Picture for Xavier Alameda-Pineda

Xavier Alameda-Pineda

UGA

MEGA: Masked Generative Autoencoder for Human Mesh Recovery

May 29, 2024
Viaarxiv icon

Socially Pertinent Robots in Gerontological Healthcare

Add code
Apr 11, 2024
Figure 1 for Socially Pertinent Robots in Gerontological Healthcare
Figure 2 for Socially Pertinent Robots in Gerontological Healthcare
Figure 3 for Socially Pertinent Robots in Gerontological Healthcare
Figure 4 for Socially Pertinent Robots in Gerontological Healthcare
Viaarxiv icon

VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space

Add code
Dec 13, 2023
Figure 1 for VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space
Figure 2 for VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space
Figure 3 for VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space
Figure 4 for VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space
Viaarxiv icon

Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation

Add code
Dec 07, 2023
Figure 1 for Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation
Figure 2 for Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation
Figure 3 for Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation
Figure 4 for Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation
Viaarxiv icon

On the Effectiveness of LayerNorm Tuning for Continual Learning in Vision Transformers

Add code
Aug 18, 2023
Figure 1 for On the Effectiveness of LayerNorm Tuning for Continual Learning in Vision Transformers
Figure 2 for On the Effectiveness of LayerNorm Tuning for Continual Learning in Vision Transformers
Figure 3 for On the Effectiveness of LayerNorm Tuning for Continual Learning in Vision Transformers
Figure 4 for On the Effectiveness of LayerNorm Tuning for Continual Learning in Vision Transformers
Viaarxiv icon

A Comprehensive Multi-scale Approach for Speech and Dynamics Synchrony in Talking Head Generation

Add code
Jul 04, 2023
Figure 1 for A Comprehensive Multi-scale Approach for Speech and Dynamics Synchrony in Talking Head Generation
Figure 2 for A Comprehensive Multi-scale Approach for Speech and Dynamics Synchrony in Talking Head Generation
Figure 3 for A Comprehensive Multi-scale Approach for Speech and Dynamics Synchrony in Talking Head Generation
Figure 4 for A Comprehensive Multi-scale Approach for Speech and Dynamics Synchrony in Talking Head Generation
Viaarxiv icon

Semi-supervised learning made simple with self-supervised clustering

Add code
Jun 13, 2023
Figure 1 for Semi-supervised learning made simple with self-supervised clustering
Figure 2 for Semi-supervised learning made simple with self-supervised clustering
Figure 3 for Semi-supervised learning made simple with self-supervised clustering
Figure 4 for Semi-supervised learning made simple with self-supervised clustering
Viaarxiv icon

Unsupervised speech enhancement with deep dynamical generative speech and noise models

Jun 13, 2023
Figure 1 for Unsupervised speech enhancement with deep dynamical generative speech and noise models
Figure 2 for Unsupervised speech enhancement with deep dynamical generative speech and noise models
Viaarxiv icon

Motion-DVAE: Unsupervised learning for fast human motion denoising

Add code
Jun 09, 2023
Figure 1 for Motion-DVAE: Unsupervised learning for fast human motion denoising
Figure 2 for Motion-DVAE: Unsupervised learning for fast human motion denoising
Figure 3 for Motion-DVAE: Unsupervised learning for fast human motion denoising
Figure 4 for Motion-DVAE: Unsupervised learning for fast human motion denoising
Viaarxiv icon

A Multimodal Dynamical Variational Autoencoder for Audiovisual Speech Representation Learning

Add code
May 05, 2023
Viaarxiv icon