Start | End | 28/10 - Mon | 29/10 - Tue | 30/10 - Wed | 31/10 - Thu | ||||||||||||
8:00 | 8:30 | Registration | Registration | Registration | Registration | ||||||||||||
8:30 | 8:45 | Opening Session Room 201 | |||||||||||||||
8:45 | 9:00 | ||||||||||||||||
9:00 | 9:15 | Room 208 | Room 209 | Room 210 | Room 208 | Room 210 | Room 208 | Room 210 | |||||||||
9:15 | 9:30 | ||||||||||||||||
9:30 | 9:45 | Room 201 | NVIDIA Room 201 | ||||||||||||||
9:45 | 10:00 | ||||||||||||||||
10:00 | 10:15 | ||||||||||||||||
10:15 | 10:30 | ||||||||||||||||
10:30 | 10:45 | ||||||||||||||||
10:45 | 11:00 | Coffee Break | Coffee Break | Coffee Break | |||||||||||||
11:00 | 11:15 | Room 208 | Room 209 | Room 210 | Coffee Break | Room 201 | Room 201 | ||||||||||
11:15 | 11:30 | Room 208 | Room 210 | ||||||||||||||
11:30 | 11:45 | ||||||||||||||||
11:45 | 12:00 | ||||||||||||||||
12:00 | 12:15 | ||||||||||||||||
12:15 | 12:30 | ||||||||||||||||
12:30 | 12:45 | Lunch | Lunch | Lunch | Lunch | ||||||||||||
12:45 | 13:00 | ||||||||||||||||
13:00 | 13:15 | ||||||||||||||||
13:15 | 13:30 | ||||||||||||||||
13:30 | 13:45 | ||||||||||||||||
13:45 | 14:00 | Room 208 | Room 209 | Room 210 | Room 201 | Room 201 | Room 208 | Room 210 | |||||||||
14:00 | 14:15 | ||||||||||||||||
14:15 | 14:30 | ||||||||||||||||
14:30 | 14:45 | ||||||||||||||||
14:45 | 15:00 | ||||||||||||||||
15:00 | 15:15 | ||||||||||||||||
15:15 | 15:30 | Coffee Break | Coffee Break | Coffee Break | Coffee Break | ||||||||||||
15:30 | 15:45 | ||||||||||||||||
15:45 | 16:00 | Room 208 | Room 209 | Room 210 | Room 208 | Room 210 | Room 201 | Room 208 | Room 210 | ||||||||
16:00 | 16:15 | ||||||||||||||||
16:15 | 16:30 | ||||||||||||||||
16:30 | 16:45 | Break | |||||||||||||||
16:45 | 17:00 | ||||||||||||||||
17:00 | 17:15 | ||||||||||||||||
17:15 | 17:30 | ||||||||||||||||
17:30 | 17:45 | Room 201 | Room 201 | Closing Session Room 208 | |||||||||||||
17:45 | 18:00 | ||||||||||||||||
18:00 | 18:15 | ||||||||||||||||
18:15 | 18:30 | ||||||||||||||||
18:30 | 18:45 | ||||||||||||||||
18:45 | 19:00 | ||||||||||||||||
19:00 | 19:15 | CEGRAPI Room 204-A | CEGRAPI Room 204-A | ||||||||||||||
19:15 | 19:30 | ||||||||||||||||
19:30 | 19:45 | ||||||||||||||||
19:45 | 20:00 | ||||||||||||||||
20:00 | 20:15 | ||||||||||||||||
20:15 | 20:30 | ||||||||||||||||
20:30 | 20:45 | ||||||||||||||||
20:45 | 21:00 | ||||||||||||||||
21:00 | 21:15 | ||||||||||||||||
21:15 | 21:30 | ||||||||||||||||
21:30 | 21:45 | ||||||||||||||||
21:45 | 22:00 | ||||||||||||||||
22:00 | 22:15 | ||||||||||||||||
22:15 | 22:30 | ||||||||||||||||
22:30 | 22:45 | ||||||||||||||||
22:45 | 23:00 | ||||||||||||||||
Session | Title | Authors |
Tutorial T1 @Location: Room 208 | Deep Learning for Computer Vision in GPUs: an introductory hands-on tutorial | Marcelo Pias (FURG); Silvia Botelho (FURG); Paulo Drews-Jr (FURG) |
Tutorial T2 @Location: Room 209 | Milestones and New Frontiers in Deep Learning | Ygor Rebouças Serpa (UNIFOR); Leonardo Augusto Pires (UNIFOR); Maria Andréia Formico Rodrigues (UNIFOR); |
Tutorial T3 @Location: Room 209 | Hands-On Transfer Learning with Keras | Ricardo Ribani (Mackenzie); Mauricio Marengoni (Mackenzie) |
Tutorial T4 @Location: Room 210 | A Hands-on Tutorial on Fast Forwarding First-Person Videos | Michel Silva (UFMG); Washington Ramos, Alan Neves (UFMG); Edson Araujo (UFMG); Mario Campos (UFMG); Erickson R. Nascimento (UFMG) |
WVIS @Location: Room 210 | Invited Talk Gabriel Zanlorenssi (Cientista de Dados, Nexo Jornal) Da tabela ao gráfico: fluxo de produção de gráficos em um jornal Abstract: Nesta palestra, Gabriel Zanlorenssi abordará o processo de produção de visualizações de dados no contexto do jornalismo. Da pauta, passando pela coleta, tratamento e construção dos gráficos. Ele também discutirá sobre ferramentas e boas práticas ao trabalhar com as visualizações. | Short Bio: Gabriel Zanlorenssi é cientista de dados do Nexo Jornal, onde trabalha com análise e visualização de dados. É professor convidado de análise e visualização de dados na Escola N e na Fundação Getúlio Vargas. Tem graduação em ciências sociais pela USP (Universidade de São Paulo) e atualmente cursa mestrado em ciência política na mesma universidade. |
Mesa Redonda Carla Dal Sasso Freitas (UFRGS) Gabriel Zanlorenssi (Cientista de Dados,, Nexo Jornal) Júlia Giannella (Visgraf, IMPA) Tema: O futuro da visualização no Brasil | Short Bios: Carla Dal Sasso Freitas é professora titular e diretora do Instituto de Informática da Universidade Federal do Rio Grande do Sul (UFRGS). Ela é doutora em Ciência da Computação pela UFRGS (1994) e seus interesses de pesquisa atuais são visualização de dados, interação humano-computador e visualização analítica imersiva. Gabriel Zanlorenssi é cientista de dados do Nexo Jornal, onde trabalha com análise e visualização de dados. É professor convidado de análise Júlia Giannella é designer e pesquisadora interessada na interseção entre design, visualização de dados e gestão do conhecimento. Atualmente é assistente de pesquisa no Laboratório Visgraf, do IMPA, e doutoranda em Design e Tecnologia na ESDI-UERJ. Em 2019, fundou o projeto Dataviz.Rio no qual atua como curadora de meetups, palestrante, facilitadora e professora na área de dataviz. |
