GestureMap: Supporting Visual Analytics and Quantitative Analysis of Motion Elicitation Data by Learning 2D Embeddings

TL;DR

GestureMap is a visual analytics tool that uses 2D embeddings of 3D gesture data to facilitate exploration, analysis, and comparison of gesture elicitation datasets, integrating computational methods for quantitative insights.

Contribution

The paper introduces GestureMap, a novel interactive visualization tool that embeds gesture data into 2D space and combines computational techniques for analysis, enabling new ways to explore and compare gesture elicitation data.

Findings

Facilitates exploration of large gesture datasets

Helps researchers understand gesture space visually

Enables comparison of gesture elicitation across studies

Abstract

This paper presents GestureMap, a visual analytics tool for gesture elicitation which directly visualises the space of gestures. Concretely, a Variational Autoencoder embeds gestures recorded as 3D skeletons on an interactive 2D map. GestureMap further integrates three computational capabilities to connect exploration to quantitative measures: Leveraging DTW Barycenter Averaging (DBA), we compute average gestures to 1) represent gesture groups at a glance; 2) compute a new consensus measure (variance around average gesture); and 3) cluster gestures with k-means. We evaluate GestureMap and its concepts with eight experts and an in-depth analysis of published data. Our findings show how GestureMap facilitates exploring large datasets and helps researchers to gain a visual understanding of elicited gesture spaces. It further opens new directions, such as comparing elicitations across studies. We discuss implications for elicitation studies and research, and opportunities to extend our approach to additional tasks in gesture elicitation.