A Shared Parameter Model for Gesture and Sub-gesture Analysis

Gesture sequences typically have a common set of distinct internal sub-structures which can be shared across the gestures. In this paper, we propose a method using a generative model to learn these common actions which we refer to as sub-gestures, and in-turn perform recognition. Our proposed model learns sub-gestures by sharing parameters between gesture models. We evaluated our method on the Palm Graffiti digits-gesture dataset and showed that the model with shared parameters outperformed the same model without the shared parameters. Also, we labeled different observation sequences thereby intuitively showing how sub-gestures are related to complete gestures.