Keynote Location: Room 201 | Ken Perlin(NYU, USA) The Dawning of the Experience Economy Abstract: As technology advances, socially shared virtual reality will soon transition from an exotic novelty to an integral part of our everyday lives. This will lead to a fundamental shift not only in entertainment and culture, but also in patterns of cooperative work and employment and ultimately, the nature of society itself. We examine the history, current state and future implications of this profound change, as we prepare to fully enter the age of the experience economy. Short Bio: Ken Perlin, a professor in the Department of Computer Science at New York University, directs the Future Reality Lab, and is a participating faculty member at NYU MAGNET. His research interests include future reality, graphics and animation, user interfaces and education. He is chief scientist at Parallux, Tactonic Technologies and Autotoon, and is an advisor for High Fidelity. He received an Academy Award for Technical Achievement from the Academy of Motion Picture Arts and Sciences for his noise and turbulence procedural texturing techniques, which are widely used in feature films and television, as well as membership in the ACM/SIGGRAPH Academy, the 2008 ACM/SIGGRAPH Computer Graphics Achievement Award, the TrapCode award for achievement in computer graphics research, the NYC Mayor's award for excellence in Science and Technology and the Sokol award for outstanding Science faculty at NYU, and a Presidential Young Investigator Award from the National Science Foundation. He serves on the Advisory Board for the Centre for Digital Media at GNWC. Previously he served on the program committee of the AAAS, was external examiner for the Interactive Digital Media program at Trinity College. general chair of the UIST2010 conference, directed the NYU Center for Advanced Technology and Games for Learning Institute, and has been a featured artist at the Whitney Museum of American Art. He received his Ph.D. in Computer Science from NYU, and a B.A. in theoretical mathematics from Harvard. Before working at NYU he was Head of Software Development at R/GREENBERG Associates in New York, NY. Prior to that he was the System Architect for computer generated animation at MAGI, where he worked on TRON. @ | ||
Session | Title | Authors |
TS1: Action and Video Recognition @Location: Room 208 Chair: Claudio Jung | Video Segmentation Learning Using Cascade Residual Convolutional Neural Network | Daniel Felipe S Santos (Sao Paulo State University)*; Rafael Gonçalves Pires (Department of Computing São Paulo State University); Danilo Colombo (Cenpes/Petroleo Brasileiro S.A. - Petrobras); Joao Papa (Sao Paulo State University) |
Fight Detection in Video Sequences Based on Multi-Stream Convolutional Neural Networks | Sarah Carneiro (Institute of Computing - UNICAMP)*; Gabriel Silva (Semantix Brasil); Silvio Guimaraes (PUC Minas); Helio Pedrini (Institute of Computing - UNICAMP) | |
Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference Joints | Carlos A Caetano (Universidade Federal de Minas Gerais - UFMG)*; Francois Bremond (Inria Sophia Antipolis, France); William R Schwartz (Federal University of Minas Gerais) | |
CV-C3D: Action Recognition on Compressed Videos with Convolutional 3D Networks | Samuel Felipe dos Santos (UNIFESP); Nicu Sebe (University of Trento); Jurandy Almeida (UNIFESP)* | |
TS2:Visualization Techniques and Applications @Location: Room 210 Chair: Emanuele Santos | [CAG] OMiCroN - Oblique Multipass Hierarchy Creation while Navigating | Vinícius da Silva (IMPA); Ricardo Marroquim (Delft University of Technology); Claudio Esperança (Federal Univeristy of Rio de Janeiro) |
Generating audiovisual summaries from literary works using emotion analysis | Daniela Milon (Universidad Catolica San Pablo); Jose Ochoa Luna (Universidad Catolica San Pablo); Erick Gomez Nieto (Universidad Catolica San Pablo) | |
eSTIMe: Towards an All-in-One Geovisualization Environment for Daily Mobility Analysis | Aline Menin (Univ. Grenoble Alpes); Paule-Annick Davoine (Univ. Grenoble Alpes); Sonia Chardonnel (Univ. Grenoble Alpes); Luciana Nedel (UFRGS) | |
[CAG] Visual Exploration of an Ensemble of Classifiers | Paula Ceccon Ribeiro (PUC-Rio); Helio Lopes (PUC-Rio); Guilherme G Schardong (PUC-Rio); Simone D. J. Barbosa (PUC-Rio); Clarisse Sieckenius de Souza (PUC-Rio) |
Keynote Location: Room 201 | Jurriaan van Rijswijk(Games for Health Europe Foundation) What if games become medicine. Abstract:. Transformation is global. We shift towards a purpose economy. The central theme for the economies will be about the impact it has on peoples’ lives instead on how profitable they are. Since a mayor component of our economies is about lifestyle interventions what better instrument for behaviour change can we use than games? People are intrinsically motivated for it and games do change behaviour. Jurriaan shares the vision of using games in all sectors with proven cases, research and benchmarks. Short Bio: Jurriaan van Rijswijk is founder and chairman of the Games for Health Europe Foundation. He is an entrepreneur and serious game designer for 24 years and won the ICT Personality of the Year Award in the Netherlands. He develops game strategies and designs behavior change interventions using clinically and scientifically-validated games – for which he has also won various awards. Games for Health Europe Foundation is the worldwide co-creation network for research, development and implementation of games within the health ecosystem. . @ | ||
Session | Title | Authors |
TS3: Biomedical Image Analysis @Location: Room 208 Chair: Leandro A. F. Fernandes | Acquisition of digital images and identification of Aedes aegypti mosquito eggs using classification and deep learning. | Pedro Saint Garcia (UFOP); Rafael Martins (UFOP); George Coelho (UFOP); Guillermo Camara-Chavez (UFOP)* |
Low-Dose CT Dental Image Denoising by Morphological Operators and 3D Filtering | Romulo Marconato Stringhini (Federal University of Santa Maria)*; Daniel Welfer (UNIVERSIDADE FEDERAL DE SANTA MARIA); Daniel Fernando Tello Gamarra (Federal University of Santa Maria); Marcos Cordeiro d'Ornellas (Federal University of Santa Maria) | |
