Fixed-Reference Pose Residuals for Measuring Cross-Dataset Cue Transfer in Human-Robot Interaction Anticipation

Name: Fixed-Reference Pose Residuals for Measuring Cross-Dataset Cue Transfer in Human-Robot Interaction Anticipation
Uploaded: 2026-10-11T19:12:59.484090+00:00
Duration: 313 s
Description: The Fixed-Reference Pose Residuals (FRPR) model creates an exact split between geometry and pose predictions to measure how cues transfer between different datasets. By training a geometry predictor and adding a pose correction, researchers found that while some cues transfer well, others, like pitch, require re-establishing their value for each new platform.

The Fixed-Reference Pose Residuals (FRPR) model creates an exact split between geometry and pose predictions to measure how cues transfer between different datasets. By training a geometry predictor and adding a pose correction, researchers found that while some cues transfer well, others, like pitch, require re-establishing their value for each new platform.

Open the full episode