Search Results for author: Alessandro L. Koerich

Found 19 papers, 2 papers with code

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

no code implementations26 Apr 2022 Bruna Delazeri, Leonardo L. Veras, Alceu de S. Britto Jr., Jean Paul Barddal, Alessandro L. Koerich

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

Facial Emotion Recognition

Multiscale Analysis for Improving Texture Classification

no code implementations21 Apr 2022 Steve T. M. Ataky, Diego Saqui, Jonathan de Matos, Alceu S. Britto Jr., Alessandro L. Koerich

Image pyramid multiresolution representations are a useful data structure for image analysis and manipulation over a spectrum of spatial scales.

Classification Texture Classification

Self-supervised Deep Reconstruction of Mixed Strip-shredded Text Documents

1 code implementation1 Jul 2020 Thiago M. Paixão, Rodrigo F. Berriel, Maria C. S. Boeres, Alessandro L. Koerich, Claudine Badue, Alberto F. de Souza, Thiago Oliveira-Santos

The solution presented in this work extends our previous deep learning method for single-page reconstruction to a more realistic/complex scenario: the reconstruction of several mixed shredded documents at once.

Two-View Fine-grained Classification of Plant Species

no code implementations18 May 2020 Voncarlos M. Araujo, Alceu S. Britto Jr., Luiz E. S. Oliveira, Alessandro L. Koerich

Automatic plant classification is a challenging problem due to the wide biodiversity of the existing plant species in a fine-grained scenario.

Classification General Classification

Continuous Emotion Recognition via Deep Convolutional Autoencoder and Support Vector Regressor

no code implementations31 Jan 2020 Sevegni Odilon Clement Allognon, Alessandro L. Koerich, Alceu de S. Britto Jr

In this paper, we present a new model for continuous emotion recognition based on facial expression recognition by using an unsupervised learning approach based on transfer learning and autoencoders.

Emotion Recognition Facial Expression Recognition +1

Data Augmentation for Histopathological Images Based on Gaussian-Laplacian Pyramid Blending

no code implementations31 Jan 2020 Steve Tsham Mpinda Ataky, Jonathan de Matos, Alceu de S. Britto Jr., Luiz E. S. Oliveira, Alessandro L. Koerich

Such a problem is troublesome because most of the ML algorithms attempt to optimize a loss function that does not take into account the data imbalance.

Data Augmentation

Tensor Analysis with n-Mode Generalized Difference Subspace

no code implementations4 Sep 2019 Bernardo B. Gatto, Eulanda M. dos Santos, Alessandro L. Koerich, Kazuhiro Fukui, Waldir S. S. Junior

In this paper, we present a new method for multi-dimensional data classification that relies on two premises: 1) multi-dimensional data are usually represented by tensors, since this brings benefits from multilinear algebra and established tensor factorization methods; and 2) multilinear data can be described by a subspace of a vector space.

Action Recognition General Classification +1

Universal Adversarial Audio Perturbations

1 code implementation arXiv preprint 2019 Sajjad Abdoli, Luiz G. Hafemann, Jerome Rony, Ismail Ben Ayed, Patrick Cardinal, Alessandro L. Koerich

We demonstrate the existence of universal adversarial perturbations, which can fool a family of audio classification architectures, for both targeted and untargeted attack scenarios.

Audio Classification

Emotion Recognition Using Fusion of Audio and Video Features

no code implementations25 Jun 2019 Juan D. S. Ortega, Patrick Cardinal, Alessandro L. Koerich

In this paper we propose a fusion approach to continuous emotion recognition that combines visual and auditory modalities in their representation spaces to predict the arousal and valence levels.

Emotion Recognition Transfer Learning

Memory Integrity of CNNs for Cross-Dataset Facial Expression Recognition

no code implementations28 May 2019 Dylan C. Tannugi, Alceu S. Britto Jr., Alessandro L. Koerich

A common way to circumvent the lack of data is to use CNNs trained on large datasets of different domains and fine-tuning the layers of such networks to the target domain.

Facial Expression Recognition

Texture CNN for Thermoelectric Metal Pipe Image Classification

no code implementations28 May 2019 Daniel Vriesman, Alessandro Zimmer, Alceu S. Britto Jr., Alessandro L. Koerich

In this paper, the concept of representation learning based on deep neural networks is applied as an alternative to the use of handcrafted features in a method for automatic visual inspection of corroded thermoelectric metallic pipes.

Classification General Classification +3

Histopathologic Image Processing: A Review

no code implementations16 Apr 2019 Jonathan de Matos, Alceu de Souza Britto Jr., Luiz E. S. Oliveira, Alessandro L. Koerich

In this work we present a literature review about the computing techniques to process HI, including shallow and deep methods.

Double Transfer Learning for Breast Cancer Histopathologic Image Classification

no code implementations16 Apr 2019 Jonathan de Matos, Alceu de S. Britto Jr., Luiz E. S. Oliveira, Alessandro L. Koerich

This work proposes a classification approach for breast cancer histopathologic images (HI) that uses transfer learning to extract features from HI using an Inception-v3 CNN pre-trained with ImageNet dataset.

Classification General Classification +2

People Counting in Crowded and Outdoor Scenes using a Hybrid Multi-Camera Approach

no code implementations2 Apr 2017 Fabio Dittrich, Luiz E. S. de Oliveira, Alceu S. Britto Jr., Alessandro L. Koerich

For such an aim, corner points are extracted from groups of people in a foreground image and computed by a learning algorithm which estimates the number of people in the scene.

Cannot find the paper you are looking for? You can Submit a new open access paper.