Zero-Shot Motion Pattern Recognition From 4D Point-Clouds

Salami, Dariush and Sigg, Stephan

Presentation

Abstract

We address a timely and relevant problem in signal processing: The recognition of patterns from spatial data in motion through a zero-shot learning scenario. We introduce a neural network architecture based on Siamese networks to recognize unseen classes of motion patterns. The approach uses a graph-based technique to achieve permutation invariance and also encodes moving point clouds into a representation space in a computationally efficient way. We evaluated the model on an open dataset with twenty-one gestures. The model outperformes state-of-the-art architectures with a considerable margin in four different settings in terms of accuracy while reducing the computational complexity up to 60 times.

Bibtex

@inproceedings{salami2021zeroshot,
  title = {Zero-Shot Motion Pattern Recognition From 4D Point-Clouds},
  author = {Salami, Dariush and Sigg, Stephan},
  booktitle = {2021 IEEE 31th International Workshop on Machine Learning for Signal Processing (MLSP)},
  pages = {},
  year = {2021},
  organization = {IEEE},
  link = {},
  video = {https://www.youtube.com/embed/VEJtSnP9530},
  doi = {}
}