Long-Range Decoder Skip Connections: Exploiting Multi-Context Information for Cardiac Image Segmentation | Nicolas Gutierrez (San Pablo Catholic University) Ricardo da Silva Torres (University of Campinas) Alexandre Xavier Falcao (University of Campinas) Sebastian Kozerke (ETH Zurich) Jürg Schwitter (Lausanne University) Pier-Giorgio Masci (King’s College London) Javier Montoya (ETH Zurich) | |
CAD System for Breast US Images with Speckle Noise Removal and Bio-inspired Segmentation | Paulo Sergio S Rodrigues (FEI); Guilherme Wachs (FEI University); Gilson Giraldi (National Laboratory for Scientific Computing)*; Celia AZ Barcelos (Federal University of Uberlândia); Luciana Vieira (UFU); Denise Guliato (UFU); Bikesh Singh (National Institute of Technology) | |
Fast and smart segmentation of paraspinal muscles in magnetic resonance imaging with CleverSeg | Jonathan da Silva Ramos (University of São Paulo)*; Mirela Cazzolato (University of São Paulo); Bruno Faiçal (University of São Paulo); Oscar Cuadros (University of São Paulo); Marcello Nogueira-Barbosa (Universidade de São Paulo); Caetano Traina Jr. (USP); Agma J Traina ((ICMC-USP)) | |
TS4:Visualization@Location: Room 210 Chair: Asla Sá | Comparing the effectiveness of visualizations of different data distributions | Ariane MB Rodrigues (PUC-Rio); Gabriel Barbosa (PUC-Rio); Hélio Lopes (Pontifícia Universidade Católica do Rio de Janeiro); Simone DJ Barbosa (PUC-Rio, Brazil) |
[CAG] A Scalable Node Ordering Strategy Based on Community Structure for Enhanced Temporal Network Visualization | Claudio Linhares (Federal University of Uberlândia); Fabiola S Pereira (Federal University of Uberlândia); Luis E Rocha (University of Greenwich); Jose Gustavo S Paiva (Federal University of Uberlândia); Jean R Ponciano (Federal University of Uberlândia); Bruno A Travençolo (Federal University of Uberlândia) | |
[CAG] A novel visual approach for enhanced attribute analysis and selection | Erasmo Artur Silva (University of São Paulo); Rosane Minghim (University of São Paulo) | |
[CAG] How do Soccer Teams Coordinate Consecutive Passes? A Visual Analytics System for Analysing the Complexity of Passing Sequences Using Soccer Flow Motifs. | João Luiz Dihl Comba (Federal University of Rio Grande do Sul); Rafael Garcia (Federal University of Rio Grande do Sul); Jose Luis Sotomayor Malqui (Google); Hande Alemdar (Middle East Technical University ); Noemí Maritza Lapa Romero (Federal University of Rio Grande do Sul) | |
Robust and effective method for automatic generation of one-dimensional transfer functions | Rustam Mesquita (Tecgraf/PUC-Rio); Waldemar Celes (PUC-Rio) | |
[CAG] Interactive directional ambient occlusion and shadow computations for volume ray casting | Leonardo Quatrin Quatrin Campagnolo (PUC-Rio); Waldemar Celes (PUC-Rio) |
Keynote Location: Room 201 | João P. Barreto(UC, Portugal) Computer Vision for Computer-Aided Surgery Abstract: Arthroscopy is a modality of orthopeadic surgery where instruments and endoscopic camera (the arthroscope) are inserted into the articular cavity through small incisions (the surgical ports). Arthroscopy is highly beneficial for the patient and healthcare system because it reduces trauma, risk of infection and recovery time. However, clinical execution is difficult to accomplish because of indirect visualization and limited manoeuvrability inside the joint, with novices having to undergo a long training period and experts making mistakes of clinical consequences. This is a scenario where surgical assistive technologies can have strong impact in improving clinical outcome and disseminating the benefits of minimally invasive surgery. This talk introduces Video-based Computer-Aided Arthroscopy (VCAA), which is the first effective concept for navigated arthroscopy. VCAA combines real-time video processing for accurate 3D measurements on the anatomy, with augmented reality for overlaying meaningful guidance information in images. We will discuss the cRoomenges in applying 3D computer vision to arthroscopic footage and the devised solutions that conducted to fully functional systems already tested in “ex-vivo” experiments. We will also see how video-based navigation can be extended to open orthopaedic surgery and overview on-going efforts in using deep-learning to accomplish surgical guidance without having to attach fiducial markers to anatomy. Short Bio: Joao P. Barreto holds a Ph.D. degree from the University of Coimbra (UC). He was visiting scholar in INRIA Rhone-Alpes, Grenoble, France, and a postdoctoral researcher in the University of Pennsylvania, Philadelphia, before joining the UC as a Professor. Joao is an acknowledged expert in 3D Computer Vision, being the author of more than 80 peer-reviewed articles in the most prestigious journals and conferences. He is the recipient of several academic distinctions and awards, including the “Google Faculty Research Award”, served as Area Chair in ECCV’2018 and ICCV2019, and is currently Associate Editor in the journals “Computer Vision and Image Understanding”, “Image and Vision Computing” and “Journal of Mathematical Image and Vision. Joao is also an entrepreneur having co-founded Perceive3D SA (P3D) in 2014. P3D builds in advanced knowledge in computer vision to provide advanced systems for improving visualization and guiding the surgeon during minimally invasive orthopedic procedures. Joao has been the CEO of P3D since foundation being responsible for R&D, Business Development and Investor Relations. The company has raised so far 1M€ in private capital and more than 2M€ in R&D grants having been awarded with the prestigious SMEi Phase 2 from the EU commission. @ | ||
