Remember and transfer what you have learned - recognizing composite activities based on activity spotting

Activity recognition approaches have shown to enable good performance for a wide variety of applications. Most approaches rely on machine learning techniques requiring significant amounts of training data for each application. Consequently they have to be retrained for each new application limiting...

Full description

Saved in:
Bibliographic Details
Main Authors: Blanke, U, Schiele, B
Format: Conference Proceeding
Language:English
Subjects:
Data models
Hidden Markov models
Joints
Knowledge transfer
Mirrors
Training
Training data
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Activity recognition approaches have shown to enable good performance for a wide variety of applications. Most approaches rely on machine learning techniques requiring significant amounts of training data for each application. Consequently they have to be retrained for each new application limiting the real-world applicability of today's activity recognition methods. This paper explores the possibility to transfer learned knowledge from one application to others thereby significantly reducing the required training data for new applications. To achieve this transferability the paper proposes a new layered activity recognition approach that lends itself to transfer knowledge across applications. Besides allowing to transfer knowledge across applications this layered approach also shows improved recognition performance both of composite activities as well as of activity events.
ISSN:1550-4816
2376-8541
DOI:10.1109/ISWC.2010.5665869