Mix-and-Match perturbation randomly replaces a subset of the RNN hidden state with noise, preventing conditional VAEs from ignoring the latent code and yielding more diverse human motion predictions.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Variations in Human Motion via Mix-and-Match Perturbation
Mix-and-Match perturbation randomly replaces a subset of the RNN hidden state with noise, preventing conditional VAEs from ignoring the latent code and yielding more diverse human motion predictions.