Hidden Conditional Randon Fields for Gesture Recognition
Speaker: Sy Bor Wang , Vision Interface Group, CSAIL, MIT
We introduce a discriminative hidden-state approach for the recognition of human gestures. Gesture sequences often have a complex underlying structure, and models that can incorporate hidden structure have proven in the past to be advantageous. Most existing approaches to gesture recognition with hidden state employ a Hidden Markov Model or suitable variant (e.g., a factored or coupled state model) to model gesture streams; a significant limitation of these models is the requirement of conditional independence of observations. In addition, hidden states in a generative model are selected to maximize the likelihood of generating all examples of a given gesture class, which is not necessarily optimal for discriminating the gesture class against other gestures. Previous discriminative approaches to gesture sequence recognition have shown promising results, but have not incorporated hidden state and have not addressed the problem of predicting the label of an entire sequence. In this talk, we will present a discriminative sequence model with hidden state structure, and demonstrate its utility both in a detection and in a multi-way classification formulation. We evaluated our method on the task of recognizing human arm and head gestures, and compared performance of our method to both generative hidden-state and discriminative fully-observable models.