Hierarchical Self-Organizing Maps System for Action Classification
(2017) ICAART 2017-International Conference on Agents and Artificial Intelligence p.583-590- Abstract
- We present a novel action recognition system that is able to learn how to recognize and classify actions. Our system employs a three-layered hierarchy of Self-Organizing Maps together with a supervised neural network for labelling the actions. We have evaluated our system in an experiments consisting of ten different actions from a publicly available data set. The results are encouraging with 83% correctly classified actions based on the actor’s spatial trajectory.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/98c8370a-8170-4acb-918e-37cb31933e8b
- author
- Gharaee, Zahra LU ; Gärdenfors, Peter LU and Johnsson, Magnus LU
- organization
- publishing date
- 2017
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Proceedings of the 9th International Conference on Agents and Artificial Intelligence (ICAART 2017)
- pages
- 8 pages
- publisher
- SciTePress
- conference name
- ICAART 2017-International Conference on Agents and Artificial Intelligence
- conference location
- Porto, Portugal
- conference dates
- 2017-02-24 - 2017-02-26
- external identifiers
-
- wos:000413244200062
- scopus:85049658703
- ISBN
- 978-989-758-220-2
- DOI
- 10.5220/0006199305830590
- project
- Ikaros: An infrastructure for system level modelling of the brain
- Thinking in Time: Cognition, Communication and Learning
- language
- English
- LU publication?
- yes
- id
- 98c8370a-8170-4acb-918e-37cb31933e8b
- date added to LUP
- 2016-12-04 17:31:13
- date last changed
- 2022-03-02 03:09:23
@inproceedings{98c8370a-8170-4acb-918e-37cb31933e8b, abstract = {{We present a novel action recognition system that is able to learn how to recognize and classify actions. Our system employs a three-layered hierarchy of Self-Organizing Maps together with a supervised neural network for labelling the actions. We have evaluated our system in an experiments consisting of ten different actions from a publicly available data set. The results are encouraging with 83% correctly classified actions based on the actor’s spatial trajectory.}}, author = {{Gharaee, Zahra and Gärdenfors, Peter and Johnsson, Magnus}}, booktitle = {{Proceedings of the 9th International Conference on Agents and Artificial Intelligence (ICAART 2017)}}, isbn = {{978-989-758-220-2}}, language = {{eng}}, pages = {{583--590}}, publisher = {{SciTePress}}, title = {{Hierarchical Self-Organizing Maps System for Action Classification}}, url = {{http://dx.doi.org/10.5220/0006199305830590}}, doi = {{10.5220/0006199305830590}}, year = {{2017}}, }