Sponsor:

*VIRTUAL* – October 18th-22nd, 2021

Co-located with SVR 2021 e SBGames 2021

Certificates for SIBGRAPI 2021 are available through this link.

SIBGRAPI 2021 Program

Quick links – Schedule  •  Keynotes  •  Talks  •  Tutorials  • 
TS1  • TS2  • TS3  • TS4  • TS5  • TS6  • TS7  • TS8  • TS9  • TS10  • TS11  • 
WTD  • WUW  • WiP  • WIA  • WVIS  • 

Scroll down for list of papers and sessions with direct YouTube links.
Times specified in Brasilia Time (BRT), UTC -3.
Click on the "Schedule at a Glance" table below to open it in a new window in full size.

SIBGRAPI 2021 Opening Ceremony

October 18th (Mon)  |  13:30 to 14:00 BRT

SIBGRAPI 2021 Scientific Awards & Closing

October 22nd (Fri)  |  18:00 to 18:30 BRT

SIBGRAPI 2021 Keynote Speakers

Photo of Luis Gustavo Nonato.

Luis Gustavo Nonato
ICMC-USP, Brazil

Photo of Hugo Proença.

Hugo Proença
University of Beira Interior, Portugal

Photo of Reginé Gilbert.

Reginé Gilbert
NYU Tandon School of Engineering, USA

Photo of Gladimir Baranoski.

Gladimir Baranoski
University of Waterloo, Canada

Photo of Magy Seif El-Nasr.

Magy Seif El-Nasr
University of California at Santa Cruz, USA

Keynote 1 - Luis Gustavo Nonato

October 19th (Tue)  |  11:00 to 12 noon BRT
Session Chair: Gladimir Baranoski (University of Waterloo, Canada)

Photo of Luis Gustavo Nonato.

Luis Gustavo Nonato
ICMC-USP, Brazil

Talk Title: From Geometry Processing to Spatio-Temporal Data Analysis and Visualization: a historical view

Talk Abstract: In this talk, we will revisit the work carried out by the research group led by prof. Nonato and his collaborators in the last decades. From a historical perspective, we will show the group's contributions in the areas of geometric processing, visualization, and spatio-temporal visual data analysis, overviewing the mathematical and computational tools employed to tackle problems ranging from mesh generation from images to crime pattern analysis.

Short Bio: Luis Gustavo Nonato received the PhD degree in applied mathematics from the Pontifícia Universidade Católica do Rio de Janeiro, Rio de Janeiro - Brazil, in 1998. He is professor in the Instituto de Ciências Matemáticas e de Computação, Universidade de São Paulo, São Carlos, Brazil. Nonato was a visiting professor at the Center for Data Science, New York University, New York - USA from 2016 to 2018 and he was also a visiting scholar in the Scientific Computing and Imaging Institute, University of Utah, Salt Lake City - USA from 2008 to 2010. Besides having served in several program committees, including IEEE SciVis, IEEE InfoVis, and EuroVis, Nonato was associate editor of the Computer Graphics Forum journal and currently he is associate editor of the IEEE Transactions on Visualization and Computer Graphics. He is also editor-in-chief of the SBMAC SpringerBriefs in Applied Mathematics and Computational Sciences. Nonato's main research interests include visual analytics, geometric computing, data science, and visualization. Nonato has a strong interest in bridging the gap between academia, industry, and governments, leading a number of initiatives with the private sector and government agencies.

Keynote 2 - Hugo Proença

October 19th (Tue)  |  15:00 to 16:00 BRT
Session Chair: David Menotti (UFPR, Brazil)

Photo of Hugo Proença.

Hugo Proença
University of Beira Interior, Portugal

Talk Title: Advances in Visually Interpretable Biometric Recognition

Talk Abstract: There is a popular adage that states that “a picture is worth more than 1,000 words”. Complex ideas are known to be conveyed in a more effective way by a single still image than by a verbal description. Among the many examples in the literature supporting this idea, we highlight Leonardo da Vinci’s, who wrote that a poet would be "overcome by sleep and hunger before being able to describe with words what a painter is able to depict in an instant" or Napoleon Bonaparte, who is supposed to have said that “un bon croquis vaut mieux qu'un long discours".
  In this talk, we will discuss the development of methods to simultaneously (and jointly) “recognize” objects in images and “interpret” their decisions. In particular, we consider the biometric (periocular) recognition problem. In practice, the idea is to obtain classification models that not only infer class (ID) information , but also provide local and global visualizations of the data that justified the decision: e.g., by providing synthetic representations of the input data, that - in a human understandable way - justify why a pair of samples is/is not from the same person.
  Such “visually interpretable recognizers” have various applications, such as: 1) support human-decision processes in domains such as forensics, where the results of one analysis should be communicated in a human-understandable way to a jury or a judge; 2) improve biometrics feature engineering, by providing cues about the features that are of most interest to provide good decisions; 3) drive future data collection protocols, by providing a good understanding of the value of each data segment privileged by the recognition system; and 4) augment trust, by showing insights that fit the usual human understanding of the recognition problem, even for people with no knowledge in data science.

Short Bio: Hugo Proença (SM'12), B.Sc. (2001), M.Sc. (2004) and Ph.D. (2007) is an Associate Professor in the Department of Computer Science, University of Beira Interior and has been researching mainly about biometrics and visual-surveillance. He was the coordinating editor of the IEEE Biometrics Council Newsletter and the area editor (ocular biometrics) of the IEEE Biometrics Compendium Journal. He is a member of the Editorial Boards of the Image and Vision Computing, IEEE Access and International Journal of Biometrics. Also, he served as Guest Editor of special issues of the Pattern Recognition Letters, Image and Vision Computing and Signal, Image and Video Processing journals.

Keynote 3 - Cláudio Rosito Jung

October 20th (Wed)  |  11:00 to 12 noon BRT
Session Chair: Afonso Paiva (ICMC-USP, Brazil)

Photo of Cláudio Rosito Jung.

Cláudio Rosito Jung
UFRGS, Brazil

Talk Title: Beyond Horizontal Bounding Boxes for Object Detection

Talk Abstract: Object Detection is a classical problem in computer vision, and it consists of identifying each instance of a set of categories in a given image. Representing objects as horizontal bounding boxes (HBBs) allows easy annotation and fewer parameters to regress, but might be a poor fit for rotated or deformable objects. On the other hand, full segmentation masks provide a complete representation of the object, but annotation is tedious and regression typically involves a non-parametric representation. In this talk I will discuss a few alternatives inbetween these two extrema: first I will talk about warped planar representations (WPR), in which the object is represented as an affine-transformed HBB; then I will talk about a fuzzy representation based on Gaussian Bounding Boxes (GBBs), which can be mapped either to rotated ellipses or Oriented Bounding Boxes (OBBs) and allows the use of a differentiable loss function that resembles the Intersection-over-Union (IoU).

Short Bio: Cláudio Rosito Jung received the B.S. and M.S. degrees in Applied Mathematics, and the Ph.D. degree in Computer Sciences, from Universidade Federal do Rio Grande do Sul (UFRGS), Brazil, in 1993,1995 and 2002, respectively. He is currently a faculty member at UFRGS in the Computer Science department, and was a visiting faculty at the University of Pennsylvania from july 2015 to july 2016. His research interests include several aspects in image processing, computer vision, pattern recognition and deep learning, such as biomedical imaging, multiscale image analysis, intelligent vehicles, multimedia applications, human motion synthesis and analysis, audiovisual signal processing, stereo/multiview matching and spherical image processing.

Keynote 4 - Reginé Gilbert

October 20th (Wed)  |  15:00 to 16:00 BRT
Session Chair: Victor Adriel de Jesus Oliveira (St. Pölten University of Applied Sciences, Austria)

Photo of Reginé Gilbert.

Reginé Gilbert
NYU Tandon School of Engineering, USA

Talk Title: Accessible XR

Talk Abstract: This talk will introduce Accessibility in XR. We will discuss opportunities we have to create spaces and experiences for our present and future selves.

Short Bio: Reginé Gilbert is a user experience designer, educator, and international public speaker with over 10 years of experience working in the technology arena. She has a strong belief in making the world a more accessible place—one that starts and ends with the user. Regine’s areas of research are digital accessibility, inclusive design and immersive experiences. In 2019, Regine’s first book, Inclusive Design for a Digital World: Designing with Accessibility in Mind was released through Apress publishing.

