Name
Abstract | ||
|---|---|---|
•A neural network platform for human action recognition by observation of kinematics is introduced.•The system is made of two layer SOMs and a costume made supervised neural network.•Input is preprocessed by coordinate transformation, rescaling, attention and dynamic extraction.•Ordered vector representation applied between first and second SOM for time in-variance.•Empirical experiments are implemented for evaluation and validation of recognition task. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1016/j.asoc.2017.06.007 | Applied Soft Computing |
Keywords | Field | DocType |
Self-Organizing Maps,Conceptual spaces,Neural networks,Action recognition,Hierarchical models,Attention,Dynamics | Categorization,3d camera,Computer science,Action recognition,Exploit,Self-organizing map,Preprocessor,Artificial intelligence,Hierarchy,Artificial neural network,Machine learning | Journal |
Volume | ISSN | Citations |
59 | 1568-4946 | 2 |
PageRank | References | Authors |
0.39 | 15 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zahra Gharaee | 1 | 4 | 2.80 |
| Peter Gärdenfors | 2 | 1699 | 183.78 |
| Magnus Johnsson | 3 | 99 | 13.51 |