Name
Abstract | ||
|---|---|---|
In the last decade, training recurrent neural networks (RNN) using techniques from the area of reservoir computing (RC) became more attractive for learning sequential data due to the ease of network train- ing. Although successfully applied in the language and speech domains, only little is known about using RC techniques for dynamic gesture recog- nition. We therefore conducted experiments on command gestures using Echo State Networks (ESN) to investigate both the eect of dierent ges- ture sequence representations and dierent parameter congurations. For recognition we employed the ensemble technique, i.e. using ESN as weak classiers. Our results show that using ESN is a promising approach for dynamic gesture recognition and we give indications for future experi- ments. |
Year | Venue | Field |
|---|---|---|
2015 | ESANN | Sequential data,Gesture,Computer science,Recurrent neural network,Gesture recognition,Speech recognition,Reservoir computing,Artificial intelligence |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Doreen Jirak | 1 | 29 | 3.59 |
| Pablo V. A. Barros | 2 | 119 | 22.02 |
| Stefan Wermter | 3 | 1100 | 151.62 |