Keynote 5 - Gladimir Baranoski

October 21st (Thu)  |  11:00 to 12 noon BRT
Session Chair: Hugo Proença (University of Beira Interior, Portugal)

Photo of Gladimir Baranoski.

Gladimir Baranoski
University of Waterloo, Canada

Talk Title: The Quest for Fundamental Biophysical Data

Talk Abstract: Predictive models of light and matter interactions are employed in a wide range of applications in several fields from computer graphics and remote sensing to biomedical optics and photonics, just to name a few. It is a well-known fact that a well-designed model is of little use without reliable specimen characterization data (e.g., thickness and pigment concentrations) to be used as input, and reliable evaluation data (e.g., spectral reflectance and transmittance) to be used in the assessment of its predictive capabilities. Ideally, the specimen’s characterization data to be incorporated into a model should correspond to the specimen used to obtain the measured data employed in its evaluation. However, the few spectral datasets available in the literature rarely provide a comprehensive description of the target specimens. Data is even more scarce for materials in their pure form, such as natural pigments, whose absorption profile is often obtained either through inversion procedures, which may be biased by the inaccuracies of the inverted model, or does not take into account in vivo and in vitro discrepancies. In this talk, we informally address these issues and their practical implications for the development of robust hyperspectral technologies relying on light interaction models.

Short Bio: Gladimir V. G. Baranoski received his doctoral degree in computer science from the University of Calgary (Canada) in 1998. He is currently a Professor of the School of Computer Science at the University of Waterloo (Canada), where he has established the Natural Phenomena Simulation Group (NPSG). His research interests include primarily the predictive simulation of light interactions with natural materials. As the leader of NPSG, he has been actively participating in the development of a wide range of hyperspectral light interaction models aimed at interdisciplinary investigations. The results of his research have been disseminated in well- known venues of different fields, including computer graphics, remote sensing, and biomedical optics. He has also organized conference courses and published books related to his research work.

Keynote 6 - Magy Seif El-Nasr

October 21st (Thu)  |  15:00 to 16:00 BRT
Session Chair: Esteban Clua (UFF, Brazil)

Photo of Magy Seif El-Nasr.

Magy Seif El-Nasr
Vice Chair of Serious Games, University of California at Santa Cruz, USA

Talk Title: A User-Centric and Data-Driven Approach to Game Design

Talk Abstract: Games, especially Serious Games, have, for many years, been used as applications for entertainment, education, training, crowdsourcing, as well as platforms for understanding human behavior, which creates opportunities for making great societal impacts. The potential social impact of these environments elevates the importance of developing methods that can enhance the player engagement during and after production as well as evaluate the value of these designs in the long term. Towards these goals, I will discuss various visualization and behavior analysis tools and innovative methods we have developed and used over the past decade. I will also discuss a case study where these tools and methods are used. I will discuss how these tools and methods enabled us to discover design problems that impacted players’ engagement, adherence, and motivation. I will then conclude by discussing results from our current studies investigating the use of user and data-centric approaches in current esports tools used for training and engagement.

Short Bio: Magy Seif El-Nasr is a Professor in Computational Media at the University of California, Santa Cruz, where she directs the Game User Interaction and Intelligence (GUII) Lab. Dr. Seif El-Nasr earned her Ph.D. degree from Northwestern University in Computer Science in 2003. Her research focuses on two goals (a) developing automated tools and techniques for authoring, adapting, and personalizing virtual environments (e.g., interactive narrative, believable characters, and visuals), and (b) developing evidence-based methodologies to measure the effectiveness of game environments through the development of novel indepth behavior mining and visual analytics tools. She worked in collaboration with several game companies both in the serious as well as the entertainment game spaces. She published the first book on the subject of game analytics, called Game Analytics: Maximizing the Value of Player Data. Her new book on Game Data Science follows her work on Game Data Science and Analytics, released October 2021. Her work is internationally known and cited in several game industry books. Additionally, she has received several awards and recognition within the game research community. Notably, she received four Best Paper Awards and one honorable mention. Further, she was named a HEVGA (Higher Education Video Game Alliance) Fellow. She also serves as an associate editor for IEEE Transactions on Games, IEEE Transactions on Affective Computing, and Human Computer Interaction.

SIBGRAPI 2021 Workshops Invited Talks

Photo of Fernando Paulovich.

Fernando Paulovich
Dalhousie University, Canada
WVIS Invited Talk

Photo of Vanessa Testoni.

Vanessa Testoni
Samsung Research Brazil
WIA Invited Talk

Photo of Marcelo Siqueira.

Marcelo Siqueira
Align Technology, Inc.
WIA Invited Talk

Fernando Paulovich

October 18th (Mon)  |  14:30 to 15:30 BRT
Session Chair: Carla Dal Sasso Freitas (UFRGS)

Photo of Fernando Paulovich.

Fernando Paulovich
Dalhousie University, Canada

Talk Title: From Visual Analytics to Explainable AI: the Ingredients of More Reliable Classification Models

Talk Abstract: In recent decades, classification models have proven to be essential machine learning tools due to their potential and applicability in various domains. In these years, the general direction of most researchers has been to improve quantitative metrics, despite the lack of information about models' inner workings such metrics convey. This paradigm is shifting, and strategies beyond tables and numbers to help interpret model decisions are gaining importance. As part of this trend, visualization and visual analytics tools and techniques have been widely used and shown to be essential ingredients for implementing the so-called explainable Artificial Intelligence (XAI) concept. In this talk, I will introduce the idea of visual analytics and discuss how it has been used to interpret classification models, support the understanding of models' general behavior, and audit the produced results to increase confidence in the predictive analytics process.

Short Bio: Fernando V. Paulovich is an associate professor and Canada Research Chair in Data Visualization at the Faculty of Computer Science, Dalhousie University, and head of the Visualization and Visual Analytics (VVA) lab. Over the past ten years, he has been researching in the field of computational visualization, more specifically information visualization, visual analytics and visual data mining. His focus is on integrating machine learning and visualization tools and techniques, taking advantage of the “intelligence” provided by machine learning approaches, and of user knowledge by means of interactions with visual representations, helping people to understand and take full advantage of this "brave new information world."

Vanessa Testoni

October 22nd (Fri)  |  9:00 to 10:00 BRT
Session Chair: TBA (-)

Photo of Vanessa Testoni.

Vanessa Testoni
Samsung Research Brazil

Talk Title: True immersive experience is finally coming to us: the standards ecosystem under construction to enable real world products

Talk Abstract: Video streaming is already the number one activity in smartphone use while video is the most used form of communication. Besides, the much-awaited new immersive experiences had been promising a significant increase in broadband usage for video streaming for years and now we already have the first dense light field (holographic) display available as a commercial product! In 2019, immersive media was considered one of the main drivers of 5G services (higher bandwidth, low latency, and speed/throughput to deliver next generation content) and its market was expected to expand at a rate of 19.6% achieving US$124.57 billion by 2025 (according to Grand View Research Inc.). The COVID-19 pandemic reinforced this trend and now we have an even better adjusted forecast: a market of US$184.27 billion by 2027. In this multi-billionaire market, the wide adoption of international multimedia standards is fundamental to ensure interoperability among all the heterogeneous devices, systems and video-on-demand platforms. The creation of new standards for the upcoming immersive media formats is a constant need and the competition among the standards organizations increases year after year. In 2018, Brazil finally became not only a user but also a producer of these standards. The official Brazilian delegation (first and only one in Latin America for the "ISO/IEC JTC 1/SC29") was created in 2018 and since then Brazilian experts from industry and academia have been actively contributing with innovative technologies for these future ISO/ITU-T multimedia standards. The Brazilian national body activities will be presented in this talk, as well as the standards creation process and current standards developing organizations (SDOs) status.

Short Bio: Vanessa Testoni is the Multimedia team leader at SRBR (Samsung Research Brazil), where her research interests are a mix of image/video coding, processing and streaming, video standards, machine learning, computer vision and information theory. She received her BS in CS from PUCPR (Brazil), her EE degree from UFPR (Brazil) and her MSc and PhD degrees in EE from UNICAMP (Brazil). She started her career at Siemens Telecommunications and later joined UCSD (USA) as a postdoctoral employee. She was awarded the Microsoft Research PhD Fellowship Award and the MIT TR35 (Young Innovators under 35) in the first Brazilian edition of the award. She is an IEEE senior member, an elected affiliate member of the Brazilian Academy of Sciences (ABC), a previous chair of the IEEE SPS (Signal Processing Society) São Paulo chapter and was nominated the first national head of the ISO/IEC JTC 001/SC 29 (JPEG/MPEG) Brazilian delegation.

