activity
20132022
most citedTraining Strategies for Improved Lip-reading

59 citations · 246 across the 25 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2021

Defensive Tensorization

Adrian Bulat, Jean Kossaifi, Sourav Bhattacharya +5

We propose defensive tensorization, an adversarial defence technique that leverages a latent high-order factorization of the network. The layers of a network are first expressed as…

cs.LG20211 cited

LiRA: Learning Visual Speech Representations from Audio through Self-supervision

Pingchuan Ma, Rodrigo Mira, Stavros Petridis +2

The large amount of audiovisual content being shared online today has drawn substantial attention to the prospect of audiovisual self-supervised learning. Recent works have focused…

cs.LG2021

DINO: A Conditional Energy-Based GAN for Domain Translation

Konstantinos Vougioukas, Stavros Petridis, Maja Pantic

Domain translation is the process of transforming data from one domain to another while preserving the common semantics. Some of the most popular domain translation systems are bas…

cs.LG20211 cited

Cauchy-Schwarz Regularized Autoencoder

Linh Tran, Maja Pantic, Marc Peter Deisenroth

Recent work in unsupervised learning has focused on efficient inference and learning in latent variables models. Training these models by maximizing the evidence (marginal likeliho…

cs.LG20207 cited

Multilinear Latent Conditioning for Generating Unseen Attribute Combinations

Markos Georgopoulos, Grigorios Chrysos, Maja Pantic +1

Deep generative models rely on their inductive bias to facilitate generalization, especially for problems with high dimensional data, like images. However, empirical studies have s…

cs.LG2019

Speech-driven facial animation using polynomial fusion of features

Triantafyllos Kefalas, Konstantinos Vougioukas, Yannis Panagakis +3

Speech-driven facial animation involves using a speech signal to generate realistic videos of talking faces. Recent deep learning approaches to facial synthesis rely on extracting…