu...
Ruihong Huang, Ellen Riloff
ICPR
2004
IEEE
16 years 4 months ago
Visual Learning and Recognition of a Probabilistic Spatio-Temporal Model of Cyclic Human Locomotion
We present a novel representation of cyclic human locomotion based on a set of spatio-temporal curves of tracked points on the surface of a person. We start by extracting a set of...
Miha Peternel, Ales Leonardis
ICPR
2004
IEEE
16 years 4 months ago
Using Multiple Graphics Cards as a General Purpose Parallel Computer : Applications to Computer Vision
Pattern recognition and computer vision tasks are computationally intensive, repetitive, and often exceed the capabilities of the CPU, leaving little time for higher level tasks. ...
James Fung, Steve Mann