Marcelo Siqueira

October 22nd (Fri)  |  10:45 to 11:45 BRT
Session Chair: TBA (-)

Photo of Marcelo Siqueira.

Marcelo Siqueira
Align Technology, Inc.

Talk Title: From trimmed NURBS to watertight boundary representations of CAD models

Talk Abstract: A fundamental problem in Geometric Modeling is the one of converting the representation of a solid from one (representation) form to another. In this talk, I will discuss a particular instance of this problem, namely, the conversion of boundary representations of CAD models from the trimmed Non-Uniform Rational B-Splines (NURBS) form to watertight parametric forms. For historical and for practical reasons, the geometry of CAD models have been represented by trimmed NURBS. While this representation form is often more convenient to control a signature piece of the boundary in isolation, it is in general very difficult or impossible to represent the entire boundary as a watertight surface. In other words, the trimmed NURBS surface patches may not join each other continuously, giving rise to a boundary representation with very small gaps (i.e., fillets) along the boundary curves of the trimmed patches. With the advent and recent progress of Iso-Geometric Analysis (IGA), the need for watertight boundary representations of CAD models prompted several researchers to pay close attention to the conversion problem again. The aim of my talk is two-fold. First, I will focus on the shortcomings of the most recent solutions to the conversion problem from an industry's perspective. Second, I will shed some light on what constitutes a good solution to the problem. The talk is related to an on-going research collaboration with Jörg Peters (UF, United States) and Paulo Pagliosa (UFMS, Brazil).

Short Bio: Marcelo Siqueira received the BSc (computer science), in 1992, from Universidade Federal do Rio Grande do Norte (UFRN). He received the master degree, in 1994, from Universidade de São Paulo (USP), and the PhD degree, in 2006, from the University of Pennsylvania (UPenn). From 1996 to 2008, he was a professor at the College of Computing of Universidade Federal de Mato Grosso do Sul (UFMS). From 2009 to 2017, he was a professor at the Department of Mathematics of UFRN. In 2017, he joined Velo3D, a startup located at Campbell, CA, USA, that developed a disruptive technology for 3d printing of metallic parts. In 2018, he joined Align Technology, the world leader of clear aligners for orthodontic therapy, where is currently a full-time researcher and software developer. His research interests are mesh generation, modeling of curves and surfaces, and digital topology.

SIBGRAPI 2021 Tutorials

Click on the icon to access the associated survey paper preprint.

Tutorial 1

This tutorial has two parts.
October 18th (Mon)
Part 1: 8:45 to 12 noon BRT
Part 2: 14:15 to 17:30 BRT
Session Chair: Sandra Avila (IC/UNICAMP)

Training Deep Networks from Zero to Hero: avoiding pitfalls and going beyond
Moacir A. Ponti (ICMC - Universidade de São Paulo), Fernando P. dos Santos (ICMC - Universidade de São Paulo), Leo S. F. Ribeiro (ICMC - Universidade de São Paulo), and Gabriel B. Cavallari (ICMC - Universidade de São Paulo)

Tutorial 2

October 18th (Mon)  |  8:45 to 12 noon BRT
Session Chair: Leandro A. F. Fernandes (IC/UFF)

PGA: reflecting on easier math for graphics programmers
Leo Dorst (University of Amsterdam) and Steven De Keninck (Origami Digital LLC)

Tutorial 3

October 18th (Mon)  |  8:45 to 12 noon BRT
Session Chair: Anselmo Antunes Montenegro (IC/UFF)

Neural Networks for Implicit Representations of 3D Scenes
Luiz Schirmer (Pontifícia Universidade Católica do Rio de Janeiro), Guilherme Schardong (Pontifícia Universidade Católica do Rio de Janeiro), Vinícius da Silva (Pontifícia Universidade Católica do Rio de Janeiro), Helio Lopes (Pontifícia Universidade Católica do Rio de Janeiro), Tiago Novello (Instituto de Matemática Pura e Aplicada), Daniel Yukimura (Instituto de Matemática Pura e Aplicada), Thales Magalhaes (Instituto de Matemática Pura e Aplicada), Hallison Paz (Instituto de Matemática Pura e Aplicada), and Luiz Velho (Instituto de Matemática Pura e Aplicada)

Tutorial 4

October 22nd (Fri)  |  8:45 to 12 noon BRT
Session Chair: Sandra Avila (IC/UNICAMP)

Machine Learning Bias in Computer Vision: Why do I have to care?
Camila Laranjeira (Universidade Federal de Minas Gerais), Virgínia Fernandes Mota (Universidade Federal de Minas Gerais), and Jefersson Alex dos Santos (Universidade Federal de Minas Gerais)

SIBGRAPI 2021 Technical Sessions (TS)

TS1 - Graphics & Visualization I

October 19th (Tue)  |  9:15 to 10:30 BRT
Session Chair: Manuel M. Oliveira (UFRGS)

Click on the icon to access each paper's preprint.
Click on the icon to access each paper's pre-recorded video presentation.

A New Focus+Context Visualization Technique for Inspecting Black Oil Reservoir Models
Luiz Felipe Netto (Tecgraf/PUC-Rio Institute) and Waldemar Celes (Tecgraf/PUC-Rio Institute)
Presenting Author(s): Luiz Felipe Netto
Optimized 2D Ball Trees
Luis Carlos dos Santos Coutinho Retondaro (Centro Federal de Educação Tecnológica do Rio de Janeiro) and Claudio Esperança (Universidade Federal do Rio de Janeiro)
Presenting Author(s): Claudio Esperança
A particle-in-cell method for anisotropic fluid simulation [C&G Track]
Emanuel Antônio Parreiras (Universidade Federal de Juiz de Fora), Marcelo Bernardes Vieira (Universidade Federal de Juiz de Fora), Arthur Gonze Machado (Universidade Federal de Juiz de Fora), Marcelo Caniato Renhe (Universidade Federal de Juiz de Fora), and Gilson Antônio Giraldi (Laboratório Nacional de Computação Científica)
Presenting Author(s): Emanuel Antônio Parreiras
Non-overlapping geometric shadow map [C&G Track]
Erison Miller Santos Mesquita (Universidade Federal do Ceará), Creto Augusto Vidal (Universidade Federal do Ceará), Joaquim Bento Cavalcante-Neto (Universidade Federal do Ceará), and Rafael Fernandes Ivo (Universidade Federal do Ceará)
Presenting Author(s): Erison Miller Santos Mesquita
Spatially and color consistent environment lighting estimation using deep neural networks for mixed reality [C&G Track]
Bruno Augusto Dorta Marques (Universidade Federal do ABC), Esteban Walter Gonzalez Clua (Universidade Federal Fluminense), Anselmo Antunes Montenegro (Universidade Federal Fluminense), and Cristina Nader Vasconcelos (Universidade Federal Fluminense)
Presenting Author(s): Bruno Augusto Dorta Marques, Esteban Walter Gonzalez Clua
Deep Learning-Based Framework for Shape Instance Registration on 3D CAD Models [C&G Track]
Lucas Figueiredo (Tecgraf/PUC-Rio Institute), Paulo Ivson (Tecgraf/PUC-Rio Institute), and Waldemar Celes (Tecgraf/PUC-Rio Institute)
Presenting Author(s): Lucas Figueiredo

TS2 - Computer Vision

October 19th (Tue)  |  13:30 to 14:30 BRT
Session Chair: William Schwartz (UFMG)

Click on the icon to access each paper's preprint.
Click on the icon to access each paper's pre-recorded video presentation.

