Oge Marques

This lecture presents and explains a diverse collection of visual perception phenomena that challenge our common knowledge of how well we detect, recognize, compare, measure, interpret, and make decisions upon the information that arrives at our brain through our eyes. It also explains the relationships between the latest developments in human vision research and emerging technologies, such as: self-driving cars, face recognition and other forms of biometrics, and virtual reality. After seeing a large number of examples of optical illusions and other visual phenomena, this talk will make you wonder: can you really trust what you see?

This lecture provides directions for developers and researchers interested in developing iOS applications with image processing and computer vision capabilities. It is divided into three main parts: (1) motivation for developing intelligent visual applications for the iOS environment; (2) overview of the languages, tools, and image processing and computer vision libraries for iOS development; and (3) a collection of examples, case studies, commercial applications and popular APIs.

This lecture provides an overview of successful leadership and communication skills that engineering and computer science students and professionals can use to thrive in today’s diverse, team-oriented, professional environments. Topics include: successful decision-making strategies, team norms, gentle and participative leadership, and the role of humor in public speaking.

This lecture presents an overview of useful image processing and computer vision algorithms and demonstrates how to quickly use them to build practical solutions implemented with MATLAB. It provides an overview of MATLAB and some of its toolboxes (notably the Image Processing toolbox and the Computer Vision System toolbox) and illustrates their use in a practical, solution-oriented way.

This talk discusses how we can use human computation methods to supplement traditional content analysis techniques and assist in the solution of hard multimedia problems. There are many challenging problems in multimedia research for which state-of-the-art solutions fall short of performing perfectly. The realization that many of these tasks are arduous for computers yet are relatively easy for humans has inspired many researchers to approach those problems from a human computation viewpoint, using methods that include crowdsourcing and serious games. This lecture covers concepts, tools, technologies, best practices, human aspects, and trade-offs involved in applying crowdsourcing and gamification approaches to relevant contemporary problems in multimedia, computer vision, and related research areas.

This talk presents an overview of Visual information retrieval (VIR), an active and vibrant research area, which attempts at providing means for organizing, indexing, annotating, and retrieving visual information (images and videos) from large, unstructured repositories. It gives special emphasis to the process of searching and retrieving images using a visual query, usually known as Content-Based Image Retrieval (CBIR). This field of research has experienced significant scientific and technological advances during the past 25 years, which have led to today's commercial solutions capable of being presented with an image and answering questions such as: What is this?, Where can I purchase it?, Who painted this?, or Can you find me more images like this?