activity
20172022
most citedMultimodal Fusion with Deep Neural Networks for Audio-Video Emotion Recognition

43 citations · 90 across the 24 of their papers we have counts for

collaborators

45 papers

cs.CV2022

Pattern Spotting and Image Retrieval in Historical Documents using Deep Hashing

Caio da S. Dias, Alceu de S. Britto, Jean P. Barddal +2

This paper presents a deep learning approach for image retrieval and pattern spotting in digital collections of historical documents. First, a region proposal algorithm detects obj…

cs.CV2022

Large-Margin Representation Learning for Texture Classification

Jonathan de Matos, Luiz Eduardo Soares de Oliveira, Alceu de Souza Britto Junior +1

This paper presents a novel approach combining convolutional layers (CLs) and large-margin metric learning for training supervised models on small datasets for texture classificati…

cs.CV2022★ 1 cited

Evaluation of Self-taught Learning-based Representations for Facial Emotion Recognition

Bruna Delazeri, Leonardo L. Veras, Alceu de S. Britto +2

This work describes different strategies to generate unsupervised representations obtained through the concept of self-taught learning for facial emotion recognition (FER). The ide…

cs.SD2022

Named Entity Recognition for Audio De-Identification

Guillaume Baril, Patrick Cardinal, Alessandro Lameiras Koerich

Data anonymization is often a task carried out by humans. Automating it would reduce the cost and time required to complete this task. This paper presents a pipeline to automate th…

cs.CV2022★ 1 cited

Multiscale Analysis for Improving Texture Classification

Steve T. M. Ataky, Diego Saqui, Jonathan de Matos +2

Information from an image occurs over multiple and distinct spatial scales. Image pyramid multiresolution representations are a useful data structure for image analysis and manipul…

cs.SD2022★ 1 cited

From Environmental Sound Representation to Robustness of 2D CNN Models Against Adversarial Attacks

Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich

This paper investigates the impact of different standard environmental sound representations (spectrograms) on the recognition performance and adversarial attack robustness of a vi…