FAPESP Thematic Projects at RECOD

RECOD Lab. has been awarded two Fapesp Thematic Projects recently. This is an AMAZING achievement for our lab. and for IC/Unicamp, especially during this tough financial moment in our country. The two projects, entitled “DéjàVu: Feature-space-time coherence from heterogeneous data for media integrity analytics and interpretation of events” — coordinated by Prof. Anderson Rocha — and “The secret of playing football: Brazil versus the Netherlands” — coordinated by Prof. Ricardo Torres are starting this semester. Details about each project are given below.

DéjàVu: Feature-Space-Time Coherence from Heterogeneous Data for Media Integrity Analytics and Interpretation of Events

FAPESP Thematic Project 2017/12646-3,  from December 2017 through November 2022

In this research project, we focus on synchronizing specific events in space and time (X-coherence), fact-checking, and mining persons, objects and contents of interest from various and heterogeneous sources including — but not limited to — the internet, social media and surveillance imagery. For that, we seek to harness information from various media sources and synchronize the multiple textual and visual information pieces around the position of an event or object as well as order them so as to allow a better understanding about what happened before, during, and shortly after the event. After automatically organizing the data and understanding the order of the facts, we can devise and deploy solutions for mining persons or objects of interest for suspect analysis/tracking, fact-checking, or even understanding the nature of the said event. Additionally, by exploring the possible existing links among different pieces of information, we aim at further designing and developing media integrity analytics tools to hint at existing forgeries, sensitive content (e.g., violent content, child pornography), and spreading patterns of multimedia objects online. With demanding and sophisticated crimes and terrorist threats becoming ever more pervasive, allied with the advent and spread of fake news, our objective is to use the developed solutions to help us answering the four most important questions in forensics regarding an event: “who”, “in what circumstances”, “why”, and “how”, thus identifying the characteristics and circumstances in which an event has taken place.

Hélio Pedrini, Co-PI (Unicamp), André C.P.L.F. de Carvalho, Co-PI (USP), Adam Czajka (Warsaw Univ. of Technology, Poland), Alex Kot (Nanyang Technological University, Singapore), C.-C. Jay Kuo (Univ. of Southern California, USA), Edward Delp (Purdue Univ., USA), Kevin Bowyer (Univ. of Notre Dame, USA), Patrick Flynn, (Univ. of Notre Dame, USA), Stefano Tubaro (Politecnico di Milano, Italy), Paolo Bestagini (Politecnico di Milano, Italy), Walter J. Scheirer (Univ. of Notre Dame, USA), Alexandre Ferreira (UNICAMP), Adin Ramirez Rivera(UNICAMP), Eduardo Valle, (UNICAMP), Fernanda Alcântara Andaló (UNICAMP), Jacques Wainer (UNICAMP), Lin Tzy Li (UNICAMP), Sandra Avila (UNICAMP), Zanoni Dias (UNICAMP), Marcos André Gonçalves (UFMG), William Schwartz (UFMG).

The Secret of Playing Football: Brazil versus the Netherlands

FAPESP Thematic Project 2016/50250-1 from August 2017 through July 2021

The scientific challenge is about unraveling the secret of Brazilian and Dutch soccer by capturing successful elements of game play of both countries, combining expertise from data science, computer science, and sport science. Suggested features from literature, as well as several novel ones, will be considered and filtered on how they capture success in soccer. A manageable set of features will then be obtained from various available Dutch datasets (focusing on the successful play). Subsequently, the same features will be used to compare playing styles between both countries. Features of game play will be approached from two different angles. The first angle (spearheaded by the Brazilian computer science partner) concerns features that capture the dynamics of game play and characterize aspects of formation on the pitch. The second angle (lead by the Dutch data science partner) will focus on how an attack is built up, and how key events (shots on goal, transitions from defenders to midfielders, etc.) can help to characterize this. For the comparison between countries data will be collected in four different age categories in Brazil and the Netherlands during official games, in order to compare (the development of) game play between both countries. Data will be collected by means of the Local Position Measurement System, for reasons of accuracy and consistency. The applied science part of this proposal is focusing on bridging the gap between fundamental science and soccer practice, i.e. coaches, trainers, clubs, and federations. The outcomes of the fundamental part will be implemented in a coach-cockpit, a software application which trainers and coaches can use to (1) decide upon their strategy before a game, (2) analyze player and team behaviour during a game enabling to adjust the strategy accordingly, and (3) choose and/or design training forms to improve player and team behaviour.

Claudio Alexandre Gobatto (UNICAMP), Sergio Augusto Cunha (UNICAMP), Ricardo Oliveira Anido (UNICAMP), Luiz Eduardo Barreto Martins (UNICAMP), Ricardo Machado Leite de Barros (UNICAMP), Felipe Arruda Moura (UEL) e Paulo Roberto Pereira Santiago (USP), Koen A. P. M. Lemmink (University of Groningen), Johan Pion (HAN University), Marije T. Elferink-Gemser (University of Groningen), Joost N. Kok (Leiden University), e Arno Knobbe (Leiden University).