Gravity Alignment for Single Panorama Depth Inference
Matheus A. Bergmann (Federal University of Rio Grande do Sul), Paulo G. L. Pinto (Federal University of Rio Grande do Sul), Thiago L. T. da Silveira (Federal University of Rio Grande do Sul), and Cláudio R. Jung (Federal University of Rio Grande do Sul)
Presenting Author(s): Matheus A. Bergmann, Paulo G. L. Pinto
Gaze Estimation Via Self-attention Augmented Convolutions
Gabriel Lefundes Vieira (Federal University of Bahia) and Luciano Oliveira (Federal University of Bahia)
Presenting Author(s): Gabriel Lefundes Vieira
An Investigation of 2D Keypoints Detection on Challenging Scenarios Using Depthwise Separable Convolutions: A Hand Pose Estimation Case Study
Willams Costa (Universidade Federal de Pernambuco), Lucas Figueiredo (Universidade Federal de Pernambuco), João Marcelo Teixeira (Universidade Federal de Pernambuco), João Paulo Lima (Universidade Federal Rural de Pernambuco), and Veronica Teichrieb (Universidade Federal de Pernambuco)
Presenting Author(s): Willams Costa
Fast Spatial-Temporal Transformer Network
Rafael Molossi Escher (Federal University of Rio Grande), Rodrigo Andrade de Bem (Federal University of Rio Grande), and Paulo Lilles Jorge Drews-Jr (Federal University of Rio Grande)
Presenting Author(s): Rafael Molossi Escher, Paulo Lilles Jorge Drews-Jr
Analyzing the Effects of Dimensionality Reduction for Unsupervised Domain Adaptation
Renato Sergio Lopes Junior (Federal University of Minas Gerais) and William Robson Schwartz (Federal University of Minas Gerais)
Presenting Author(s): Renato Sergio Lopes Junior

TS3 - Medical & Biomedical Imaging

October 19th (Tue)  |  16:30 to 18:00 BRT
Session Chair: Alexandre X. Falcão (UNICAMP)

Click on the icon to access each paper's preprint.
Click on the icon to access each paper's pre-recorded video presentation.

BORDE: Boundary and Sub-Region Denormalization for Semantic Brain Image Synthesis
Israel N. Chaparro-Cruz (Universidad Católica San Pablo) and Javier A. Montoya-Zegarra (ETH Zurich)
Presenting Author(s): Israel N. Chaparro-Cruz
Learning to Segment Medical Images from Few-Shot Sparse Labels
Pedro H. T. Gama (Universidade Federal de Minas Gerais), Hugo Oliveira (Universidade de São Paulo), and Jefersson A. dos Santos (Universidade Federal de Minas Gerais)
Presenting Author(s): Pedro H. T. Gama
A New Grammar for Creating Convolutional Neural Networks Applied to Medical Image Classification
Cleber A. C. F da Silva (Federal Rural University of Pernambuco), Péricles B. C. Miranda (Federal Rural University of Pernambuco), and Filipe R. Cordeiro (Federal Rural University of Pernambuco)
Presenting Author(s): Cleber A. C. F da Silva
Improving Similarity Metric of Multi-modal MR Brain Image Registration Via a Deep Ensemble
Natan Andrade (Universidade Federal de São Paulo), Fabio A. Faria (Universidade Federal de São Paulo), and Fábio A. M. Cappabianco (Universidade Federal de São Paulo)
Presenting Author(s): Fábio A. M. Cappabianco
An Approach Based on Image Processing Techniques to Segment Lung Region in Chest X-ray Images
Luiza C. de Menezes (Universidade Federal Fluminense), Augusto R. V. F. de Araújo (Universidade Federal Fluminense), Aura Conci (Universidade Federal Fluminense)
Presenting Author(s): Luiza C. de Menezes
Automatic Segmentation of Posterior Fossa Structures in Pediatric Brain MRIs
Hugo Oliveira, Larissa Penteado (Universidade de São Paulo), José Luiz Maciel (Universidade de São Paulo), Suely Fazio Ferraciolli (Universidade de São Paulo), Marcelo Straus Takahashi (Universidade de São Paulo), Isabelle Bloch (Sorbonne Universite), Roberto Cesar Junior (Universidade de São Paulo)
Presenting Author(s): Hugo Oliveira
The Gated Recurrent Conditional Generative Adversarial Network (GRC-GAN): application to denoising of low-dose CT images
Mateus Baltazar de Almeida (Universidade Federal do Agreste de Pernambuco), Luis F. Alves Pereira (Universidade Federal do Agreste de Pernambuco), Tsang Ing Ren (Universidade Federal de Pernambuco), George D. C. Cavalcanti (Universidade Federal de Pernambuco), and Jan Sijbers (University of Antwerp)
Presenting Author(s): Mateus Baltazar de Almeida

TS4 - Graphics & Visualization II

October 20th (Wed)  |  9:15 to 10:30 BRT
Session Chair: Jose Gustavo S. Paiva (UFU)

Click on the icon to access each paper's preprint.
Click on the icon to access each paper's pre-recorded video presentation.

DRIFT: A visual analytic tool for scientific literature exploration based on textual and image content
Ximena Pocco (Universidad Catolica San Pablo), Jorge Poco (Getulio Vargas Foundation), Matheus Viana (IBM Research), Rogerio de Paula (IBM Research), Luis Gustavo Nonato (University of São Paulo), and Erick Gomez-Nieto (Universidad Catolica San Pablo)
Presenting Author(s): Ximena Pocco
Interactive Visualizations to Support Randomized Clinical Trial Monitoring
Marina Fortes Rey (Universidade Federal do Rio Grande do Sul) and Carla Maria Dal Sasso Freitas (Universidade Federal do Rio Grande do Sul)
Presenting Author(s): Carla Maria Dal Sasso Freitas
An appearance-driven space to create new BRDFs [C&G Track]
Mislene da Silva Nunes (Federal University of Sergipe), Gastão Florêncio Miranda Junior (Federal University of Sergipe), and Beatriz Trinchão Andrade (Federal University of Sergipe)
Presenting Author(s): Mislene da Silva Nunes
Simultaneous Magnification of Subtle Motions and Color Variations in Videos Using Riesz Pyramids [C&G Track]
Thomas V. Fontanari (Instituto de Informática, UFRGS) and Manuel M. Oliveira (Instituto de Informática, UFRGS)
Presenting Author(s): Thomas V. Fontanari
Contrastive analysis for scatterplot-based representations of dimensionality reduction [C&G Track]
Wilson E. Marcílio-Jr (São Paulo State University), Danilo M. Eler (São Paulo State University), and Rogério E. Garcia (São Paulo State University)
Presenting Author(s): Wilson E. Marcílio-Jr
Fast and reliable incremental dimensionality reduction for streaming data [C&G Track]
Tácito Trindade de Araújo Tiburtino Neves (Federal University of Alagoas), Rafael Messias Martins (Linnaeus University), Danilo Barbosa Coimbra (Federal University of Bahia), Kostiantyn Kucher (Linnaeus University), Andreas Kerren (Linnaeus University), and Fernando V. Paulovich (Dalhousie University)
Presenting Author(s): Tácito Trindade de Araújo Tiburtino Neves

TS5 - Image & Video Analysis

October 20th (Wed)  |  13:30 to 14:30 BRT
Session Chair: Luciano Oliveira (UFBA)

Click on the icon to access each paper's preprint.
Click on the icon to access each paper's pre-recorded video presentation.

Non-local Medians Filter for Joint Gaussian and Impulsive Image Denoising
Alexandre L. M. Levada (Federal University of São Carlos)
Presenting Author(s): Alexandre L. M. Levada
Learning-based End-to-End Video Compression Using Predictive Coding
Matheus C. de Oliveira (University of Brasília), Luiz G. R. Martins (University of Brasília), Henrique Costa Jung (University of Brasília), Nilson Donizete Guerin Jr. (University of Brasília), Renam Castro da Silva (Samsung R&D Brazil), Eduardo Peixoto (University of Brasília), Bruno Macchiavello (University of Brasília), Edson M. Hung (University of Brasília), Vanessa Testoni (Samsung R&D Brazil), and Pedro Garcia Freitas (Samsung R&D Brazil)
Presenting Author(s): Matheus C. de Oliveira
Improving Transferability of Domain Adaptation Networks Through Domain Alignment Layers
Lucas F. A. Silva (Universidade Federal de São Paulo), Daniel C. G. Pedronette (São Paulo State University), Fabio A. Faria (Universidade Federal de São Paulo), João Paulo Papa (São Paulo State University), and Jurandy Almeida (Universidade Federal de São Paulo)
Presenting Author(s): Lucas F. A. Silva, Jurandy Almeida
A System for Visual Analysis of Objects Behavior in Surveillance Videos
Cibele Mara Fonseca (Federal University of Uberlândia) and Jose Gustavo S. Paiva (Federal University of Uberlândia)
Presenting Author(s): Jose Gustavo S. Paiva, Cibele Mara Fonseca
Musical Hyperlapse: A Multimodal Approach to Accelerate First-Person Videos
Diognei de Matos (Universidade Federal de Minas Gerais), Washington Ramos (Universidade Federal de Minas Gerais), Luiz Romanhol (Universidade Federal de Minas Gerais), Erickson R. Nascimento (Universidade Federal de Minas Gerais)
Presenting Author(s): Diognei de Matos

TS6 - Datasets & Classifiers

October 21st (Thu)  |  9:15 to 10:30 BRT
Session Chair: George Cavalcanti (UFPE)

Click on the icon to access each paper's preprint.
Click on the icon to access each paper's pre-recorded video presentation.

