925 citations
- Universidade Estadual de Campinas (UNICAMP)BR4 papers
- Universidade Federal de Minas GeraisBR2 papers
- Universidade Federal de São PauloBR2 papers
- Centre National de la Recherche ScientifiqueFR1 paper
- Equipes Traitement de l'Information et SystèmesFR1 paper
- Informatique, BioInformatique, Systèmes ComplexesFR1 paper
- Laboratoire d'Informatique Gaspard-MongeFR1 paper
- Norwegian University of Science and TechnologyNO1 paper
- Samsung (South Korea)KR1 paper
- Universidade Federal do ABCBR1 paper
- Université Gustave EiffelFR1 paper
- Université Paris-SaclayFR1 paper
9 papers
Exploring Bounded Component Analysis Using an Norm Criterion
Renan D. B. Brotto, Kenji Nose-Filho, João M. T. Romano
In this paper we propose a new criterion for the Blind Source Separation (BSS) of antisparse bounded sources, based on the sum of the -norm of the sources. Based on th…
Improving Deep Learning Sound Events Classifiers using Gram Matrix Feature-wise Correlations
Antonio Joia Neto, Andre G C Pacheco, Diogo C Luvizon
In this paper, we propose a new Sound Event Classification (SEC) method which is inspired in recent works for out-of-distribution detection. In our method, we analyse all the activ…
Parallax Motion Effect Generation Through Instance Segmentation And Depth Estimation
Allan Pinto, Manuel A. Córdova, Luis G. L. Decker +8
Stereo vision is a growing topic in computer vision due to the innumerable opportunities and applications this technology offers for the development of modern solutions, such as vi…
Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition
Diogo C Luvizon, Hedi Tabia, David Picard
Human pose estimation and action recognition are related tasks since both problems are strongly dependent on the human body representation and analysis. Nonetheless, most recent me…
Bright and Vivid Diffractive-Plasmonic Structural Colors
Emerson G. Melo, Ana L. A. Ribeiro, Rodrigo S. Benevides +5
Colors observed in nature are very important to form our perception of an object as well as its design. The desire to reproduce vivid colors such as those found in birds, fishes, f…
Data, Depth, and Design: Learning Reliable Models for Skin Lesion Analysis
Eduardo Valle, Michel Fornaciali, Afonso Menegola +4
Deep learning fostered a leap ahead in automated skin lesion analysis in the last two years. Those models are expensive to train and difficult to parameterize. Objective: We invest…