A Variational Time Series Feature Extractor for Action Prediction
This is an incremental improvement for action recognition in robotics or motion analysis, but lacks testing for prediction as intended.
The authors tackled action recognition by proposing a Variational Time Series Feature Extractor (VTSFE) that improves upon VAE-DMP with better noise inference and a tighter variational bound, achieving better performance for feature extraction on a dataset of 7 tasks with 10 demonstrations each.
We propose a Variational Time Series Feature Extractor (VTSFE), inspired by the VAE-DMP model of Chen et al., to be used for action recognition and prediction. Our method is based on variational autoencoders. It improves VAE-DMP in that it has a better noise inference model, a simpler transition model constraining the acceleration in the trajectories of the latent space, and a tighter lower bound for the variational inference. We apply the method for classification and prediction of whole-body movements on a dataset with 7 tasks and 10 demonstrations per task, recorded with a wearable motion capture suit. The comparison with VAE and VAE-DMP suggests the better performance of our method for feature extraction. An open-source software implementation of each method with TensorFlow is also provided. In addition, a more detailed version of this work can be found in the indicated code repository. Although it was meant to, the VTSFE hasn't been tested for action prediction, due to a lack of time in the context of Maxime Chaveroche's Master thesis at INRIA.