Picture for Valter Estevam

Valter Estevam

Less is more: concatenating videos for Sign Language Translation from a small set of signs

Add code
Sep 03, 2024
Viaarxiv icon

Leveraging Model Fusion for Improved License Plate Recognition

Add code
Sep 08, 2023
Viaarxiv icon

Do We Train on Test Data? The Impact of Near-Duplicates on License Plate Recognition

Add code
Apr 10, 2023
Viaarxiv icon

Global Semantic Descriptors for Zero-Shot Action Recognition

Add code
Sep 24, 2022
Figure 1 for Global Semantic Descriptors for Zero-Shot Action Recognition
Figure 2 for Global Semantic Descriptors for Zero-Shot Action Recognition
Figure 3 for Global Semantic Descriptors for Zero-Shot Action Recognition
Figure 4 for Global Semantic Descriptors for Zero-Shot Action Recognition
Viaarxiv icon

A First Look at Dataset Bias in License Plate Recognition

Add code
Aug 23, 2022
Figure 1 for A First Look at Dataset Bias in License Plate Recognition
Figure 2 for A First Look at Dataset Bias in License Plate Recognition
Figure 3 for A First Look at Dataset Bias in License Plate Recognition
Figure 4 for A First Look at Dataset Bias in License Plate Recognition
Viaarxiv icon

On the Cross-dataset Generalization in License Plate Recognition

Add code
Jan 04, 2022
Figure 1 for On the Cross-dataset Generalization in License Plate Recognition
Figure 2 for On the Cross-dataset Generalization in License Plate Recognition
Figure 3 for On the Cross-dataset Generalization in License Plate Recognition
Figure 4 for On the Cross-dataset Generalization in License Plate Recognition
Viaarxiv icon

Tell me what you see: A zero-shot action recognition method based on natural language descriptions

Add code
Dec 18, 2021
Figure 1 for Tell me what you see: A zero-shot action recognition method based on natural language descriptions
Figure 2 for Tell me what you see: A zero-shot action recognition method based on natural language descriptions
Figure 3 for Tell me what you see: A zero-shot action recognition method based on natural language descriptions
Figure 4 for Tell me what you see: A zero-shot action recognition method based on natural language descriptions
Viaarxiv icon

Dense Video Captioning Using Unsupervised Semantic Information

Add code
Dec 15, 2021
Figure 1 for Dense Video Captioning Using Unsupervised Semantic Information
Figure 2 for Dense Video Captioning Using Unsupervised Semantic Information
Figure 3 for Dense Video Captioning Using Unsupervised Semantic Information
Figure 4 for Dense Video Captioning Using Unsupervised Semantic Information
Viaarxiv icon