2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06) (2006)
New York, NY
June 17, 2006 to June 22, 2006
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CVPR.2006.132
Sy Bor Wang , MIT
Ariadna Quattoni , MIT
Louis-Philippe Morency , MIT
David Demirdjian , MIT
Trevor Darrell , 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 structures have proven to be advantageous for recognition tasks. Most existing approaches to gesture recognition with hidden states 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 the 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 states nor addressed the problem of predicting the label of an entire sequence. In this paper, we derive a discriminative sequence model with a hidden state structure, and demonstrate its utility both in a detection and in a multi-way classification formulation. We evaluate our method on the task of recognizing human arm and head gestures, and compare the performance of our method to both generative hidden state and discriminative fully-observable models.
S. B. Wang, L. Morency, A. Quattoni, T. Darrell and D. Demirdjian, "Hidden Conditional Random Fields for Gesture Recognition," 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)(CVPR), New York, NY, 2006, pp. 1521-1527.