Flexible Dictionaries for Action Classification
Abstract
We present a simple approach to action classification which constructs a vector quantization of primitive motions from time series data corresponding to relative limb position estimates. The temporal scale, mean, and shape of primitive motion trajectories are independently modeled, thus creating a exible dictionary of action primitives. We then explore two inference techniques that leverage our action dictionary representation, and evaluate their performance on both motion capture and video benchmark data. Our results indicate that even simplistic algorithms can outperform significantly more sophisticated ones in existing benchmark datasets.
Origin : Files produced by the author(s)
Loading...