Posted in awards, blog, DéjàVu, science | Tagged , , , , , , | 1 Comment

Kuaa: A unified framework for design, deployment, execution, and recommendation of ML experiments

Several libraries and machine-learning frameworks have been proposed in the literature to support users in the process of defining the most appropriate methods for their applications. However, many frameworks have limitations including the lack of flexibility to include novel proposed descriptors and machine learning methods, and specially, the inability to reuse previous experiments and learn from them.

In this article published in Future Generation Computer Systems, the authors propose Kuaa, a workflow-based framework that can be used for designing, deploying, and executing machine learning experiments in an automated fashion. This framework is able to provide a standardized environment for exploratory analysis of machine learning solutions, as it supports the evaluation of feature descriptors, normalizers, classifiers, and fusion approaches in a wide range of tasks involving machine learning. Kuaa also is capable of providing users with the recommendation of machine-learning workflows. The use of recommendations allows users to identify, evaluate, and possibly reuse previously defined successful solutions. The authors propose the use of similarity measures (e.g., Jaccard, Sørensen, and Jaro–Winkler) and learning-to-rank methods (LRAR) in the implementation of the recommendation service.

Experimental results show that Jaro–Winkler yields the highest effectiveness performance with comparable results to those observed for LRAR, presenting the best alternative machine learning experiments to the user. In both cases, the recommendations performed are very promising and the developed framework might help users in different daily exploratory machine learning tasks.

Kuaa Code: https://github.com/rafaelwerneck/kuaa

Rafael de Oliveira Werneck, Waldir Rodrigues de Almeida, Bernardo Vecchia Stein, Daniel Vatanabe Pazinato, Pedro Ribeiro Mendes Júnior, Otávio Augusto Bizetto Penatti, Anderson Rocha, Ricardo da Silva Torres, Kuaa: A unified framework for design, deployment, execution, and recommendation of machine learning experiments, Future Generation Computer Systems, Volume 78, 2018, Pages 59-76, ISSN 0167-739X, http://dx.doi.org/10.1016/j.future.2017.06.013.

Posted in blog, publications, science | Tagged , , , , , , , , , , , , | Leave a comment

RECOD on the news

An article published at Correio Braziliense (in Portuguese), which is an important vehicle of communication in Brazil, highlights that 40% of doctored images are not perceived by people. This conclusion was reached by researchers at Warwick University through several experiments. Prof. Anderson Rocha was invited to comment this scenario and to talk about our efforts in developing algorithms capable of identifying these manipulations in an automatic fashion. The article discuss the importance of an automatic image manipulation tool and its impact in our modern digital society.

O que os olhos não veem (in Portuguese)

Posted in blog, extra, media | Tagged , , , , | Leave a comment

RECOD amasses (for the second time) two awards at the Google Research Awards for Latin America 2017

As a good déjà vu of what happened in 2016, two RECOD projects coordinated by Prof. Anderson Rocha and Prof. Eduardo Valle will keep receiving their scholarships from Google LARA (Latin American Research Awards) for the next 12 months.

This year there were 281 projects submitted but only 27 awarded. The result reaffirms the serious research work we have been doing at RECOD in the Computer Science field and, in particular, in Machine Learning.

The projects are:

Prof. Anderson Rocha and PhD candidate José Ramon Trindade Pires

Automated Data­-Driven Screening of Diabetic Retinopathy – Extension

In this research, we aim to design methods to recognize discriminative patterns of diabetic retinopathy stages, providing an advanced and robust severity decision; and incorporate such information into a final higher-level (and more refined) decision of referable DR. We also intend to explore possible forms of understanding the decisions taken by the devised solutions toward accountable decision-making methods.

Prof. Eduardo Alves do Valle Junior and PhD candidate Michel Fornaciali

Reliable Automated Melanoma Screening for the Real World

This project aims to speed-up real-world adoption of computer-aided melanoma screening, both by enhancing the Machine Learning models used to detect the disease, and by interacting with doctors to identify and remove barriers that prevent the adoption of the technology.

The event was covered by our local press (in Portuguese):


This slideshow requires JavaScript.

Posted in awards, blog | Tagged , , , , , , , , | Leave a comment

Your PLOS ONE Article is in the Top 25% Most Cited

The research paper entitled “Advancing Bag-of-Visual-Words Representations for Lesion Classification in Retinal Images” is among the top 25% most cited articles at PLOS ONE journal.

This article inaugurates RECOD’s policy on improving the reproducibility of our published results, by making publicly available both data and code as much as allowable by copyright law and by ethical practice.


Posted in awards, blog, media | Tagged , , , , | Leave a comment

User-Centric Coordinates for Applications Leveraging 3-Axis Accelerometer Data

Mobile devices are becoming ubiquitous and, sometimes, even extensions of ourselves. These devices are growing fast in terms of delivered computational power, storage capacity, battery duration, and built-in sensors. Time and again, we see headlines advertising new unforeseen applications leveraging this power, especially the sensors, for solving diverse problems, including fall detection, user’s activity recognition, location identification, or even user authentication based on the way of walking (gait).

