Explanipedia

GauCho: Gaussian Distributions with Cholesky Decomposition for Oriented Object Detection Open

Jeffri Murrugarra-LLerena, José Marques Júnior, Cláudio R. Jung · 2025

Oriented Object Detection (OOD) has received increased attention in the past years, being a suitable solution for detecting elongated objects in remote sensing analysis. In particular, using regression loss functions based on Gaussian dist…

An Approach Based on LiDAR and Spherical Images for Automated Vegetation Inspection in Urban Power Distribution Lines Open

Matheus A. Bergmann, Larissa Ferreira Rodrigues Moreira, Breno Krohling, Thiago L. T. da Silveira, Cláudio R. Jung , et al. · 2024

Preventive tree pruning is an efficient way to reduce the risks of outages in the electrical network, such as cable rupture, short circuits, and fires, which may occur due to interferences between vegetation and urban electrical distributi…

"A Nova Eletricidade: Aplicações, Riscos e Tendências da IA Moderna -- "The New Electricity": Applications, Risks, and Trends in Current AI Open

Ana L. C. Bazzan, Anderson Rocha Tavares, André G. Pereira, Cláudio R. Jung, Jacob Scharcanski , et al. · 2023

The thought-provoking analogy between AI and electricity, made by computer scientist and entrepreneur Andrew Ng, summarizes the deep transformation that recent advances in Artificial Intelligence (AI) have triggered in the world. This chap…

Cell Tracking-by-detection using Elliptical Bounding Boxes Open

Lucas N. Kirsten, Cláudio R. Jung · 2023

Cell detection and tracking are paramount for bio-analysis. Recent approaches rely on the tracking-by-model evolution paradigm, which usually consists of training end-to-end deep learning models to detect and track the cells on the frames …

“A Nova Eletricidade”: Aplicações, Riscos e Tendências da IA Moderna Open

Ana L. C. Bazzan, Anderson Rocha Tavares, André M. Pereira, Cláudio R. Jung, Jacob Scharcanski , et al. · 2023

The provocative comparison between AI and electricity, made by computer scientist and entrepreneur Andrew Ng, summarizes the deep transformation that recent advances in Artificial Intelligence (AI) have triggered in the world.This chapter …

Processamento de Imagens Omnidirecionais e Aplicações Open

Thiago L. T. da Silveira, Cláudio R. Jung · 2023

Omnidirectional images and videos have been widely disseminated due to the popularization of devices for capture and visualization.Unlike images captured with perspective projection, omnidirectional media are defined on the surface of a sp…

Omnidirectional 2.5D representation for COVID-19 diagnosis using chest CTs Open

Thiago L. T. da Silveira, Paulo G. L. Pinto, Thiago S. Lermen, Cláudio R. Jung · 2023

Lightweight Traffic Sign Detection using Detachable Onboard Cameras Open

Mauricio de Paula, Cláudio R. Jung · 2023

This paper presents a novel approach for traffic sign recognition (TSR) using off-the-shelf onboard vehicular cameras. Assuming that the camera intrinsic parameters are obtained offline, an online calibration scheme is used to estimate the…

Omnidirectional Visual Computing: Foundations, Challenges, and Applications Open

Thiago L. T. da Silveira, Cláudio R. Jung · 2023

SVBR-NET: A Non-Blind Spatially Varying Defocus Blur Removal Network Open

Ali Karaali, Cláudio R. Jung · 2022

Defocus blur is a physical consequence of the optical sensors used in most cameras. Although it can be used as a photographic style, it is commonly viewed as an image degradation modeled as the convolution of a sharp image with a spatially…

3D Scene Geometry Estimation from 360° Imagery: A Survey Open

Thiago L. T. da Silveira, Paulo G. L. Pinto, Jeffri Murrugarra-Llerena, Cláudio R. Jung · 2022

This article provides a comprehensive survey on pioneer and state-of-the-art 3D scene geometry estimation methodologies based on single, two, or multiple images captured under omnidirectional optics. We first revisit the basic concepts of …

Gaussian Bounding Boxes and Probabilistic Intersection-over-Union for\n Object Detection Open

Jeffri M. Llerena, Luis Felipe Zeni, Lucas N. Kristen, Cláudio R. Jung · 2021

Most object detection methods use bounding boxes to encode and represent the\nobject shape and location. In this work, we explore a fuzzy representation of\nobject regions using Gaussian distributions, which provides an implicit binary\nre…

Gaussian Bounding Boxes and Probabilistic Intersection-over-Union for Object Detection Open

Jeffri M. Llerena, Luis Felipe Zeni, Lucas N. Kristen, Cláudio R. Jung · 2021

Most object detection methods use bounding boxes to encode and represent the object shape and location. In this work, we explore a fuzzy representation of object regions using Gaussian distributions, which provides an implicit binary repre…

