Abstract | ||
---|---|---|
Our work focuses on metric learning between gesture sample signatures using Siamese Neural Networks (SNN), which aims at modeling semantic relations between classes to extract discriminative features. Our contribution is the notion of polar sine which enables a redefinition of the angular problem. Our final proposal improves inertial gesture classification in two challenging test scenarios, with respective average classification rates of 0.934 +/- 0.011 and 0.776 +/- 0.025. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-44781-0_48 | ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2016, PT II |
Keywords | Field | DocType |
Siamese neural network, Metric learning, Polar sine, Gesture recognition | Inertial frame of reference,Pattern recognition,Computer science,Gesture,Gesture recognition,Speech recognition,Polar sine,Scenario testing,Artificial intelligence,Artificial neural network,Discriminative model,Gesture classification | Conference |
Volume | ISSN | Citations |
9887 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 12 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Samuel Berlemont | 1 | 34 | 3.38 |
Gregoire Lefebvre | 2 | 82 | 12.13 |
Stefan Duffner | 3 | 340 | 43.23 |
Christophe Garcia | 4 | 34 | 6.84 |