Keynote Location: Room 201 | Filip Sadlo(UH, Germany) Flows and Features in Higher Dimensions Abstract: In this talk, we examine recent advances in the visualization of multidimensional and multivariate fields. One direction of research is the development of novel feature concepts to extract the essential structure of such data. Due to the intricacy and high dimensionality of the resulting features, as well as the spaces that contain them, a related field of research is concerned with their visual representation and interaction. We motivate and exemplify the utility of the techniques using problems from mathematics, physics, and Earth science, and discuss possible directions of future work. Short Bio: Filip Sadlo received his master’s and PhD degrees in computer science from ETH Zurich. Since 2014, he is a full professor of computer science at Heidelberg University, Germany, and the head of the Visual Computing Group. His research interests include visualization, computer graphics, and computational photography, with a focus on features and flows, physics, and simulation. He served on numerous program committees in the field, and as a co-chair for several conferences. @ | ||
Session | Title | Authors |
TS5: Image Processing @Location: Room 208 Chair: João Paulo Papa | Exploring hierarchy simplification for non-significant region removal | Isabela Borlido (PUC Minas); Gabriel B Fonseca (Pontifícia Universidade Católica de Minas Gerais); Zenilton Patrocinio Jr (PUC Minas); Jean Cousty (ESIEE); Benjamin Perret (ESIEE/PARIS); Laurent Najman (ESIEE); Yukiko Kenmochi (CNRS); Silvio Guimaraes (PUC Minas)* |
The Importance of Object-based Seed Sampling for Superpixel Segmentation | Felipe de Castro Belém (University of Campinas)*; Leonardo Melo (University of Campinas); Silvio Guimaraes (PUC Minas); Alexandre Xavier Falcao (IC-UNICAMP) | |
Solving Tangram Puzzles Using Raster-Based Mathematical Morphology | Fernanda M Yamada (Federal University of ABC)*; Joao Gois (UFABC); Harlen C Batagelo (UFABC) | |
Exploring Double Cross Cyclic Interpolation in Unpaired Image-to-Image Translation | Jorge Roberto López Cáceres (Catholic University San Pablo); Manasses A. Mauricio (Universidad Católica San Pablo)*; Guillermo Cámara (Universidade Federal de Ouro Preto) | |
[GRSL] Smoothing Tidal Effects in Well Test Pressure Data | Andrea Lins (PUC-Rio); Felipe de Oliveira (PUC-Rio); Abelardo Barreto (PUC-Rio); Marcos Craizer (PUC-Rio); Helio C. V. Lopes (PUC-Rio); Sinesio Pesco (PUC-Rio) | |
[GRSL] Level-set Formulation Based on an Infinite Series of Sample Moments for SAR Image Segmentation | Jeova Farias Sales Rocha Neto (Brown University); Alan Braga (UFC); Regis Marques (IFCE) ; Fátima Medeiros (UFC) | |
TS6: Geometry and Animation @Location: Room 210 Chair: Luiz Henrique de Figueiredo | GPU-based Visualization of Arbitrarily Complex Cutting Surfaces for Black Oil Reservoir Models | Bernardo Franceschin (Tecgraf/PUC-Rio); Frederico Abraham (Tecgraf/PUC-Rio); Luiz Felipe Netto (Tecgraf/PUC-Rio); Waldemar Celes (PUC-Rio) |
[CAG] A minimalistic approach for fast computation of geodesic distances on triangular meshes | Luciano Arnaldo Romero Calla (University of Zurich); Lizeth J Fuentes Perez (University of Zurich); Anselmo A Montenegro (Federal Fluminense University) | |
A partition approach to interpolate polygon sets for animation | Alexandre R. C. Ramos (Universidade Federal do Ceará); Emanuele M Santos (Federal University of Ceara); Joaquim Cavalcante-Neto (UFC) | |
Energy Embedded Gauss-Seidel Iteration for Soft Body Simulations | Ozan Cetinaslan (Universidade do Porto); Rafael Chaves (Federal University of Pará) | |
[CAG] Boundary particle resampling for surface reconstruction in liquid animation | Afonso Paiva (University of São Paulo); Nicolas Oe (University of São Paulo); Paulo Pagliosa (Federal University of Mato Grosso do Sul); Douglas Cedrim (University of São Paulo); Marcos Sandim (University of São Paulo) |
Keynote Location: Room 201 | Gilliard Lopes(Eletronic Arts, Canada) Who Makes Games ? Abstract: A journey across the past, present and future of game development through the lenses of some of its most unique and inspiring developers. Short Bio: Gilliard Lopes is a video games producer, designer and programmer with 20 years of experience in the industry. Born in Rio de Janeiro, Gilliard holds a BSc. in Computer Sciences from Universidade Federal Fluminense (UFF) and a MSc. in Computer Graphics from PUC-Rio. He was a partner at Paralelo Computação, a pioneering development studio of real-time rendering technology in Brazil, and has also worked as a producer at Hoplon Infotainment in Florianópolis. In 2008, Gilliard moved to Vancouver, Canada to work at Electronic Arts, where he is currently a game designer and producer in the FIFA series of football games. He also hosts a weekly podcast about game development called PodQuest. @ | ||
Session | Title | Authors |
WTD @ | Simulating Behavior Diversity in BioCrowds | Paulo Knob (Pontifical Catholic University of Rio Grande do Sul); Soraia Raupp Musse (Pontifical Catholic University of Rio Grande do Sul) |
Digital Video Stabilization: Algorithms and Evaluation | Marcos Roberto Souza (University of Campinas); Helio Pedrini (University of Campinas) | |
Unsupervised Selective Rank Fusion on Content-Based Image Retrieval | Lucas Pascotti Valem (UNESP); Daniel Carlos Guimarães Pedronette (UNESP) | |
Multimodal social scenario perception model for initial human-robot interaction | Diego Cardoso Alves (University of Campinas); Paula Dornhofer Paro Costa (University of Campinas) | |
Human Activity Recognition based on Wearable Sensors using Multiscale DCNN Ensemble | Jessica Sena (UFMG); William Robson Schwartz (UFMG) | |
