Picture for Roberto J. López-Sastre

Roberto J. López-Sastre

Live Video Captioning

Add code
Jun 20, 2024
Figure 1 for Live Video Captioning
Figure 2 for Live Video Captioning
Figure 3 for Live Video Captioning
Figure 4 for Live Video Captioning
Viaarxiv icon

Realistic Continual Learning Approach using Pre-trained Models

Add code
Apr 11, 2024
Figure 1 for Realistic Continual Learning Approach using Pre-trained Models
Figure 2 for Realistic Continual Learning Approach using Pre-trained Models
Figure 3 for Realistic Continual Learning Approach using Pre-trained Models
Figure 4 for Realistic Continual Learning Approach using Pre-trained Models
Viaarxiv icon

Visual Semantic Navigation with Real Robots

Add code
Nov 28, 2023
Figure 1 for Visual Semantic Navigation with Real Robots
Figure 2 for Visual Semantic Navigation with Real Robots
Figure 3 for Visual Semantic Navigation with Real Robots
Figure 4 for Visual Semantic Navigation with Real Robots
Viaarxiv icon

Rethinking Online Action Detection in Untrimmed Videos: A Novel Online Evaluation Protocol

Add code
Mar 26, 2020
Figure 1 for Rethinking Online Action Detection in Untrimmed Videos: A Novel Online Evaluation Protocol
Figure 2 for Rethinking Online Action Detection in Untrimmed Videos: A Novel Online Evaluation Protocol
Figure 3 for Rethinking Online Action Detection in Untrimmed Videos: A Novel Online Evaluation Protocol
Figure 4 for Rethinking Online Action Detection in Untrimmed Videos: A Novel Online Evaluation Protocol
Viaarxiv icon

The Instantaneous Accuracy: a Novel Metric for the Problem of Online Human Behaviour Recognition in Untrimmed Videos

Add code
Mar 25, 2020
Figure 1 for The Instantaneous Accuracy: a Novel Metric for the Problem of Online Human Behaviour Recognition in Untrimmed Videos
Figure 2 for The Instantaneous Accuracy: a Novel Metric for the Problem of Online Human Behaviour Recognition in Untrimmed Videos
Figure 3 for The Instantaneous Accuracy: a Novel Metric for the Problem of Online Human Behaviour Recognition in Untrimmed Videos
Viaarxiv icon

Deep Anomaly Detection for Generalized Face Anti-Spoofing

Add code
Apr 17, 2019
Figure 1 for Deep Anomaly Detection for Generalized Face Anti-Spoofing
Figure 2 for Deep Anomaly Detection for Generalized Face Anti-Spoofing
Figure 3 for Deep Anomaly Detection for Generalized Face Anti-Spoofing
Figure 4 for Deep Anomaly Detection for Generalized Face Anti-Spoofing
Viaarxiv icon

Generalized Presentation Attack Detection: a face anti-spoofing evaluation proposal

Add code
Apr 12, 2019
Figure 1 for Generalized Presentation Attack Detection: a face anti-spoofing evaluation proposal
Figure 2 for Generalized Presentation Attack Detection: a face anti-spoofing evaluation proposal
Figure 3 for Generalized Presentation Attack Detection: a face anti-spoofing evaluation proposal
Figure 4 for Generalized Presentation Attack Detection: a face anti-spoofing evaluation proposal
Viaarxiv icon

Embarrassingly Simple Model for Early Action Proposal

Add code
Oct 18, 2018
Figure 1 for Embarrassingly Simple Model for Early Action Proposal
Figure 2 for Embarrassingly Simple Model for Early Action Proposal
Figure 3 for Embarrassingly Simple Model for Early Action Proposal
Viaarxiv icon

ISA$^2$: Intelligent Speed Adaptation from Appearance

Add code
Oct 11, 2018
Figure 1 for ISA$^2$: Intelligent Speed Adaptation from Appearance
Figure 2 for ISA$^2$: Intelligent Speed Adaptation from Appearance
Figure 3 for ISA$^2$: Intelligent Speed Adaptation from Appearance
Figure 4 for ISA$^2$: Intelligent Speed Adaptation from Appearance
Viaarxiv icon

Unsupervised learning from videos using temporal coherency deep networks

Add code
Oct 11, 2018
Figure 1 for Unsupervised learning from videos using temporal coherency deep networks
Figure 2 for Unsupervised learning from videos using temporal coherency deep networks
Viaarxiv icon