Iterative Pseudo-Labeling with Deep Feature Annotation and Confidence-Based Sampling
Barbara C. Benato (University of Campinas), Alexandru C. Telea (Utrecht University), and Alexandre X. Falcão (University of Campinas)
Presenting Author(s): Barbara C. Benato
Reducing the Need for Bounding Box Annotations in Object Detection Using Image Classification Data
Leonardo Blanger (University of Sao Paulo), Nina S. T. Hirata (University of Sao Paulo), and Xiaoyi Jiang (University of Münster)
Presenting Author(s): Leonardo Blanger
Data Augmentation Guidelines for Cross-Dataset Transfer Learning and Pseudo Labeling
Fernando Pereira dos Santos (Universidade de São Paulo), Gabriela Salvador Thumé (Universidade de São Paulo), and Moacir Antonelli Ponti (Universidade de São Paulo)
Presenting Author(s): Fernando Pereira dos Santos
STN PLAD: A Dataset for Multi-Size Power Line Assets Detection in High-Resolution UAV Images
André Luiz Buarque Vieira-e-Silva (Universidade Federal de Pernambuco), Heitor de Castro Felix (Universidade Federal de Pernambuco), Thiago de Menezes Chaves (Universidade Federal de Pernambuco), Francisco, Paulo Magalhães Simões (Universidade Federal Rural de Pernambuco), Veronica Teichrieb, Michel Mozinho dos Santos (In Forma Software), Hemir da Cunha Santiago (In Forma Software), Virginia Adélia Cordeiro Sgotti (In Forma Software), and Henrique Baptista Duffles Teixeira Lott Neto (Sistema de Transmissão Nordeste)
Presenting Author(s): André Luiz Buarque Vieira-e-Silva
Semi-supervised Siamese Network Using Self-supervision Under Scarce Annotation improves Class Separability and Robustness to Attack
Gabriel B. Cavallari (Universidade de São Paulo) and Moacir A. Ponti (Universidade de São Paulo)
Presenting Author(s): Gabriel B. Cavallari
BRCars: a Dataset for Fine-Grained Classification of Car Images
Daniel M. Kuhn (Universidade Federal do Rio Grande do Sul), and Viviane P. Moreira (Universidade Federal do Rio Grande do Sul)
Presenting Author(s): Daniel M. Kuhn

TS7 - Computer Vision & Applications

October 21st (Thu)  |  13:30 to 14:30 BRT
Session Chair: David Menotti (UFPR, Brazil)

Click on the icon to access each paper's preprint.
Click on the icon to access each paper's pre-recorded video presentation.

A Generative Approach for Face Mask Removal Using Audio and Appearance
Luiz E. L. Coelho (Universidade Federal de Minas Gerais), Raphael Prates (Universidade Federal de Minas Gerais), and William Robson Schwartz (Universidade Federal de Minas Gerais)
Presenting Author(s): Luiz E. L. Coelho
Bias and Fairness in Face Detection
Hanna F. Menezes (Universidade Federal de Campina Grande), Arthur S. C. Ferreira (Universidade Federal de Campina Grande), Eanes T. Pereira (Universidade Federal de Campina Grande), and Herman M. Gomes (Universidade Federal de Campina Grande)
Presenting Author(s): Hanna F. Menezes, Arthur S. C. Ferreira
SGAT: Semantic Graph Attention for 3D Human Pose Estimation
Luiz Schirmer (Pontifícia Universidade Católica do Rio de Janeiro), Djalma Lucio (Pontifícia Universidade Católica do Rio de Janeiro), Leandro Cruz (University of Coimbra), Alberto Raposo (Pontifícia Universidade Católica do Rio de Janeiro), Luiz Velho (Instituto de Matemática Pura e Aplicada), and Hélio Lopes (Pontifícia Universidade Católica do Rio de Janeiro)
Presenting Author(s): Luiz Schirmer, Luiz Velho
TVAnet: a spatial and feature-based attention model for self-driving car
Victor Flores-Benites (Universidad Católica San Pablo), Carlos A. Mugruza-Vassallo (Universidad Nacional Tecnológica de Lima Sur), Rensso Mora-Colque (Universidad Católica San Pablo)
Presenting Author(s): Victor Flores-Benites
A Vision-based Solution for Track Misalignment Detection
Koteswar Rao Jerripothula (Indraprastha Institute of Information Technology Delhi), Sharik Ali Ansari (College of Engineering Roorkee), and Rahul Nijhawan (University of Petroleum and Energy Studies)
Presenting Author(s): Koteswar Rao Jerripothula

TS8 - Remote Sensing

October 21st (Thu)  |  16:30 to 17:30 BRT
Session Chair: Gilson Costa (UERJ)

Click on the icon to access each paper's preprint.
Click on the icon to access each paper's pre-recorded video presentation.

ChessMix: Spatial Context Data Augmentation for Remote Sensing Semantic Segmentation
Matheus Barros Pereira (Universidade Federal de Minas Gerais) and Jefersson Alex dos Santos (Universidade Federal de Minas Gerais)
Presenting Author(s): Matheus Barros Pereira
Simplifying Horizon Picking Using Single-Class Semantic Segmentation Networks
Danilo Calhes (IBM), Felipe K. Kobayashi (Federal University of ABC), Andrea Britto Mattos (IBM Research), Maysa M. G. Macedo (IBM Research), and Dario A. B. Oliveira (IBM Research)
Presenting Author(s): Danilo Calhes, Maysa M. G. Macedo
Unsupervised Semantic Segmentation of Aerial Images with Application to UAV Localization [GRSL Track]
João Pedro Klock Ferreira (UFMG), Brayan Rene Acevedo Jaimes (UFMG), and Cristiano Leite Castro (UFMG)
Presenting Author(s): João Pedro Klock Ferreira
Open Set Semantic Segmentation For Multitemporal Crop Recognition [GRSL Track]
Jorge A. Chamorro Martinez (PUC-Rio), Hugo Oliveira (USP), Jefersson A. dos Santos (UFMG), and Raul Queiroz Feitosa (PUC-Rio)
Presenting Author(s): Jorge A. Chamorro Martinez, Hugo Oliveira
Poststack Seismic Data Compression Using a Generative Adversarial Network [GRSL Track]
Kevyn Swhants Ribeiro (UFJF), Ana Paula Schiavon (UFJF), João Paulo Navarro (NVIDIA), Marcelo Vieira (UFJF), Saulo Moraes Villela (UFJF), and Pedro Mário Cruz e Silva (NVIDIA)
Presenting Author(s): Kevyn Swhants Ribeiro

TS9 - Pattern Recognition & Applications

October 22nd (Fri)  |  13:30 to 14:45 BRT
Session Chair: João P. Papa (UNESP)

Click on the icon to access each paper's preprint.
Click on the icon to access each paper's pre-recorded video presentation.