In this paper, the authors focus on motion sensors and discuss how the provided data can be interpreted and transformed to better serve different purposes. They propose a method to process the data from such sensors that reduces the acquisition noise and possible artifacts, and turns the data invariant to the device’s position and the user’s movement direction. A new coordinate system referred to as user-centric is introduced, as opposed to the two most common coordinate systems used—the device and world-coordinate systems. The results show the importance of properly pre-processing the acquired data to enable more reliable applications underpinned by mobile sensors.

The figure shows the acceleration data represented in the world-coordinate system (left side) and in the user-centric coordinate system (right side). The samples are divided into three straight lines, represented by A, B, and C slots, and two left turns. In the world-coordinate system, after the first user’s left turn, we can notice the acceleration data from axis x in slot A moving to axis y in slot B, as blue box shows. This phenomenon happens again after the second user’s left turn, from slot B to slot C. It indicates that the direction the user is following is somehow represented in the acceleration data. Because it aims at being as much independent as possible from external factors – such as the user’s path – the coordinate systems shall not capture such variations. This is exactly what happens in the proposed user-centric coordinate system, in which the acceleration samples are kept in the same axis even after the user’s left turns.

Ferreira, A., Santos, G., Rocha, A., & Goldenstein, S. (2017). User-Centric Coordinates for Applications Leveraging 3-Axis Accelerometer Data. IEEE Sensors Journal, 17(16), 5231-5243.

Posted in blog, publications, science | Tagged , , , , , , , , , | Leave a comment

RECOD on the news

With the advances of artificial intelligence (AI), specially machine learning, many areas can take advantages of these emerging technologies. The learning experience, for instance, could be much more personal with algorithms that are able to identify possible difficulties of one particular student regarding specific topics and thus provide additional material or extra exercises.

In the following interviews, Prof. Anderson Rocha from RECOD has highlighted some important points in the relationship between AI and the modern society.

1) Pais do milênio confiam na inteligência artificial para educação dos filhos (O Globo, 20 jul. 2017 – in Portuguese)

2) Pais jovens confiam na inteligência artificial para educação dos filhos (Pequenas Empresas & Grandes Negócios, 20 jul. 2017 – in Portuguese)

Posted in blog, extra, media | Tagged , , , , , | Leave a comment

RECOD at ICIP 2017

The 2017 IEEE International Conference on Image Processing (ICIP 2017), to be held in China on September, will have three papers from RECOD. These papers are examples of the obtained results from the collaboration between University of Campinas and University of Notre Dame through research projects supported by DARPA (FA8750-16-2-0173), FAPESP (2015/19222-9), CAPES (DeepEyes) and CNPq (304472/2015-8).

The accepted papers are:

1. Spotting the Difference: Context Retrieval and Analysis for Improved Forgery Detection and Localization. Joel Brogan, Paolo Bestagini, Aparna Bharati, Allan Pinto, Daniel Moreira, Kevin Bowyer, Patrick Flynn, Anderson Rocha, Walter Scheirer.

2. U-Phylogeny: Undirected Provenance Graph Construction in the Wild. Aparna Bharati, Daniel Moreira, Allan Pinto, Joel Brogan, Kevin Bowyer, Patrick Flynn, Walter Scheirer, Anderson Rocha (oral presentation).

3. Provenance Filtering for Multimedia Phylogeny. Allan Pinto, Daniel Moreira, Aparna Bharati, Joel Brogan, Kevin Bowyer, Patrick Flynn, Walter Scheirer, Anderson Rocha (oral presentation).

Posted in blog, publications, science | Tagged , , , , , , , , , , , , , , , | Leave a comment

RECOD’s paper is the 2017 best paper at the Elsevier JVCI

We are happy to announce that the paper entitled “Going deeper into copy-move forgery detection: Exploring image telltales via multi-scale analysis and voting processes” published at the Elsevier Journal of Visual Communication and Image Representation (JVCI) has received the 2017 Best Paper Award.

Silva E., Carvalho T., Ferreira A., Rocha A, Going deeper into copy-move forgery detection: Exploring image telltales via multi-scale analysis and voting processes, vol. 29, May 2015.


Posted in awards, blog | Tagged , , , , , , | Leave a comment

RECODists have gotten their Ph.D. Thesis awarded

Two Ph.D. Thesis from RECOD lab have been awarded recently. First, the thesis entitled “Multi-Analysis Techniques for Digital Image Forensics” from Anselmo Castelo Branco Ferreira under the supervision of Prof. Anderson Rocha and co-supervision of Prof. Jefersson dos Santos won as best Ph.D. thesis in 2016 from the Institute of Computing – IC/Unicamp.

Then, the thesis entitled “Sensitive-video analysis” from Daniel Henriques Moreira under the supervision of Prof. Anderson Rocha and co-supervision of Prof. Siome Goldenstein won as best Ph.D. thesis at the XXXVII Brazilian Society Congress 2017. The thesis will be published at SpringerBriefs in Computer Science.


Posted in awards, blog | Tagged , , , , , , , , | Leave a comment