CoDE-VAE computes the shared latent code of multiple data views by Bayesian combination of correlated per-view estimates, improving coherence/quality trade-offs and log-likelihood bounds.
Assuming a categorical prior distribution for p(ξ) with probability mass function η = (1/K,··· , 1/K), where K = 2M− 1, i.e
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Aggregation of Dependent Expert Distributions in Multimodal Variational Autoencoders
CoDE-VAE computes the shared latent code of multiple data views by Bayesian combination of correlated per-view estimates, improving coherence/quality trade-offs and log-likelihood bounds.