Evaluation of machine learning applied to the realignment of hierarchies for image segmentation | Milena Menezes Adão (Pontifical Catholic University of Minas Gerais); Silvio Jamil F. Guimarães (Pontifical Catholic University of Minas Gerais); Zenilton K. G. Patrocı́nio Jr. (Pontifical Catholic University of Minas Gerais) | |
Multimodal person discovery using label propagation over speaking faces graphs | Gabriel Barbosa Fonseca (PUC Minas); Zenilton K. G. Patrocínio Jr (PUC Minas); Guillaume Gravier (CNRS, IRISA); Silvio Jamil F. Guimarães (PUC Minas) | |
On the Training Algorithms for Restricted Boltzmann Machines | Leandro Aparecido Passos (São Paulo State University); João Paulo Papa (São Paulo State University) | |
Visual Analytics via Graph Signal Processing | Alcebiades Dal Col (Federal University of Espı́rito Santo); Luis Gustavo Nonato (University of São Paulo) | |
Adaptive Face Tracking Based on Online Learning | Aasim Khurshid (UFRGS and SIDIA); Jacob Scharcanski (UFRGS) | |
FASTensor: A tensor framework for spatiotemporal description | Virgı́nia F. Mota (UFMG); Jefersson A. dos Santos (UFMG) ; Arnaldo de A. Araújo (UFMG) | |
A Collaborative Support for Recommending References in Papers | Orlando Fonseca Guilarte (PUC-Rio); Simone Diniz Junqueira Barbosa (PUC-Rio); Sinesio Pesco (PUC-Rio) | |
An Efficient Hierarchical Layered Graph Approach for Multi-Region Segmentation | Leissi M. Castañeda Leon (IME-USP); Krzysztof Chris Ciesielski (West Virginia University); Paulo A. Vechiatto Miranda (IME-USP) | |
Semantic Hyperlapse: a Sparse Coding-based and Multi-Importance Approach for First-Person Videos | Michel M. Silva (UFMG); Mario F. M. Campos (UFMG); Erickson R. Nascimento (UFMG) | |
Concomitant Hierarchy Construction and Rendering of Large Point Clouds | Vinı́cius Silva (IMPA); Ricardo Guerra Marroquim (UFRJ); Claudio Esperança (UFRJ) | |
Object segmentation by Oriented Image Foresting Transform with connectivity constraints | Lucy A. C. Mansilla (IME-USP); Paulo A. V. Miranda (IME-USP) | |
Matching People Across Surveillance Cameras | Raphael Prates (UFMG); William Robson Schwartz (UFMG) | |
Speckle Denoising With NL Filter and Stochastic Distances Under the Haar Wavelet Domain | Pedro A. A. Penna (UFSCar); Nelson D. A. Mascarenhas (UFSCar, UNIFACCAMP) | |
Emotion, Personality and Cultural Aspects in Crowds: towards a Geometrical Mind | Rodolfo Migon Favaretto (Pontifical Catholic University of Rio Grande do Sul); Soraia Raupp Musse (Pontifical Catholic University of Rio Grande do Sul) | |
A visual approach for user-guided feature fusion | Gladys M. Hilasaca (University of São Paulo ICMC-USP); Fernando V. Paulovich (University of São Paulo ICMC-USP) | |
WUW @ | Classificação da densidade mamária em mamografias utilizando redes neurais convolucionais | Marcos Felipe Vendramini Carvalho (PUC-Minas); Alexei Manso Correa Machado (UFMG) |
Detecção e Contagem do Pirarucu utilizando Técnicas de Visão Computacional | Wandelany Abreu (UFOPA); Deam Silva (UFOPA); Roberto Nascimento (UFOPA); Josivan Reis (UFOPA); Márcio Ponte (UFOPA) | |
An assault detection system based on human Pose Tracking for video surveillance | Pedro Gabriel Santos do Couto Soares (UFRPE); Arnaldo Barros da Silva (UFRPE); Luis Filipe Alves Pereira (UFRPE) | |
Multitemporal liver analysis for surgical plan and clinical follow-up, adapted for Sibgrapi 2019 | Rodrigo Braga dos Santos (UERJ); Guilherme Fontes dos Reis (UERJ); Gilson Alexandre Ostwald Pedro da Costa (UERJ) | |
Reconhecimento de Objetos em Linhas de Distribuição de Energia Utilizando IBM Cloud |
Raianny Proença de Camargo de Oliveira (FPTI, UNIOESTE); Valéria Nunes dos Santos (FPTI); Cláudio Roberto Marquetto Maurício (UNIOESTE) | |
Classificação de Imagens de Raio-x de Torax com Reconhecimento Visual da IBM Cloud para Diagnóstico de Pneumonia | Raianny Proença de Camargo de Oliveira (UNIOESTE); Guilherme Rodrigues Sganderla (UNIOESTE); Claudio Roberto Marquetto Maurício (UNIOESTE); Fabiana Frata Furlan Peres (UNIOESTE) | |
Tecnologia assistiva para reconhecimento de cartas de baralho utilizando aprendizado profundo | Samuel Alves dos Santos (IF Goiano); Allan Duque dos Santos (IF Goiano); Junio Cesar de Lima (IF Goiano); Fabrízzio Alphonsus Alves de Melo Nunes Soares (UFG); Gabriel da Silva Vieira (IF Goiano) | |
Hierarchy-of-Visual-Words: a Learning-based Approach for Trademark Image Retrieval | Vítor Lourenço (UFF); Gabriela Silva (UFF); Leandro Fernandes (UFF) | |
Multi-Lingual Text Localization via Language-Specific Convolutional Neural Networks | Jhonatas Santos de Jesus Conceição(UNICAMP); Allan Pinto (UNICAMP); Luis Decker, Jose Luis Flores Campana (UNICAMP); Manuel Cordova Neira (UNICAMP); Andreza A. dos Santos (UNICAMP); Helio Pedrini (UNICAMP); Ricardo Torres (NTNU, UNICAMP) | |
Use of reorderable matrices and heatmaps to support data analysis of students transcripts | Rafael Tavares Carvalho Barros (UNICAMP); Thiago Gonçalves Mendes (UNICAMP); Celmar Guimarães da Silva (UNICAMP) | |
WIP @ | Multiband image classification of astronomical objects | Ana Martinazzo (IME-USP); Nina Sumiko Tomita Hirata (IME-USP) |
Parametrização hierárquica de superfícies poligonais construída com triangulação de Delaunay restrita | Pablo Telles (PUC-Rio); Romildo Silva (UFC); Esdras Medeiros (UFC); Sinesio Pesco (PUC-Rio) | |
Normal Transformations for Overhang Reduction | Carlos Leal de Castro (UFSC); Leonardo Koller Sacht (UFSC) | |
Detecção de Desfolha de Soja Utilizando Redes Neurais Convolucionais |
Patrik Olã Bressan (IFMS); Wesley Nunes Gonçalves (UFMS) | |
An Approach to Classify Chronic Kidney Diseases using Scintigraphy Images | Elene Firmeza Ohata (IFCE); Francisco Hercules dos Santos Silva (IFCE); Shara Shami Araujo Alves (IFCE); Suane Pires Pinheiro da Silva (IFCE); Jefferson Silva Almeida (IFCE); Pedro Pedrosa Rebouças Filho (IFCE) | |
