Transformer generative model produces emotional body motions from Japanese motion-capture data, achieving 22.8% machine and 24.9% human recognition accuracy, with demonstrated utility for augmenting recognition models, extracting patterns, and synthesizing transitions.
Synthetic data generation by supervised neural gas network for physiological emotion recognition data,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Generative Learning as a Tool to Improve Perception of Emotional Body Motion Expressions
Transformer generative model produces emotional body motions from Japanese motion-capture data, achieving 22.8% machine and 24.9% human recognition accuracy, with demonstrated utility for augmenting recognition models, extracting patterns, and synthesizing transitions.