Sciweavers

1227 search results - page 163 / 246
» Learning Rates for Q-Learning
Sort
View
ACCV
2009
Springer
14 years 5 months ago
Human Action Recognition Using HDP by Integrating Motion and Location Information
The method based on local features has an advantage that the important local motion feature is represented as bag-of-features, but lacks the location information. Additionally, in ...
Yasuo Ariki, Takuya Tonaru, Tetsuya Takiguchi
ICPR
2008
IEEE
14 years 5 months ago
Text detection from scene images using sparse representation
A sparse representation based method is proposed for text detection from scene images. We start with edge information extracted using Canny operator and then group these edge poin...
Wumo Pan, Tien D. Bui, Ching Y. Suen
FOCI
2007
IEEE
14 years 5 months ago
Simulated Annealing with Opposite Neighbors
— This paper presents an improvement to the vanilla version of the simulated annealing algorithm by using opposite neighbors. This new technique, is based on the recently propose...
Mario Ventresca, Hamid R. Tizhoosh
ICMCS
2007
IEEE
194views Multimedia» more  ICMCS 2007»
14 years 5 months ago
Automatically Tuning Background Subtraction Parameters using Particle Swarm Optimization
A common trait of background subtraction algorithms is that they have learning rates, thresholds, and initial values that are hand-tuned for a scenario in order to produce the des...
Brandyn White, Mubarak Shah
ICMCS
2007
IEEE
158views Multimedia» more  ICMCS 2007»
14 years 5 months ago
Automatic Multi-Modal Meeting Camera Selection for Video-Conferences and Meeting Browsers
In a video-conference the participants usually see the video of the speaker. However if somebody reacts (e. g. nodding) the system should switch to his video. Current systems do n...
Marc Al-Hames, Benedikt Hörnler, Ronald M&uum...