Book ChapterDOI
Using Natural Language and Video Data to Query and Learn American Football Plays
Mihai Lazarescu,Svetha Venkatesh,Geoff West +2 more
- pp 63-72
Reads0
Chats0
TLDR
A decision tree based incremental learning algorithm which combines context knowledge, attribute selection and the ageing of knowledge to keep the model representation of the plays consistent with the information extracted from the American Football video tapes is described.Abstract:
In this paper we describe methods currently under investigation for learning, recognising and representing American Football plays. This is a complex spatio-temporal pattern recognition problem which we propose to solve by integrating image understanding and natural language understanding. Specifically, this paper describes the model representation used at different levels of abstraction incorporating several types of knowledge: expert knowledge, domain knowledge and spatio-temporal knowledge. We also describe a decision tree based incremental learning algorithm which combines context knowledge, attribute selection and the ageing of knowledge to keep the model representation of the plays consistent with the information extracted from the American Football video tapes.read more
Citations
More filters
Proceedings ArticleDOI
On the automatic indexing of cricket using camera motion parameters
TL;DR: An application of camera motion estimation to index cricket games using an incremental learning algorithm that has the advantages that it is fast and avoids complex image segmentation.
Book ChapterDOI
Classifying and Learning Cricket Shots Using Camera Motion
TL;DR: By using the camera motion parameters, a complex and diflficult process of low level image segmenting of either the batsman or the cricket ball from video images is avoided and the method does not require high resolution images.
Book
Advanced Topics in Artificial Intelligence
TL;DR: This paper presents an algorithm for inducing simple, accurate decision lists from model trees and shows that this method produces comparably accurate and smaller rule sets than the commercial state-of-the-art rule learning system Cubist.
References
More filters
Towards a General Theory of Action and Time.
TL;DR: A formalism for reasoning about actions that is based on a temporal logic allows a much wider range of actions to be described than with previous approaches such as the situation calculus and a framework for planning in a dynamic world with external events and multiple agents is suggested.
Journal ArticleDOI
Towards a general theory of action and time
TL;DR: In this article, a formalism for reasoning about actions is proposed that is based on a temporal logic, which allows a much wider range of actions to be described than with previous approaches such as the situation calculus.
Proceedings Article
On the simultaneous interpretation of real world image sequences and their natural language description: the system soccer
TL;DR: In this paper, the authors present Soccer, a system that generates a description of the game which it is watching and which the listener cannot see, based on a conception that short sections of soccer games have been chosen as the domain of discourse.
Journal Article
Incremental learning of concept descriptions: A method and experimental results
Natural Language Access to Visual Data: Dealing with Space and Movement
Gerd Herzog,Thomas Rist +1 more
TL;DR: This paper reports on practical experience gained in the project Vitra (VIsual TRAnslator), and designs an interface between image understanding and natural language systems, which are combined with a concrete vision system.