Development of Embedded Algorithm for Visual Simultaneous Localization and Mapping | Onias Silveira (IME); João de Melo (IME); Leandro Moreira (IME); Luiz Rodrigues (IMBEL); Paulo Rosa (IME) | |
Metodologia Adotada na Reconstrução 3D da Estação Saudade, em Ponta Grossa - PR | Matheus T Fratus (UTFPR); Mauren Louise Sguario Coelho de Andrade (UTFPR) | |
A New Strategy for Mobile Robots Localization based on Omnidirectional Sonar Images and Machine Learning | Jefferson Silva Almeida (IFCE); Elene Firmeza Ohata (IFCE); Suane Pires Pinheiro da Silva (IFCE); Francisco Hercules dos Santos Silva (IFCE); Pedro Henrique Feijó de Sousa (IFCE); Navar Medeiros M. Nascimento (IFCE); Pedro Pedrosa Rebouças Filho (IFCE) | |
Object-based Method for Identifying New Constructions around Water Reservoirs: Preliminary Results | Nayereh Hamidishad (USP); Roberto Cesar Junior (USP) | |
Similaridade de Imagens pela Análise da Aleatoriedade Utilizando Compressão de Dados | Rafael Divino F Feitosa (IF Goiano); Anderson Soares (UFG) | |
Utilização de Redes Neurais Completamente Convolucionais para identificação e medição de crânios fetais | Everton Leonardo Skeika (UTPFR); Mauren Louise Sguario Coelho de Andrade (UTPFR); Hugo Valadares Siqueira (UTFPR) |
Keynote Location: Room 201 | André Hinkenjann(Bonn-Rhein-Sieg University of Applied Sciences, Sankt Augustin, Germany) Handmade Pixels - Feeding High-Resolution and High-Framerate Displays Abstract: In this talk we will present work on rendering approaches for high resolution and high frame rate displays at IVC. Displays include projections, display walls and HMDs. We show that game engines can be used to facilitate application development for large tiled display walls. Further, we report on work using tracked projectors to create a variable-dpi display. This is extended by audio cues to represent the context of a detail view. An upcoming problem in high-resolution realtime high-quality rendering is the sheer number of pixels that need to be updated with high frequency. We argue that ray tracing is suited to address this problem and present work on foveated ray tracing for HMDs. The latter can be combined with elaborate global illumination approaches which we report on in the last part of the talk. Short Bio: Dr. André Hinkenjann is a research professor for Computer Graphics and Interactive Environments at the University of Applied Sciences (H-BRS) in Sankt Augustin, Germany. He received his Diploma in Computer Science from TU Dortmund. After that he worked at Fraunhofer IAO in Stuttgart on one of Germany’s first VR installations. Dr. Hinkenjann received his PhD from the Technical University Dortmund. Since 2012 he has also been the founding director of the Institute of Visual Computing. His main research areas are Interactive Environments, Visualisation, Efficient Global Illumination, and Ultra-High Resolution Display Systems. He is a member of IEEE, ACM SIGGRAPH, Eurographics, and the German Informatics Society. He is also a regular reviewer for many international conferences and workshops in the field of computer graphics and interactive environments.@ | ||
Keynote Location: Room 201 | Carla Dal Sasso Freitas(UFRGS) Data Visualization to Immersive Analytics: What’s next? Abstract: Data visualization has been around for decades since the first computer graphics applications. However, only in the mid-eighties, visualization was understood as a research and development field per se, motivated by the ever-growing computational resources applied to collect, process, and generate large volumes of scientific data. Then, the web provided another environment to produce and disseminate information in several forms. Researchers started to develop techniques to visualize this variety of information in different ways since the data made available represented abstract information. In the mid-nineties, analysis tools joined this scenario because only visualizing information was not enough for the needs of new applications. The term "visual analytics" was coined to denominate several techniques from information visualization, statistics, and machine learning, which aimed to help develop solutions for data analysis. In the last few years, we witnessed the emerging field of "immersive analytics", where we find virtual and augmented reality techniques being used for data visualization, especially for analysis of big data. Immersive analytics combines new interaction and display technologies to support analytical reasoning and decision making, thus encompassing visualization techniques and multisensory input (and output). In this talk, I will summarize the main aspects involved in immersive analytics, by tracing the path from data visualization to immersive analytics, discuss the pros and cons of adopting such techniques, and outline the research scenario in the field. Short Bio: Carla Dal Sasso Freitas is a full professor at the Institute of Informatics, Federal University of Rio Grande do Sul (UFRGS). She has a Ph.D. in Computer Science from UFRGS (1994) and was a visiting scholar at the International Computer Science Institute and E.O. Lawrence Berkeley National Laboratory, Berkeley, CA, USA (1996-1997). Her current research interests are data visualization, human-computer interaction, and immersive analytics. She has coordinated international cooperation projects with University Paul Sabatier (Toulouse, France), INRIA Saclay (Paris, France) and Université Catholique de Louvain (Louvain-la-Neuve, Belgique). She has already supervised more than 50 graduate students (MSc and Ph.D. candidates) and published more than 150 papers in journals and conferences. Along with her researcher career, she also served as administrative director of the Brazilian Computer Society (SBC) and coordinator of the SBC Special Interest Group on Computer Graphics and Image Processing. Currently she is the dean of the Institute of Informatics at UFRGS. @ | ||
