Quick Announcements

Post-doctoral Fellowship

The Thematic Research Project, entitled DéjàVu: Feature-Space-Time Coherence from Heterogeneous Data form Media Integrity and Interpretation of Events funded by FAPESP is seeking candidates for a 2-year (renewable) post-doctoral fellowship position to work at the Reasoning for Complex Data (RECOD) Lab.

The project relies upon collaborators from all over the globe such as the University of Campinas (Brazil), University of São Paulo in São Carlos (Brazil), Federal University of Minas Gerais (Brazil), Purdue University (USA), University of Notre Dame (USA), Politécnico di Milano (Italy), University of Siena (Italy), Nanyang Technological University, NTU (Singapore) and others.

More Information about the Project

In this 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. 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.

The Position

This fellowship position requires research and development in Computer Vision, Machine Learning and Visual Analytics, in collaboration with graduate students and partners. The work of the fellow will be focused on machine learning and visual analytics methods to perform X-coherence, or in other words, to find out the order of facts related to an event in space and time.

It is desirable that the candidate demonstrates domain knowledge in machine learning, visual analytics, and computer vision. However, candidates with good mathematical and programming backgrounds in any of the three areas and motivation to learn the others are equally welcomed.

The post-doctoral fellowship includes a monthly stipend of R$ 7,174.80 (about USD 2,300 and EU$ 2,000), access to the health-care system of Unicamp, and research contingency funds (15% of the annual value of the fellowship, each year). For more details, check out Fapesp’s webpage.

How to Apply

Interested candidates should email Prof. Anderson Rocha, project's coordinator, before February 20th, 2018 with:
A motivation letter for the application;
A recommendation letter from a previous supervisor;
Curriculum vitae with the list of publications, education background, research track-record and experience, and copy of diplomas/degree certificate(s).

Additional Information

Eligibility Criteria: Ph.D. in Computer Science or related areas (in case you have any doubt about a possible related area, drop an e-mail to the Project’s Coordinator above)

Selection process: It will be based on the motivation letter for the application, recommendation letter from a previous supervisor, curriculum vitae with the list of publications, education and experience, and copy of diplomas/degree certificate(s). An interview with the finalists shall take place via Telecom.

Information About Campinas

More details

Project Overview

Data Collection & Cleaning

We can gather data re- lated to a specific place, ob ject or event that were shared or posted in vari- ous places (e.g., social net- works, CCTVs and body cams) or that were seized in an operation.

Data Organization & X-coherence

The main task consists of tying together different information pieces in a spatial and temporal coherent form (X-coherence). Space-time-coherent pieces can be exploited to have an overall idea of the event, place or object as a whole, as well as of specific points within the event’s timeline.

Content Understanding & Inference

With X-coherent pieces, we can (i) look for specific clues (authorship, related topics); (ii) mine possible suspects, objects or places of interest through biometrics and machine learning techniques; (iii) counter fake propaganda and media repurposing through provenance analysis methods; and (iv) assess sensitive content through diverse filters (e.g., violence), everything underpinned by open-set recognition techniques.

Motivational Video

This video presents the main ideas behind the DéjàVu project.


Feature-space-time coherence, i.e., space-time coherence in physical terms (position in time), that is where and when something happened.

How to connect different information for the same event be it in the physical world or online
How to gather time information
How to synchronize the different pieces in time
How to organize the different pieces (shortly before, during, and shortly after) with respect to the event

Content Understanding & Inference

Crowd Data Analysis

Given any of these events, it would be extremely important to find associated information pieces in space and time both in the pool of apprehended materials and in possible collected social media information.

Mining points of interest

Leveraging the feature- space-time coherent information pieces from previous stages to find possible persons, objects or places involved with the event and, ultimately, propose some candidate suspects for further inves- tigation.

Provenace Analysis

Forensics analysts are interested not only in determining if a digital object is fake or real but also in pinpointing who created it, what happened, when and how (genealogy) an asset was created.

Sensitive Media Analysis

Given data collected and processed with the previous steps of the research, we will focus on deciding whether or not an image or video stream presents sensitive content.


November 27, 2017

Talk: Prof. Alex Kot

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 … Continue reading