Sciweavers

33 search results - page 1 / 7
» Conditional Feature Sensitivity: A Unifying View on Active R...
Sort
View
ICCV
2003
IEEE
14 years 6 months ago
Conditional Feature Sensitivity: A Unifying View on Active Recognition and Feature Selection
The objective of active recognition is to iteratively collect the next "best" measurements (e.g., camera angles or viewpoints), to maximally reduce ambiguities in recogn...
Xiang Sean Zhou, Dorin Comaniciu, Arun Krishnan
IROS
2007
IEEE
158views Robotics» more  IROS 2007»
13 years 10 months ago
Feature selection in conditional random fields for activity recognition
Abstract— Temporal classification, such as activity recognition, is a key component for creating intelligent robot systems. In the case of robots, classification algorithms mus...
Douglas L. Vail, John D. Lafferty, Manuela M. Velo...
AAAI
2008
13 years 6 months ago
Feature Selection for Activity Recognition in Multi-Robot Domains
In multi-robot settings, activity recognition allows a robot to respond intelligently to the other robots in its environment. Conditional random fields are temporal models that ar...
Douglas L. Vail, Manuela M. Veloso
ICPR
2010
IEEE
13 years 9 months ago
Motif Discovery and Feature Selection for CRF-Based Activity Recognition
Abstract—Due to their ability to model sequential data without making unnecessary independence assumptions, conditional random fields (CRFs) have become an increasingly popular ...
Liyue Zhao, Xi Wang, Gita Sukthankar
BC
2004
133views more  BC 2004»
13 years 4 months ago
Coevolution of active vision and feature selection
We show that complex visual tasks, such as position- and size-invariant shape recognition and navigation in the environment, can be tackled with simple architectures generated by a...
Dario Floreano, Toshifumi Kato, Davide Marocco, Er...