Talks: LIRMM and WIFS 2017, France

Prof. Anderson Rocha is visiting the Montpellier Laboratory of Informatics, Robotics and Microelectronics (LIRMM), Montpellier, France, hosted by Prof. William Puech. Two talks were/will be given:

Talk #1: Dec. 12th, 2017

Interpretation of Events from Heterogenous Data: How to Connect Existing Pieces of Evidence in Time and Space

Abstract: In this talk, we will discuss problems associated with 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.

Talk #2: Dec. 19th, 2017

Media Integrity Analytics: Beyond Digital Forensics of Single Objects

Abstract: Currently, multimedia objects can be easily created, stored, (re)-transmitted, and edited for good or bad. In this sense, there has been an increasing interest in finding the structure of temporal evolution within a set of documents and how documents are related to one another overtime. This process, also known in the literature as Multimedia Phylogeny, aims at finding the phylogeny tree(s) that best explains the creation process of a set of related documents (e.g., images/videos) and their ancestry relationships. Solutions to this problem have direct applications in forensics, security, copyright enforcement, news tracking services and other areas. In this talk, we explore solutions for reconstructing the evolutionary tree(s) associated with a set of visual documents, more specifically images and videos. This can be useful for aiding experts to track the source of child pornography image broadcasting or the chain of image and video distribution in time, being extremely useful for complex different media provenance tasks. Finally, we will also discuss how to implement such solutions in large-scale considering millions of documents at the same time.

In Rennes, on Dec. 6th, Prof. Anderson gave a talk at IEEE Intl. Workshop on Information Forensics and Security (WIFS 2017) in which he presented the paper:

Authorship Attribution for Social Media Forensics, A. Rocha, W. J. Scheirer, C. W. Forstall, T. Cavalcante, A. Theophilo, B. Shen, A. R. B. Carvalho, and E. Stamatatos, in IEEE Transactions on Information Forensics and Security, vol. 12, no. 1, pp. 5-33, Jan. 2017.

This slideshow requires JavaScript.

Posted in blog, DéjàVu, Keynotes, publications, science, talk | Tagged , , , , , , , , , | Leave a comment

RECODist has been awared with INOVA Prize 2017

We are very proud to announce that Gabriel Bertocco, one of our RECODists, has been awarded with the Unicamp INOVA Prize on Introduction to Innovation 2017. Supervised by Prof. Anderson Rocha and Fernanda Andaló, the work entitled “Automatic age range estimation on mobile devices” is the result of a partnership between RECOD and Motorola. The Unicamp INOVA Prize awarded to most innovative works in applied or basic sciences made by undergraduate students under scientific tutorial at Unicamp.

Another research work from RECOD, entitled “CrowdPet: Deep learning applied to the detection of dogs in the wild”, was also among the finalists in the technological area.

The related links are (in Portuguese):

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

Talk: Alex Kot from NTU, Singapore

The first DéjàVu invited talked happened this week, on Nov. 27th, at IC/Unicamp. In his talk, Prof. Alex Kot, director of ROSE Lab at Nanyang Technological University (NTU), Singapore, presented the most relevant ongoing research project at the Rapid-Rich Object Search (ROSE) Lab, which is comprised of 12 faculty, 26 research staff and a total of 48 PhD students from the Schools of Electrical & Electronic Engineering (EEE) and Computer Science & Engineering (SCSE) at the NTU.

The ROSE Lab is focusing on visual object search (including object classification, recognition, & retrieval); deep learning & visual analytics (including anomaly detection, pedestrian detection, person re-identification, object tracking, action recognition); as well as multimedia forensics & biometrics (including face spoofing & liveness detection) Since 2012, the ROSE Lab has secured 24 industry partners, including Tencent (one of the largest Internet companies in Asia), NVIDIA (the world’s leading visual computing company), Accenture (one of the world’s leading management consulting companies), and OMRON (a leading Japanese industry automation company).

This slideshow requires JavaScript.

Posted in blog, DéjàVu, Keynotes, science, talk | Tagged , , , , , | Leave a comment

1st Workshop of “The Secret of Playing Football: Brazil versus the Netherlands” project

On last Nov. 9th, 2017 the first workshop of the FAPESP research project entitled “The Secret of Playing Football: Brazil versus the Netherlands” took place at FEF/Unicamp. The presentations were given by Prof. Miguel de Arruda (FEF director), Prof. Ricardo Torres (project PI), Prof. Claudio Gobatto, Prof. Thomas Beltrame, Prof. Barreto, Prof. Felipe Moura, Prof. Paulo Santiago, Prof. Paulo Ruffino and Prof. Sergio Cunha.

