Picture for Gaoussou Youssouf Kebe

Gaoussou Youssouf Kebe

Bridging the Gap: Using Deep Acoustic Representations to Learn Grounded Language from Percepts and Raw Speech

Add code
Dec 27, 2021
Figure 1 for Bridging the Gap: Using Deep Acoustic Representations to Learn Grounded Language from Percepts and Raw Speech
Figure 2 for Bridging the Gap: Using Deep Acoustic Representations to Learn Grounded Language from Percepts and Raw Speech
Figure 3 for Bridging the Gap: Using Deep Acoustic Representations to Learn Grounded Language from Percepts and Raw Speech
Figure 4 for Bridging the Gap: Using Deep Acoustic Representations to Learn Grounded Language from Percepts and Raw Speech
Viaarxiv icon

Discriminative and Generative Transformer-based Models For Situation Entity Classification

Add code
Sep 15, 2021
Figure 1 for Discriminative and Generative Transformer-based Models For Situation Entity Classification
Figure 2 for Discriminative and Generative Transformer-based Models For Situation Entity Classification
Figure 3 for Discriminative and Generative Transformer-based Models For Situation Entity Classification
Figure 4 for Discriminative and Generative Transformer-based Models For Situation Entity Classification
Viaarxiv icon

Practical Cross-modal Manifold Alignment for Grounded Language

Sep 01, 2020
Figure 1 for Practical Cross-modal Manifold Alignment for Grounded Language
Figure 2 for Practical Cross-modal Manifold Alignment for Grounded Language
Figure 3 for Practical Cross-modal Manifold Alignment for Grounded Language
Figure 4 for Practical Cross-modal Manifold Alignment for Grounded Language
Viaarxiv icon

Presentation and Analysis of a Multimodal Dataset for Grounded LanguageLearning

Add code
Jul 31, 2020
Figure 1 for Presentation and Analysis of a Multimodal Dataset for Grounded LanguageLearning
Figure 2 for Presentation and Analysis of a Multimodal Dataset for Grounded LanguageLearning
Figure 3 for Presentation and Analysis of a Multimodal Dataset for Grounded LanguageLearning
Figure 4 for Presentation and Analysis of a Multimodal Dataset for Grounded LanguageLearning
Viaarxiv icon