Using FORM Data to Predict Phase Labels
lrecFORM2.pdf (122.8Kb)Abstract
In this paper we present an augmentation of the FORM gesture corpus and describe experiments using FORM to predict gesture phase, i.e. preparation, stroke, and retraction. We compare these results to experiments using motion-captured data to predict the same. Interestingly, the FORM data, which is gathered via annotation, does significantly better than the motion-captured data.
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.Collections
Related items
Showing items related by title, author, creator and subject.
-
Dynamic Characteristics of Liquid Motion in Partially Filled tanks of Spinning Spacecraft
(1990);This paper presents a boundary layer model to predict dynamic characteristics of liquid motion in partially filled tanks of a spinning spacecraft. The solution is obtained by solving three boundary value problems: inviscid, ... -
Dynamic Characteristics of Liquid Motion in Partially Filled Tanks of a Spinning Spacecraft
(1993);This paper presents a boundary-layer model to predict dynamic characteristics of liquid motion in partially filled tanks of a spinning spacecraft. The solution is obtained by solving three boundary-value problems: an ... -
Underwater acoustic pulse propagation using the Recursive Ray Acoustics (RRA) Algorithm
(Monterey, California. Naval Postgraduate School, 1995-06);The purpose of this thesis is to demonstrate the ability to predict the pulse shape at the location of a receiver in the ocean for a given transmitted pulse and ocean medium model by using the Recursive Ray Acoustics (RRA) ...
