2 papers
cs.LG2026
-VAE: Variance Equalization for Posterior Collapse
Girum Demisse
Variational Autoencoders (VAEs) frequently suffer from posterior collapse, a failure mode in which the approximate posterior converges to the prior, rendering the latent code uninf…
cs.CV2019
Localized Trajectories for 2D and 3D Action Recognition
Konstantinos Papadopoulos, Girum Demisse, Enjie Ghorbel +3
The Dense Trajectories concept is one of the most successful approaches in action recognition, suitable for scenarios involving a significant amount of motion. However, due to nois…