Leonardo Vilela Cardoso

According to our database, Leonardo Vilela Cardoso authored at least 8 papers between 2021 and 2025.

Collaborative distances:

• Dijkstra number of six.
• Erdős number of five.

2025

Streamlined extended Long Short-Term Memory for video skimming.

Leonardo Vilela Cardoso, Barbara Hellen P. Soraggi, Silvio Jamil Ferzoli Guimarães, Zenilton Kleber Gonçalves do Patrocínio Jr.

Pattern Recognit. Lett., 2025

Memory-Augmented Long Short-Term Memory for Dynamic Video Summarization.

Leonardo Vilela Cardoso, Barbara H. P. Soraggi, Silvio Jamil Ferzoli Guimarães, Zenilton K. G. do Patrocínio

Proceedings of the 38th SIBGRAPI Conference on Graphics, Patterns and Images, 2025

SkimCap: A Transformer-Based Video Captioning Method with Adaptive Attention and Hierarchical Skimming Features.

Leonardo Vilela Cardoso, Bernardo P. B. V. da C. Azevedo, Silvio Jamil Ferzoli Guimarães, Zenilton Kleber Gonçalves do Patrocínio Jr.

Proceedings of the 38th SIBGRAPI Conference on Graphics, Patterns and Images, 2025

2024

Unsupervised Video Skimming with Adaptive Hierarchical Shot Detection.

Leonardo Vilela Cardoso, July F. M. Werneck, Silvio Jamil Ferzoli Guimarães, Zenilton K. G. Patrocínio Jr.

Proceedings of the 37th SIBGRAPI Conference on Graphics, Patterns and Images, 2024

2023

Hierarchical Time-Aware Summarization with an Adaptive Transformer for Video Captioning.

Leonardo Vilela Cardoso, Silvio Jamil Ferzoli Guimarães, Zenilton Kleber Gonçalves do Patrocínio Jr.

Int. J. Semantic Comput., December, 2023

Hierarchical Time-Aware Approach for Video Summarization.

Leonardo Vilela Cardoso, Gustavo Oliveira Rocha Gomes, Silvio Jamil Ferzoli Guimarães, Zenilton Kleber Gonçalves do Patrocínio Jr.

Proceedings of the Intelligent Systems - 12th Brazilian Conference, 2023

2022

Exploring adaptive attention in memory transformer applied to coherent video paragraph captioning.

Leonardo Vilela Cardoso, Silvio Jamil Ferzoli Guimarães, Zenilton Patrocínio

Proceedings of the Eighth IEEE International Conference on Multimedia Big Data, 2022

2021

Enhanced-Memory Transformer for Coherent Paragraph Video Captioning.

Leonardo Vilela Cardoso, Silvio Jamil Ferzoli Guimarães, Zenilton K. G. do Patrocínio

Proceedings of the 33rd IEEE International Conference on Tools with Artificial Intelligence, 2021