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

1st Advanced Computing Workshop

The 1st Advanced Computing Workshop, which is in partnership with the Army Research Office/US, took place in São Paulo on November 13th, 2017. In the video below, Prof. Anderson Rocha explains how three RECOD’s projetcs, DeepEyes, MediFor and DéjàVu, are related and how they are contributing with Digital Forensics research advances.

Posted in blog, DéjàVu, Keynotes, science, talk | Tagged , , , | Leave a comment

RECODists Talks

During the last weeks, RECODists were performing several talks about the research projects we have been carrying on. They are:

  • Deep Learning” at EncPos 2017, IMECC Unicamp – Eduardo Valle

This slideshow requires JavaScript.

Posted in blog, extra, science, talk | Tagged , , , , , , , , | Leave a comment

DéjàVu on the news

Fapesp DéjàVu project, which will start soon, is attracting attention of Brazilian press for its high objectives and potential of impact in the society at large. They are (in Portuguese):

Posted in blog, DéjàVu, media, science | Tagged , , , , , , | Leave a comment

Talk: Remote Sensing Image Analysis in Phenology Studies: Challenges and Research Opportunities

Next Friday, on October 20th, Prof. Ricardo Torres will talk about Remote Sensing Image Analysis in Phenology Studies: Challenges and Research Opportunities at the Workshop on Pattern Recognition for Earth Observation in conjunction with the SIBGRAPI 2017 – Conference on Graphics, Patterns and Images. Check out the workshop program.

Posted in blog, Keynotes, science, talk | Tagged , , , , , , | Leave a comment

Graph-based Bag-of-Words for Classification

This paper, entitled Graph-based Bag-of-Words for Classification, introduces the Bag of Graphs (BoG), a Bag-of-Words model that encodes in graphs the local structures of a digital object. It presents a formal definition, introducing concepts and rules that make this model flexible and adaptable for different applications. It is defined two BoG-based methods – Bag of Singleton Graphs (BoSG) and Bag of Visual Graphs (BoVG), which create vector representations for graphs and images, respectively. The hypothesis explored in this paper is that the combination of graphs with the BoW model can create a discriminant and efficient representation based on local structures of an object, leading to fast and accurate results in classification tasks. The rationale is that the two representations are complementary and can help each other overcome their individual deficiencies.

The authors evaluate the Bag of Singleton Graphs (BoSG) for graph classification on four datasets of the IAM repository, obtaining significant results in accuracy and execution time. The method Bag of Visual Graphs (BoVG) is evaluated for image classification on Caltech and ALOI datasets, and for remote sensing image classification on images of Monte Santo and Campinas datasets. This framework opens possibilities for retrieval, classification, and clustering tasks on large datasets that use graph-based representations impractical before due to the complexity of inexact graph matching.

Fernanda B. Silva, Rafael de O. Werneck, Siome Goldenstein, Salvatore Tabbone, Ricardo da S. Torres, Graph-based Bag-of-Words for Classification, Pattern Recognition (2017), doi: 10.1016/j.patcog.2017.09.018

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

Talk: Remote Sensing Image Analysis in Phenology Studies

Tomorrow, on Oct 6th 2017 at 14h IC/Unicamp auditorium, Prof. Ricardo Torres will give a talk about Remote Sensing Image Analysis in Phenology Studies. The talk is part of the Institute of Computing weekly seminars series of 2017.

Title: Remote Sensing Image Analysis in Phenology Studies: Challenges and Research Opportunities

Abstract: Environmental changes are becoming an important issue in the global agenda. Typical change understanding ecological studies rely on the use of huge volumes of remote sensing image, demanding the definition of effective and efficient services for appropriate storing, retrieval, and knowledge extraction. This lecture will focus on presenting ongoing research initiatives focused on the specification and implementation of appropriate systems to handle large-scale remote sensing image collections. Special attention will be given to recent research results on image processing, machine learning, and time series analysis in the context of the e-Phenology project. The e-Phenology is a multidisciplinary project that combines research efforts in Computer Science and Phenology. Its objective is to address practical and theoretical problems involved in the use of new technologies to the remote observation of phenology, aiming to detect local environmental changes.

Posted in blog, Keynotes, science, talk | Tagged , , , , | Leave a comment