An Egg Image Noise Model for Digital Visual Counting Processing
Carlos Alberto Ramirez Behaine (University of Passo Fundo) and Jaime S. Ide (Yale University)
Presenting Author(s): Carlos Alberto Ramirez Behaine
Combination of Optical Character Recognition Engines for Documents Containing Sparse Text and Alphanumeric Codes
Iago Lourenço Correa (Federal University of Rio Grande), Paulo Lilles Jorge Drews-Jr (Federal University of Rio Grande), and Ricardo Nagel Rodrigues (Federal University of Rio Grande)
Presenting Author(s): Paulo Lilles Jorge Drews-Jr
Entropic Laplacian Eigenmaps for Unsupervised Metric Learning
Alexandre L. M. Levada (Federal University of São Carlos) and Michel F. C. Haddad (Queen Mary University of London)
Presenting Author(s): Alexandre L. M. Levada
Performance Analysis of Chess Players Comparing Traditional and Novel Cognitive Perception Ranking Measures
Laercio Silva Junior (Centro Universitário FEI), Wilson da Silva (Centro Universitário UniDomBosco), and Carlos Thomaz (Centro Universitário FEI)
Presenting Author(s): Laercio Silva Junior
An Offline Writer-Independent Signature Verification Method with Robustness Against Scalings and Rotations
Felix Eduardo Huaroto Pachas (Universidade Federal do Rio Grande do Sul) and Eduardo S. L. Gastal (Universidade Federal do Rio Grande do Sul)
Presenting Author(s): Felix Eduardo Huaroto Pachas
A Form Understanding Approach to Printed and Structured Engineering Documentation
Gabriel L. Santos (Universidade Federal do Rio Grande), Vanessa T. Silva (Universidade Federal do Rio Grande), Laura A. Dalmolin (Universidade Federal do Rio Grande), Ricardo N. Rodrigues (Universidade Federal do Rio Grande), Paulo L. J. Drews-Jr (Universidade Federal do Rio Grande), and Nelson L. Duarte Filho (Universidade Federal do Rio Grande)
Presenting Author(s): Vanessa T. Silva

TS10 - Segmentation, Features & Classification

October 22nd (Fri)  |  15:00 to 16:00 BRT
Session Chair: Nina Hirata (IME-USP)

Click on the icon to access each paper's preprint.
Click on the icon to access each paper's pre-recorded video presentation.

Descriptive Image Gradient from Edge-Weighted Image Graph and Random Forests
Raquel Almeida (PUC Minas), Zenilton K. G. Patrocínio Jr. (PUC Minas), Arnaldo de A. Araújo (Universidade Federal de Minas Gerais), Ewa Kijak (Université de Rennes 1), Simon Malinowski (Université de Rennes 1), and Silvio Jamil F. Guimarães (PUC Minas)
Presenting Author(s): Raquel Almeida
Towards a Simple and Efficient Object-based Superpixel Delineation Framework
Felipe C. Belém (University of Campinas), Benjamin Perret (Université Gustave Eiffel), Jean Cousty (Université Gustave Eiffel), Silvio J. F. Guimarães (Pontifical Catholic University of Minas Gerais), and Alexandre X. Falcão (University of Campinas)
Presenting Author(s): Felipe C. Belém
New Hierarchy-based Segmentation Layer: towards automatic marker proposal
Gabriel Barbosa da Fonseca (Pontifícia Universidade Católica de Minas Gerais), Romain Negrel (Université Gustave Eiffel), Benjamin Perret (Université Gustave Eiffel), Jean Cousty (Université Gustave Eiffel), and Silvio Jamil F. Guimarães (Pontifícia Universidade Católica de Minas Gerais)
Presenting Author(s): Gabriel Barbosa da Fonseca
Domain Adaptation for Holistic Skin Detection
Aloisio Dourado (Universidade de Brasília), Frederico Guth (Universidade de Brasília), Teofilo de Campos (Universidade de Brasília), and Li Weigang (Universidade de Brasília)
Presenting Author(s): Frederico Guth
A Deep Learning-based Approach for Tree Trunk Segmentation
Danilo Samuel Jodas (São Paulo State University), Sergio Brazolin (University of São Paulo), Takashi Yojo (University of São Paulo), Reinaldo Araujo de Lima (University of São Paulo), Giuliana Del Nero Velasco (University of São Paulo), Aline Ribeiro Machado (University of São Paulo), and João Paulo Papa (São Paulo State University)
Presenting Author(s): Danilo Samuel Jodas

TS11 - Neural Networks & Classifiers

October 22nd (Fri)  |  16:30 to 17:45 BRT
Session Chair: Moacir Ponti (ICMC-USP)

Click on the icon to access each paper's preprint.
Click on the icon to access each paper's pre-recorded video presentation.

Enhancing Shallow Neural Networks Through Fourier-based Information Fusion for Stroke Classification
Mateus Roder (Universidade Estadual Paulista), Gustavo Henrique Rosa (Universidade Estadual Paulista), João Paulo Papa (Universidade Estadual Paulista), and Daniel Carlos Guimarães Pedronette (Universidade Estadual Paulista)
Presenting Author(s): Mateus Roder
ConformalLayers: A non-linear sequential neural network with associative layers
Eduardo Vera Sousa (Universidade Federal Fluminense), Leandro A. F. Fernandes (Universidade Federal Fluminense), and Cristina Nader Vasconcelos (Universidade Federal Fluminense)
Presenting Author(s): Eduardo Vera Sousa
A Convolutional Neural Network-based Mobile Application to Bedside Neonatal Pain Assessment
Lucas P. Carlini (University Center of FEI), Leonardo A. Ferreira (University Center of FEI), Gabriel A. S. Coutrin (University Center of FEI), Victor V. Varoto (University Center of FEI), Tatiany M. Heiderich (University Center of FEI), Rita C. X. Balda (Federal University of São Paulo), Marina C. M. Barros (Federal University of São Paulo), Ruth Guinsburg (Federal University of São Paulo), and Carlos E. Thomaz (University Center of FEI)
Presenting Author(s): Lucas P. Carlini
One-Class Classifiers for Novelties Detection in Electrical Submersible Pumps
Gabriel Soares Baptista (Universidade Federal do Espírito Santo), Lucas Henrique Sousa Mello (Universidade Federal do Espírito Santo), Thiago Oliveira-Santos (Universidade Federal do Espírito Santo), Flávio Miguel Varejão (Universidade Federal do Espírito Santo), Marcos Pellegrini Ribeiro (CENPES/Petrobras), and Alexandre Loureiros Rodrigues (Universidade Federal do Espírito Santo)
Presenting Author(s): Lucas Henrique Sousa Mello, Gabriel Soares Baptista
GCOOD: A Generic Coupled Out-of-Distribution Detector for Robust Classification
Rogério Ferreira de Moraes (Universidade Federal Fluminense), Raphael dos S. Evangelista (Universidade Federal Fluminense), Leandro A. F. Fernandes (Universidade Federal Fluminense), and Luis Martí (Inria Chile Research Center)
Presenting Author(s): Rogério Ferreira de Moraes
Representation Learning for Image Retrieval through 3D CNN and Manifold Ranking
Lucas Barbosa de Almeida (São Paulo State University), Vanessa Helena Pereira-Ferrero (São Paulo State University), Lucas Pascotti Valem (São Paulo State University), Jurandy Almeida (Federal University of São Paulo), and Daniel Carlos Guimarães Pedronette (São Paulo State University)
Presenting Author(s): Lucas Barbosa de Almeida

SIBGRAPI 2021 Workshops

WTD - Workshop of Theses and Dissertations

October 20th (Wed)  |  16:30 to 19:30 BRT
Chairs: Antonio Lopes Apolinario Junior (UFBA) and João Paulo Papa (UNESP)

This session will occur in the SIBGRAPI 2021 Discord server.
(invitation link sent to all registered SIBGRAPI attendees.)

Click on the icon to access each paper's preprint.
Click on the icon to access each paper's pre-recorded video presentation.

