Picture for Yasser Abdelaziz Dahou Djilali

Yasser Abdelaziz Dahou Djilali

ViSpeR: Multilingual Audio-Visual Speech Recognition

Add code
May 27, 2024
Viaarxiv icon

Do Vision and Language Encoders Represent the World Similarly?

Add code
Jan 10, 2024
Viaarxiv icon

Learning Saliency From Fixations

Add code
Nov 23, 2023
Figure 1 for Learning Saliency From Fixations
Figure 2 for Learning Saliency From Fixations
Figure 3 for Learning Saliency From Fixations
Figure 4 for Learning Saliency From Fixations
Viaarxiv icon

Do VSR Models Generalize Beyond LRS3?

Add code
Nov 23, 2023
Figure 1 for Do VSR Models Generalize Beyond LRS3?
Figure 2 for Do VSR Models Generalize Beyond LRS3?
Figure 3 for Do VSR Models Generalize Beyond LRS3?
Figure 4 for Do VSR Models Generalize Beyond LRS3?
Viaarxiv icon

Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping

Add code
Aug 11, 2023
Figure 1 for Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping
Figure 2 for Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping
Figure 3 for Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping
Figure 4 for Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping
Viaarxiv icon

One-Step Distributional Reinforcement Learning

Add code
Apr 27, 2023
Figure 1 for One-Step Distributional Reinforcement Learning
Figure 2 for One-Step Distributional Reinforcement Learning
Figure 3 for One-Step Distributional Reinforcement Learning
Figure 4 for One-Step Distributional Reinforcement Learning
Viaarxiv icon