Nonlinear Methods for Analyzing Pose in Behavioral Research
This work addresses the problem of analyzing complex human movement data for behavioral researchers, offering a versatile tool that is incremental in combining existing methods into a unified pipeline.
The paper tackles the challenge of extracting meaningful patterns from high-dimensional, noisy pose data in behavioral research by presenting a general-purpose analysis pipeline that combines preprocessing, dimensionality reduction, and recurrence-based time series analysis, demonstrating its flexibility through three case studies across diverse contexts.
Advances in markerless pose estimation have made it possible to capture detailed human movement in naturalistic settings using standard video, enabling new forms of behavioral analysis at scale. However, the high dimensionality, noise, and temporal complexity of pose data raise significant challenges for extracting meaningful patterns of coordination and behavioral change. This paper presents a general-purpose analysis pipeline for human pose data, designed to support both linear and nonlinear characterizations of movement across diverse experimental contexts. The pipeline combines principled preprocessing, dimensionality reduction, and recurrence-based time series analysis to quantify the temporal structure of movement dynamics. To illustrate the pipeline's flexibility, we present three case studies spanning facial and full-body movement, 2D and 3D data, and individual versus multi-agent behavior. Together, these examples demonstrate how the same analytic workflow can be adapted to extract theoretically meaningful insights from complex pose time series.