Time Series Classification using the Hidden-Unit Logistic Model
This work addresses time series classification problems in computer vision, offering a novel method that improves performance in tasks such as facial action unit detection, though it appears incremental as it builds on prior models like hidden conditional random fields.
The authors tackled time series classification by introducing the hidden-unit logistic model, which uses binary stochastic hidden units in a chain structure to model temporal dependencies and complex decision boundaries, achieving strong performance across tasks like handwritten character recognition, speech recognition, facial expression, and action recognition, including a state-of-the-art system for facial action unit detection.
We present a new model for time series classification, called the hidden-unit logistic model, that uses binary stochastic hidden units to model latent structure in the data. The hidden units are connected in a chain structure that models temporal dependencies in the data. Compared to the prior models for time series classification such as the hidden conditional random field, our model can model very complex decision boundaries because the number of latent states grows exponentially with the number of hidden units. We demonstrate the strong performance of our model in experiments on a variety of (computer vision) tasks, including handwritten character recognition, speech recognition, facial expression, and action recognition. We also present a state-of-the-art system for facial action unit detection based on the hidden-unit logistic model.