In four large user studies, human motion capture beat all five gesture-generation systems on realism and alignment, and nearly all systems scored at chance on semantic and dyadic appropriateness.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The GENEA Challenge 2026: A Large-Scale Disentangled Evaluation of Speech-Driven Gesture Generation on the Seamless Interaction Dataset
In four large user studies, human motion capture beat all five gesture-generation systems on realism and alignment, and nearly all systems scored at chance on semantic and dyadic appropriateness.