This paper presents two approaches for the representation and recognition of human action in video, aiming for viewpoint invariance. The paper first presents new results using a 2...
We propose a framework that performs action recognition and identity maintenance of multiple targets simultaneously. Instead of first establishing tracks using an appearance mode...
The behavior of an agent is defined through the specification of plans and actions. Agents have a set of plans that are selected to be executed according to their goals (and other...
Viviane Torres da Silva, Ricardo Choren, Carlos Jo...
The Action Semantics for UML provides a standard and platform independent way to describe the behavior of methods and executable actions in object-oriented system design prior to i...
We present tractable, exact algorithms for learning actions' effects and preconditions in partially observable domains. Our algorithms maintain a propositional logical repres...