Keynote Location: Room 201 | Soraia Raupp Musse(PUCRS) Crowds Behavior Analysis and Simulation Abstract: In this presentation, I will talk about the work I have done in the Crowds area since 1996, focusing on security systems and digital entertainment. In particular, I have worked to answer some questions: What features should I include in a crowd simulator in order to provide realistic mass, group and individual behaviors? When a crowd becomes a collective structure where groups are not visible anymore and collective abstractions are possible? Some methods take into account video data extraction; others consider the information coming from psychology or sociology areas, including cultural and personality analysis. And finally, how should I compare crowds and evaluate their realism? All analyzed data can be used in entertainment or serious applications to improve the realism of simulated NPC behaviors. Short Bio: Soraia Raupp Musse is an associate professor at the School of Technology, Pontifical Catholic University of Rio Grande do Sul (Brazil), where she created and coordinates the Virtual Human Laboratory. Her research interests include crowd simulation and analysis, facial animation, and integration of computer graphics, pattern recognition and computer vision applied to games. Dr. Musse has a Ph.D. in Computer Science from the Ecole Polytechnique Fèdérale de Lausanne (Switzerland) where she was supervised by Prof. Daniel Thalmann. Recently, she spent a year at UPENN (USA) working as a visiting scholar with Prof. Norman Badler. She has supervised more than 40 graduate students and postdocs and published more than 160 peer-reviewed papers in journals and conferences. She also published four books on the domain of Crowd and behaviors Simulation with Springer-Verlag. Currently, she is a member of Brazilian Special Group in Games and Digital Entertainment from Brazilian Computer Society. @ | ||
Session | Title | Authors |
TS7: Pattern Recognition I @Location: Room 208 Chair: Alexandre Falcão | RetailNet: A deep learning approach for people counting and hot spots detection in retail stores | Valério Nogueira Jr. (Federal University of Alagoas); Hugo Oliveira (Federal University of Alagoas); José Augusto Silva (Federal University of Alagoas); Thales Vieira (UFAL); Krerley Oliveira (Federal University of Alagoas) |
Face Recognition Using LBP on an Image Transformation Based on Complex Network Degrees | Murilo da Costa (Universidade Federal de Uberlandia); Cynthia Couto (Universidade de São Paulo); Leandro N Couto (Universidade Federal de Uberlandia) | |
Multi-Loss Recurrent Residual Networks for Gesture Detection and Recognition | Igor L Bastos (Universidade Federal de Minas Gerais); Victor Hugo C. de Melo (Federal University of Minas Gerais); William R Schwartz (Federal University of Minas Gerais) | |
Simultaneous Iris and Periocular Region Detection Using Coarse Annotations | Diego R Lúcio (Federal Universisty of Paraná); Rayson Laroca (Federal University of Paraná (UFPR)); Luiz A Zanlorensi (Federal University of Paraná (UFPR)); David Menotti (Federal University of Paraná); Gladston Moreira (Federal University of Ouro Preto) | |
Video Audience Analysis using Bayesian Networks and Face Demographics | Ítalo de P. Oliveira (UFCG); Carlos Daniel Interaminense (UFCG); Eanes Pereira (UFCG); Herman M Gomes (UFCG) | |
[GRSL] Fully Convolutional Siamese Auto-encoder for Change Detection in UAV Aerial Images | Daniel B. Mesquita (UFMG); Ronaldo F. dos Santos (UFMG); Douglas G. Macharet (UFMG); Mario F. M. Campos (UFMG); Erickson R. Nascimento (UFMG) | |
TS8: Computer Vision @Location: Room 210 Chair: Mauricio Pamplona | [CAG] Human Pose Regression by Combining Indirect Part Detection and Contextual Information | Diogo Luvizon (Paris Seine University); Hedi Tabia (Paris Seine University); David Picard (Paris Seine University) |
[CAG] TensorPose: Real-time pose estimation for interactive applications | Luiz José Schirmer Silva (PUC-Rio); Luiz Velho (IMPA); Alberto Raposo (PUC-Rio); Hélio Côrtes Vieira Lopes (PUC-Rio); Djalma Lucio Soares da Silva (PUC-Rio) | |
[CAG] Handling Pedestrians in Self-Driving Cars using Image Tracking and Alternative Path Generation with Frenét Frames | Renan Sarcinelli (Federal University of Espirito Santo); Vinicius B Cardoso (Federal University of Espirito Santo); Pedro Azevedo (Federal University of Espirito Santo); Claudine Badue (Federal University of Espirito Santo); Thiago M Paixão (Federal University of Espirito Santo); Rodrigo F Berriel (Federal University of Espirito Santo); Thiago Oliveira-Santos (Federal University of Espirito Santo); Rânik Guidolini (Federal University of Espirito Santo); | |
Optimizing Super Resolution for Face Recognition | Antonio A Abello (IME-USP)*; Roberto Hirata Junior (USP) | |
[GRSL] Roof Classification from 3D LiDAR Point Clouds using Multi-view CNN with Self Attention | Dimple Shajahan; Vaibhav Nayel; Ramanathan Muthuganapathy | |
TS9: Computer Vision and Pattern Recognition @Location: Room 208 Chair: David Menotti | How Effective Is Super-Resolution to Improve Dense Labelling of Coarse Resolution Imagery? | Matheus B Pereira (UFMG)*; Jefersson A dos Santos (UFMG) |
Simple and Effective Load Volume Estimation in Moving Trucks using LiDARs | Lucas L Amorim (Universidade Federal do Espírito Santo)*; Filipe Mutz (Instituto Federal do Espirito Santo); Claudine Badue (UFES); Alberto De Souza (UFES); Thiago Oliveira-Santos (Universidade Federal do Espirito Santo) | |
