Title :
Action Recognition from Experience
Author :
Tu, Peter ; Sebastian, Thomas ; Gao, Dashan
Abstract :
A reinforcement learning model, which allows for an agent to interact with a simulated 3D learning environment under the initial guidance of an all knowing oracle is proposed. Methods are presented that allow the agent to learn how to perform a set of task oriented actions. It is then hypothesized that the ability to recognize an action may in fact be a byproduct of learning how to perform an action. Evidence supporting this conjecture is presented using both simulated and real world imagery.
Keywords :
image motion analysis; image recognition; interactive systems; learning (artificial intelligence); action recognition; agent interaction; real-world imagery; reinforcement learning model; simulated 3D learning environment; simulated imagery; task-oriented actions; Avatars; Current measurement; Image recognition; Joints; Mathematical model; Springs; Vectors;
Conference_Titel :
Advanced Video and Signal-Based Surveillance (AVSS), 2012 IEEE Ninth International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4673-2499-1
DOI :
10.1109/AVSS.2012.85
