Sciweavers

35 search results - page 2 / 7
» A Psychogenetic Algorithm for Behavioral Sequence Learning
Sort
View
ATAL
2005
Springer
13 years 11 months ago
Discovering strategic multi-agent behavior in a robotic soccer domain
2. THE MASM ALGORITHM An input to the MASM algorithm is a time-annotated multi-agent action sequence. The action sequence is then transformed into an action graph. An action graph ...
Andraz Bezek
IIHMSP
2006
IEEE
137views Multimedia» more  IIHMSP 2006»
14 years 11 days ago
Understanding Human Behavior Using a Language Modeling Approach
Visual analysis of human behavior has generated considerable interest in the field of computer vision because of the wide spectrum of potential applications. In this paper, we pre...
Yu-Ming Liang, Sheng-Wen Shih, Arthur Chun-Chieh S...
STAIRS
2008
175views Education» more  STAIRS 2008»
13 years 7 months ago
Learning Process Behavior with EDY: an Experimental Analysis
This paper presents an extensive evaluation, on artificial datasets, of EDY, an unsupervised algorithm for automatically synthesizing a Structured Hidden Markov Model (S-HMM) from ...
Ugo Galassi
ECCV
2006
Springer
14 years 8 months ago
Robust Attentive Behavior Detection by Non-linear Head Pose Embedding and Estimation
We present a new scheme to robustly detect a type of human attentive behavior, which we call frequent change in focus of attention (FCFA), from video sequences. FCFA behavior can b...
Nan Hu, Weimin Huang, Surendra Ranganath
AR
2007
105views more  AR 2007»
13 years 6 months ago
Reinforcement learning of a continuous motor sequence with hidden states
—Reinforcement learning is the scheme for unsupervised learning in which robots are expected to acquire behavior skills through self-explorations based on reward signals. There a...
Hiroaki Arie, Tetsuya Ogata, Jun Tani, Shigeki Sug...