A Novel Human-Machine Hybrid Framework for Person Re-Identification from Full Frame Videos
Felix Oliver S Huayta (Universidade Federal Fluminense), Joris Guerin (Université de Toulouse), and Esteban Clua (Universidade Federal Fluminense)
Presenting Author(s): Felix Oliver Sumari Huayta
Advances in subspace learning and its applications (click here for the full thesis/dissertation text)
Bernardo B. Gatto (Center for Artificial Intelligence Research (C-AIR)), Kazuhiro Fukui (University of Tsukuba), Waldir da Silva Junior ( Federal University of Amazonas), and Eulanda M. dos Santos (Federal University of Amazonas)
Presenting Author(s): Bernardo Bentes Gatto
Breast Tomosynthesis Reconstruction Using Artificial Neural Networks with Deep Learning (click here for the full thesis/dissertation text)
Davi de Paula (Unesp), and Denis Salvadeo (UNESP)
Presenting Author(s): Davi Duarte de Paula
Computing Vessel Velocity from Single Perspective Projection Images (click here for the full thesis/dissertation text)
Jose L Huillca Mango (UFF), and Leandro A. F. Fernandes (Universidade Federal Fluminense)
Presenting Author(s): Jose Luis Huillca Mango
Dealing with Imbalanceness in Hierarchical Classification Problems Through Data Resampling (click here for the full thesis/dissertation text)
Rodolfo Miranda Pereira (Pontifical Catholic University of Parana), Yandre Costa (State University of Maringa), and Carlos N Silla (Pontifical Catholic University of Parana (PUCPR))
Presenting Author(s): Rodolfo Miranda Pereira
Exploring ERP Distortions to Reduce the Encoding Time of 360 Videos (click here for the full thesis/dissertation text)
Iago C Storch (Federal University of Rio Grande do Sul), Luciano Volcan Agostini (UFPel - Federal University of Pelotas), Bruno Zatt (Federal University of Pelotas), and Daniel Palomino (Federal University of Pelotas)
Presenting Author(s): Iago Storch
ForestEyes Project - Citizen Science and Machine Learning to detect deforested areas in tropical forests (click here for the full thesis/dissertation text)
Fernanda Dallaqua (UNIFESP), Fabio Faria (Federal University of Sao Paulo), and Álvaro Luiz Fazenda (UNIFESP)
Presenting Author(s): Fernanda Beatriz Jordan Rojas Dallaqua
KutralNext: An Efficient Multi-label Fire and Smoke Image Recognition Model
Angel Ayala (Universidade de Pernambuco), David Macêdo (Federal University of Pernambuco), Cleber Zanchettin (Federal University of Pernambuco ), Francisco Cruz (Deakin University), and Bruno Fernandes (Universidade de Pernambuco)
Presenting Author(s): Angel Ayala
Methods for segmentation of spinal cord and esophagus in radiotherapy planning computed tomography (click here for the full thesis/dissertation text)
João Otávio Bandeira Diniz (Federal Institute of Maranhão), Aristófanes Silva (Federal University of Maranhão), and Anselmo Paiva (Federal University of Maranhão )
Presenting Author(s): João Otávio Bandeira Diniz
On periodic tilings with regular polygons (click here for the full thesis/dissertation text)
José Ezequiel Soto Sánchez (IMPA, Brazil), Asla Medeiros e Sá (FGV / EMAp), and Luiz Henrique de Figueiredo (IMPA)
Presenting Author(s): José Ezequiel Soto Sánchez
Partial Least Squares: A Deep Space Odyssey
Artur Jordão L Correia (University of Campinas), and William R Schwartz (Federal University of Minas Gerais)
Presenting Author(s): Artur Jordão Lima Correia
Real-Time Frequency Adjustment of Images and Videos (click here for the full thesis/dissertation text)
Rafael L Germano (Federal University of Rio Grande do Sul), and Eduardo S. L. Gastal (UFRGS)
Presenting Author(s): Rafael Lucena Germano
Scene Classification using a Combination of Aerial and Ground Images (click here for the full thesis/dissertation text)
Gabriel Machado (UFMG), Jefersson A dos Santos (UFMG), and Keiller Nogueira (UFMG)
Presenting Author(s): Gabriel Lucas Silva Machado
Screen-Space Virtual Point Light propagation for Real-Time Global Illumination (click here for the full thesis/dissertation text)
Vitor M Aranha (UFBA), Márcio C. F. Macedo (UFBA), and Antônio L. Apolinário Jr. (UFBA)
Presenting Author(s): Vitor Moraes Aranha
Semantic Segmentation with Multi-Source Domain Adaptation for Radiological Images (click here for the full thesis/dissertation text)
Hugo N Oliveira (University of São Paulo), Arnaldo de Albuquerque Araujo (Federal University of Minas Gerais, Brasil"), and Jefersson A dos Santos (UFMG)
Presenting Author(s): Hugo Neves de Oliveira
Semantic graph attention networks and tensor decompositions for computer vision and computer graphics (click here for the full thesis/dissertation text)
Luiz Schirmer (PUC-Rio), Luiz Velho (IMPA), and Hélio Lopes (Pontifícia Universidade Católica do Rio de Janeiro )
Presenting Author(s): Luiz Schirmer
Semi-automatic Segmentation of Skin Lesions based on Superpixels and Hybrid Texture Information (click here for the full thesis/dissertation text)
Elineide Santos (Federal University from Piauí), and Rodrigo Veras (Federal University from Piauí)
Presenting Author(s): Elineide Silva dos Santos
Synthesizing Realistic Human Dance Motions Conditioned by Musical Data using Graph Convolutional Networks
João Ferreira (Universidade Federal de Minas Gerais), Renato Martins (INRIA), and Erickson R. Nascimento (UFMG)
Presenting Author(s): João Pedro
Targets Detection Using Multiple Foveas (click here for the full thesis/dissertation text)
Petrucio R. T. Medeiros (Federal University of Rio Grande do Norte), Rafael Gomes (Federal University of Rio Grande do Norte), and Luiz M.G. Goncalves (UFRN)
Presenting Author(s): Petrúcio Medeiros
Unsupervised Brain Anomaly Detection in MR Images (click here for the full thesis/dissertation text)
Samuel Botter Martins (University of Campinas), Alexandru Telea (Utrecht University), and Alexandre Xavier Falcao (IC-UNICAMP)
Presenting Author(s): Samuel Botter Martins
Visual Rhythm-based Convolutional Neural Networks and Adaptive Fusion for a Multi-stream Architecture Applied to Human Action Recognition (click here for the full thesis/dissertation text)
Helena Almeida Maia (Unicamp), Marcelo Bernardes Vieira (UFJF), and Helio Pedrini (Institute of Computing - UNICAMP)
Presenting Author(s): Helena de Almeida Maia

WUW - Workshop of Undergraduate Works

October 20th (Wed)  |  16:30 to 19:30 BRT
Chairs: Paulo Pagliosa (UFMS) and Thiago Oliveira dos Santos (UFES)

This session will occur in the SIBGRAPI 2021 Discord server.
(invitation link sent to all registered SIBGRAPI attendees.)

Click on the icon to access each paper's preprint.
Click on the icon to access each paper's pre-recorded video presentation.

A Comparative Study of Text Document Representation Approaches Using Point Placement-based Visualizations
Hevelyn L Carvalho (Universidade de Brasília), and Vinicius R. P. Borges (UnB)
Presenting Author(s): Hevelyn Sthefany Lima de Carvalho
Classificando Modelos de Implantes Dentários Usando Redes Neurais Convolucionais com Dados Sintetizados
Henrique A Louzada (PUC Minas), and Maria Inês Lage Paula (PUC Minas)
Presenting Author(s): Henrique Almeida Louzada
Coffee Leaf Diseases Identification and Severity Classification using Deep Learning
Eduardo A L Lisboa (Universidade Federal de Alagoas), Givanildo Júnior (Universidade Federal de Alagoas), and Fabiane Queiroz (UFAL)
Presenting Author(s): Eduardo Antônio de Lucena Lisboa
Detecção de Fissuras utilizando Redes Neurais Convolucionais
Raianny P C Oliveira (Universidade Estadual do Oeste do Paraná), Valéria Santos (Fundação Parque Tecnológico Itaipu), Claudio Marquetto (Unioeste), and Fabiana Peres (Universidade Estadual do Oeste do Paraná)
Presenting Author(s): Raianny Proença
Detecção e Classificação de Objetos Presentes em Imagens Aéreas de Drones de Ambientes Urbanos
Fabiana Peres (Universidade Estadual do Oeste do Paraná), Guilherme Sganderla (Universidade Estadual do Oeste do Paraná), Claudio Marquetto (Unioeste), and Valéria Santos (Fundação Parque Tecnológico Itaipu)
Presenting Author(s): Guilherme Rodrigues Sganderla
Evaluating Loss Functions for Illustration Super-Resolution Neural Networks
Raphael Nepomuceno (Universidade Federal de Viçosa), and Michel M Silva (Universidade Federal de Viçosa)
Presenting Author(s): Raphael Nepomuceno
Improved Smart Eye Tracker Communicator Using Low Resolution Webcam
Allana L. dos S. Rocha (University of Pernambuco), Bruno Fernandes (Universidade de Pernambuco), and Leandro Silva (University of Pernambuco )
Presenting Author(s): Allana Lais dos Santos Rocha
The Use of an Augmented Reality Application to improve User Experience in Museums in São Luís - Maranhão
Gabriel Nogueira Berthier da Silva (IFMA), Daniel Gomes Jr (IFMA), Ivana Marcia Maia (IFMA), and Anselmo Paiva (Federal University of Maranhão )
Presenting Author(s): Gabriel Nogueira Berthier da Silva
Um Estudo Comparativo de Redes Convolucionais Profundas para Detecção de Insetos em Imagens
Jéssica Regina Di Domênico (Sul-rio-grandense Federal Institute of Education, Science and Technology (IFSUL)), Rafael Rieder ( Universidade de Passo Fundo), Douglas Lau (Empresa Brasileira de Pesquisa Agropecuária - Embrapa Trigo), Daniel Ribeiro (Sul-rio-grandense Federal Institute of Education, Science and Technology (IFSUL)), and Telmo De Cesaro Júnior (Sul-rio-grandense Federal Institute of Education, Science and Technology (IFSUL))
Presenting Author(s): Jéssica Regina e Telmo Júnior
Virtual lines for offside situations analysis in football
Karim F Lima (Universidade do Vale do Rio dos Sinos - Unisinos), Rodrigo Figueiredo (Unisinos), Eduardo Augusto Martins ( Universidade do Vale do Rio dos Sinos - Unisinos), and Jean Schmith ( Universidade do Vale do Rio dos Sinos - Unisinos)
Presenting Author(s): Karim Ferreira Lima