Improving the Classification of Rare Chords With Unlabeled Data Open

Marcelo Bortolozzo, Rodrigo Schramm, Cláudio R. Jung · 2021

In this work, we explore techniques to improve performance for rare classes in the task of Automatic Chord Recognition (ACR). We first explored the use of the focal loss in the context of ACR, which was originally proposed to improve the c…

The Subcortical-Allocortical- Neocortical continuum for the Emergence and Morphological Heterogeneity of Pyramidal Neurons in the Human Brain Open

Alberto A. Rasia‐Filho, Kétlyn T. Knak Guerra, Carlos Escobar Vásquez, Aline Dall’Oglio, Roman Reberger , et al. · 2021

Human cortical and subcortical areas integrate emotion, memory, and cognition when interpreting various environmental stimuli for the elaboration of complex, evolved social behaviors. Pyramidal neurons occur in developed phylogenetic areas…

Dense 3D Indoor Scene Reconstruction from Spherical Images Open

Thiago L. T. da Silveira, Cláudio R. Jung · 2020

Techniques for 3D reconstruction of scenes based on images are popular and support a number of secondary applications. Traditional approaches require several captures for covering whole environments due to the narrow field of view (FoV) of…

Superpixel Image Classification with Graph Attention Networks Open

Pedro H. C. Avelar, Anderson Rocha Tavares, Thiago L. T. da Silveira, Cláudio R. Jung, Luís C. Lamb · 2020

This paper presents a methodology for image classification using Graph Neural Network (GNN) models. We transform the input images into region adjacency graphs (RAGs), in which regions are superpixels and edges connect neighboring superpixe…

Deep Multi-Scale Feature Learning for Defocus Blur Estimation Open

Ali Karaali, Naomi Harte, Cláudio R. Jung · 2020

This paper presents an edge-based defocus blur estimation method from a single defocused image. We first distinguish edges that lie at depth discontinuities (called depth edges, for which the blur estimate is ambiguous) from edges that lie…

Distilling Knowledge from Refinement in Multiple Instance Detection Networks Open

Luis Felipe Zeni, Cláudio R. Jung · 2020

Weakly supervised object detection (WSOD) aims to tackle the object detection problem using only labeled image categories as supervision. A common approach used in WSOD to deal with the lack of localization information is Multiple Instance…

Distilling Knowledge from Refinement in Multiple Instance Detection\n Networks Open

Luis Felipe Zeni, Cláudio R. Jung · 2020

Weakly supervised object detection (WSOD) aims to tackle the object detection\nproblem using only labeled image categories as supervision. A common approach\nused in WSOD to deal with the lack of localization information is Multiple\nInsta…

Collective behavior recognition using compact descriptors Open

Gustavo Führ, Cláudio R. Jung · 2018

This paper presents a novel hierarchical approach for collective behavior recognition based solely on ground-plane trajectories. In the first layer of our classifier, we introduce a novel feature called Personal Interaction Descriptor (PID…

Evaluation of Histogram of Oriented Gradients Soft Errors Criticality for Automotive Applications Open

Fernando Fernandes dos Santos, Lucas Weigel, Cláudio R. Jung, Philippe O. A. Navaux, Luigi Carro , et al. · 2016

Pedestrian detection reliability is a key problem for autonomous or aided driving, and methods that use Histogram of Oriented Gradients (HOG) are very popular. Embedded Graphics Processing Units (GPUs) are exploited to run HOG in a very ef…

Automatic Solfège Assessment. Open

Rodrigo Schramm, Helena de Souza Nunes, Cláudio R. Jung · 2015

[TODO] Add abstract here.

High Level Event Detection based on Spatial Occupancy and Interpersonal Relationships DOI: 10.14209/jcis.2015.8 Open

John Soldera, J. Bins, Marcelo Cohen, Julio Cesar Silveira Jacques, Soraia Raupp Musse , et al. · 2015

This paper describes a new approach for eventdetection in video sequences. A tracking algorithm for obliquecamera setups is initially used to extract trajectories in a trainingperiod, and a map of spatial occupancy of the scene is built. I…

High Level Event Detection based on Spatial Occupancy and Interpersonal Relationships Open

John Soldera, J. Bins, Marcelo Cohen, J.C.S. Jacques Júnior, Soraia Raupp Musse , et al. · 2015

This paper describes a new approach for eventdetection in video sequences. A tracking algorithm for obliquecamera setups is initially used to extract trajectories in a trainingperiod, and a map of spatial occupancy of the scene is built. I…

Tecnologia para automação veicular: soluções em mecatrônica e sistemas de apoio ao motorista Open

C.R. Kelber, Fernando Santos Osório, Cláudio R. Jung, Raphael Dreger, Roger Gules , et al. · 2015

O presente artigo apresenta uma visão geral das tecnologias que estão sendo desenvolvidas e implementadas em automação veicular, bem como exemplos, de alguns dos projetos desenvolvidos pelos grupo de pesquisa Veículos Autônomos da UNISINOS…

Cláudio R. Jung YOU? Author Swipe