Hierarchy-of-Visual-Words: a Learning-based Approach for Trademark Image Retrieval | Vítor Lourenço (Universidade Federal Fluminense)*; Gabriela Silva (Universidade Federal Fluminense); Leandro A. F. Fernandes (Universidade Federal Fluminense) | |
PursuitPass: A Visual Pursuit Based User Authentication System | Alex Carneiro (Universidade de São Paulo)*; Candy Tenorio (Universidade de São Paulo); Carlos E. L. Elmadjian (University of Sao Paulo); Carlos Morimoto (IME-USP); Flávio Coutinho (EACH-USP) | |
Brain extraction network trained with ``silver standard" data and fine-tuned with manual annotation for improved segmentation | Roberto Souza (University of Calgary)*; Oeslle Lucena (King's College University); Mariana Bento (University of Calgary); Julia Garrafa (UNICAMP); Leticia Rittner (UNICAMP); Simone Appenzeller (UNICAMP); Roberto Lotufo (UNICAMP); Richard Frayne (University of Calgary) | |
[GRSL] Generating Sketch-Based Realistic Seismic Images with Generative Adversarial Networks | Rodrigo Ferreira; Julia Noce; Dário Oliveira; Emilio Brazil. | |
TS10: Pattern Recogniton II @Location: Room 208 Chair: Thales Vieira | Alignment of Local and Global Features from Multiple Layers of Convolutional Neural Network for Image Classification | Fernando Pereira dos Santos (Universidade de São Paulo)*; Moacir Ponti (Universidade de São Paulo) |
On Modeling Context from Objects with a Long Short-Term Memory for Indoor Scene Recognition | Camila L Silva (Universidade Federal de Minas Gerais)*; Anisio Lacerda (Universidade Federal de Minas Gerais); Erickson R. Nascimento (UFMG) | |
A Hybrid Frequency-domain/Image-domain Deep Network for Magnetic Resonance Image Reconstruction | Roberto Souza (University of Calgary)*; Richard Frayne (University of Calgary) | |
Dynamic Sign Language Recognition Based on Convolutional Neural Networks and Texture Maps | Edwin J Escobedo Cardenas (Federal University of Ouro Preto)*; Lourdes Ramirez Cerna (Federal University of Ouro Preto); Guillermo Camara-Chavez (UFOP) | |
[GRSL] SAR image segmentation based on unsupervised classification of log-cumulant estimates | Regis Marques (IFCE); Enilton Silva (); Fátima Medeiros (UFC) | |
[CAG] Classification of breast and colorectal tumors based on percolation of color normalized images | Guilherme Freire Roberto (Federal University of Uberlândia); Thaína A Tosta (Federal University of ABC); Paulo R Faria (Federal University of Uberlândia); Alessandro S Martins (Federal Institute of Triângulo Mineiro); Leandro A Neves (São Paulo State University) | |
[GRSL] Image-based Time Series Representations for Pixelwise Eucalyptus Region Classification: a Comparative Study | Danielle Dias; Ulisses Dias; Nathalia Menini; Rubens Lamparelli; Guerric Le Maire; Ricardo Torres. | |
WIA1 @Location: Room 210 | Uncertainty quantification in reservoir history matching using the ensemble smoother | Thiago M. D. Silva (PUC-RIO); Abelardo Barreto (PUC-RIO); Sinesio Pesco (PUC-RIO) |
Improving the performance of a SVM+HOG classifier for detection and tracking of wagon components by using geometric constraints | Camilo Lélis A. Gonçalves (UFPA); Ronaldo F. Zampolo (UFPA); Fabrício José B. Barros (UFPA); Ana Claudia S. Gomes (ISI/SENAI); Eduardo C. de Carvalho (ISI/SENAI); Bruno Victor M. Ferreira (ISI/SENAI); Rafael L. Rocha (ISI/SENAI); Rodrigo C. Rodrigues (VALE S.A); Giovanni Augusto F. Dias (VALE S.A); Diego A. Freitas (VALE S.A) | |
Visual assessment of equirectangular images for virtual reality applications In Unity | Adriano Gil (SVIDIA); Aasim Khurshid (UFRGS, SVIDIA); Juliana Postal (SVIDIA); Thiago Figueira (SVIDIA) | |
Invited Talk Pablo Bioni (VFX R&D Director, TV Globo) TV special effects | Short Bio: Pablo Bioni is the Director of the Research & Development division in visual effects (VFX) of the TV Globo, Rio de Janeiro, Brazil. He holds an MSc in Informatics (Computer Graphics) and a computer engineering degree from Pontifical Catholic University of Rio de Janeiro (PUC-Rio). He designed the innovation processes of the VFX production workflow currently being used by TV Globo and defined new methods and techniques for the visual effects used by soap operas, mini-series, and TV specials. | |
WIA2 @Location: Room 210 | Invited Talk Leandro Franco de Souza (ICMC, USP São Carlos) CFD applications in industry | Short Bio: graduate at Engenharia Mecânica from Pontifícia Universidade Católica de Minas Gerais (1992), master's at Mechanical Engineering from Pontifícia Universidade Católica de Minas Gerais (2000) and ph.d. at Aerospace Engineering from Instituto Tecnológico de Aeronáutica (2003). Has experience in Aerospace Engineering, acting on the following subjects: high order methods, immersed boundary method, direct numerical simulation - dns, hydrodynamic instability and compressible flow. |
Invited Talk Leila Maria Garcia Fonseca (National Institute for Space Research – INPE) Remote sensing & environmental monitoring | Short Bio: Graduated in Electrical Engineering, Master of Electrical Engineering and Computer Science at the Technological Institute of Aeronautics and Ph.D. in Applied Computing at the National Institute for Space Research (INPE), Brazil. She has been working at INPE since 1985 serving in important technological projects (CBERS Program), and international organizations and committees such as the Committee on Earth Observation Satellites (CEOS) and Latin American Society of Specialists in Remote Sensing (SELPER). She has been Head of the Image Processing Division (DP ) at INPE from 2011 to 2014, and also Director of Earth Observation Coordination at INPE, Brazil, from 2014 to 2018. Currently she is the technical coordinator of the Cerrado Monitoring Project, with financial support of the Forest Investment Program (FIP). |