WiP - Workshop of Works in Progress

October 20th (Wed)  |  16:30 to 19:30 BRT
Chairs: Asla Medeiros e Sá (FGV Rio) and Thiago LT da Silveira (UFRGS)

This session will occur in the SIBGRAPI 2021 Discord server.
(invitation link sent to all registered SIBGRAPI attendees.)

Click on the icon to access each paper's preprint.
Click on the icon to access each paper's pre-recorded video presentation.

Aprendizado Profundo na Classificação de Lesões Crescentes Glomerulares: modelos e condições
Joacy M da Silva (Universidade Estadual de Feira de Santana), Michele F Angelo (UEFS), and Angelo C Loula (State University of Feira de Santana, UEFS)
Presenting Author(s): Joacy Mesquita da Silva
Automated Visual Inspection of Aircraft Exterior Using Deep Learning
Yuri DV Yasuda (Universidade Federal de Sao Paulo, Instituto de Ciencia e Tecnologia), Fabio Cappabianco (Universidade Federal de Sao Paulo, Instituto de Ciencia e Tecnologia), Luiz Martins (Universidade Federal de Sao Paulo, Instituto de Ciencia e Tecnologia), and Jorge Gripp (Autaza)
Presenting Author(s): Yuri Del Vigna Yasuda
Avaliação de Modelos de Detecção de Objetos para Detectar Glomérulos em Imagens Histológicas
Abel R Galvão (UEFS), Jonathan Rehem (UEFS), Washington Luis Conrado dos Santos (Fiocruz), Angelo Duarte (UEFS), Luciano Rebouças (UFBA), and Michele F Angelo (UEFS)
Presenting Author(s): Abel Ramalho Galvão
Estimativa dos Níveis de Obesidade com Base em Hábitos Alimentares e Condição Física Através de Técnicas de Aprendizado de Máquina
Leonardo F Lopes (IFCE), Adonias Caetano de Oliveira (IFCE), Rhyan Ximenes de Brito (IFCE - Campus Tianguá), Saulo Oliveira (IFCE), and Luiz Torres Raposo Neto (Instituto Federal do Ceará- Campus Tianguá)
Presenting Author(s): Leonardo Ferreira Lopes (autor principal para apresentação) / Adonias Caetano de Oliveira
Hearing glasses to visually impaired people prototype
Vinicius Mafra Viti (Universidade Federal do ABC), and Bruno Augusto Dorta Marques (CMCC - Universidade Federal do ABC)
Presenting Author(s): Vinícius Mafra Viti
PathoSpotter-Search: A Content-Based Image Retrieval Tool for Nephropathology
Ellen Aguiar (UEFS), Rodrigo Calumby (UEFS), Luciano Oliveira (UFBA), Washington dos-Santos (FIOCRUZ), and Angelo Duarte (UEFS)
Presenting Author(s): Ellen Chalegre Aguiar
Segmentation and graph generation of muzzle images for cattle identification
Lucas M Wojcik (UFPR), Jorge Junior (UFPR), David Menotti (Federal University of Paraná), and João Hill (Institute of Rural Development of Paraná)
Presenting Author(s): Lucas Matheus Leite Wojcik
Using images to avoid collisions and bypass obstacles in indoor environments
David S Medeiros (IFCE), Elias Teodoro da Silva Junior (IFCE), Thiago A Batista (IFCE), and Geraldo Luis Bezerra Ramalho (Instituto Federal do Ceará)
Presenting Author(s): David Silva de Medeiros

WIA - Workshop of Industry Applications

October 22nd (Fri)  |  8:45 to 12 noon BRT
Chairs: Emilio Vital Brazil (IBM) and Moacir A. Ponti (ICMC-USP)

Tentative schedule for WIA:
08:45 - 09:00
Opening
09:00 - 10:00
10:00 - 10:15
Break (15 min)
10:15 - 10:45
Paper presentations (10 min presentation + 5 min Q&A per paper)
10:45 - 11:45
11:45 - 12:00
Closing and announcements

Click on the icon to access each paper's preprint.
Click on the icon to access each paper's pre-recorded video presentation.

A Comparative Study of Methods based on Deep Neural Networks for Self-reading of Energy Consumption in a Chatbot Application Context
Carlos Rocha (Federal University of Maranhão), Pedro Carvalho (Federal University of Maranhão), Antonio Pinto (Federal University of Maranhão), Pedro Bernhard (Federal University of Maranhão), Ricardo Anchieta Júnior (Federal University of Maranhão), Ricardo Marques (Federal University of Maranhão), Italo F Silva (Federal University of Maranhão), Simara Rocha (Federal University of Maranhão), Aristófanes Silva (Federal University of Maranhão), Eliana Monteiro (Equatorial Energy), and Hugo Nogueira (Equatorial Energy)
Presenting Author(s): Italo Francyles Santos da Silva

WVIS - Workshop on Visual Analytics, Information Visualization and Scientific Visualization

October 18th (Mon)  |  14:15 to 18:30 BRT
Chairs: Carla Maria Dal Sasso Freitas (UFRGS), Celmar Guimarães da Silva (UNICAMP) and Marcos Lage (UFF)

Tentative schedule for WVIS:
14:15 - 14:30
Opening
14:30 - 15:30
15:30 - 17:30
Labs presentations session
17:30 - 18:25
Discussion on how to increase collaboration between groups
18:25 - 18:30
Closing

Click on the icon to access each paper's preprint.
Click on the icon to access each paper's pre-recorded video presentation.

DaVInt - Data Visualization and Interaction Lab
Isabel Harb Manssour, Milene Selbach Silveira (PUC-RS)
Visualization Research at the Software Engineering and Information Systems Laboratory (SEIS)
Celmar Guimarães da Silva (UNICAMP)
Visual Analytics Research at Universidade Federal do Ceará
Emanuele Santos, José F. de Queiroz Neto, George A. M. Gomes, Antonio José M. Leite Junior, Joaquim Bento Cavalcante Neto, Creto Augusto Vidal, Ticiana L. Coelho da Silva, Jose Antonio F. Macedo (UFC)
Visualization, Interaction and Simulation Lab — INF/UFRGS
Carla M.D.S. Freitas, Luciana Nedel and Anderson Maciel (UFRGS)
Visualization Research at Universidade Federal Fluminense
Marcos Lage (UFF)
Visualization Research at ExACTa — PUC-Rio
Helio Lopes (PUC-Rio)
Visual Data Science Laboratory — FGV
Jorge Poco (Fundação Getúlio Vargas)

Organized by

Sponsored by

Support by

In-Cooperation with