Search Results for author: Diman Zad Tootaghaj

Found 1 papers, 0 papers with code

High Five: Improving Gesture Recognition by Embracing Uncertainty

no code implementations25 Oct 2017 Diman Zad Tootaghaj, Adrian Sampson, Todd Mytkowicz, Kathryn S. McKinley

We introduce a new statistical quantization approach that mitigates these problems by (1) during training, producing gesture-specific codebooks, HMMs, and error models for gesture sequences; and (2) during classification, exploiting the error model to explore multiple feasible HMM state sequences.

Classification General Classification +4

Cannot find the paper you are looking for? You can Submit a new open access paper.