Picture for Enrique Sanchez

Enrique Sanchez

MeMSVD: Long-Range Temporal Structure Capturing Using Incremental SVD

Jun 11, 2024
Viaarxiv icon

Multiscale Vision Transformers meet Bipartite Matching for efficient single-stage Action Localization

Add code
Dec 29, 2023
Viaarxiv icon

Variational prompt tuning improves generalization of vision-language models

Oct 05, 2022
Figure 1 for Variational prompt tuning improves generalization of vision-language models
Figure 2 for Variational prompt tuning improves generalization of vision-language models
Figure 3 for Variational prompt tuning improves generalization of vision-language models
Figure 4 for Variational prompt tuning improves generalization of vision-language models
Viaarxiv icon

REST: REtrieve & Self-Train for generative action recognition

Sep 29, 2022
Figure 1 for REST: REtrieve & Self-Train for generative action recognition
Figure 2 for REST: REtrieve & Self-Train for generative action recognition
Figure 3 for REST: REtrieve & Self-Train for generative action recognition
Figure 4 for REST: REtrieve & Self-Train for generative action recognition
Viaarxiv icon

From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery

Add code
May 31, 2022
Figure 1 for From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery
Figure 2 for From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery
Figure 3 for From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery
Figure 4 for From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery
Viaarxiv icon

Subpixel Heatmap Regression for Facial Landmark Localization

Nov 03, 2021
Figure 1 for Subpixel Heatmap Regression for Facial Landmark Localization
Figure 2 for Subpixel Heatmap Regression for Facial Landmark Localization
Figure 3 for Subpixel Heatmap Regression for Facial Landmark Localization
Figure 4 for Subpixel Heatmap Regression for Facial Landmark Localization
Viaarxiv icon

Pre-training strategies and datasets for facial representation learning

Mar 30, 2021
Figure 1 for Pre-training strategies and datasets for facial representation learning
Figure 2 for Pre-training strategies and datasets for facial representation learning
Figure 3 for Pre-training strategies and datasets for facial representation learning
Figure 4 for Pre-training strategies and datasets for facial representation learning
Viaarxiv icon

Affective Processes: stochastic modelling of temporal context for emotion and facial expression recognition

Add code
Mar 24, 2021
Figure 1 for Affective Processes: stochastic modelling of temporal context for emotion and facial expression recognition
Figure 2 for Affective Processes: stochastic modelling of temporal context for emotion and facial expression recognition
Figure 3 for Affective Processes: stochastic modelling of temporal context for emotion and facial expression recognition
Figure 4 for Affective Processes: stochastic modelling of temporal context for emotion and facial expression recognition
Viaarxiv icon

Semi-supervised Facial Action Unit Intensity Estimation with Contrastive Learning

Nov 04, 2020
Figure 1 for Semi-supervised Facial Action Unit Intensity Estimation with Contrastive Learning
Figure 2 for Semi-supervised Facial Action Unit Intensity Estimation with Contrastive Learning
Figure 3 for Semi-supervised Facial Action Unit Intensity Estimation with Contrastive Learning
Figure 4 for Semi-supervised Facial Action Unit Intensity Estimation with Contrastive Learning
Viaarxiv icon

A recurrent cycle consistency loss for progressive face-to-face synthesis

Add code
Apr 14, 2020
Figure 1 for A recurrent cycle consistency loss for progressive face-to-face synthesis
Figure 2 for A recurrent cycle consistency loss for progressive face-to-face synthesis
Figure 3 for A recurrent cycle consistency loss for progressive face-to-face synthesis
Figure 4 for A recurrent cycle consistency loss for progressive face-to-face synthesis
Viaarxiv icon