Costa Pereira, Jose

Bio

I’m a Ph.D. from University of California, San Diego (USA), in Electrical and Computer Engineering; currently a Research Scientist at Huawei Noah’s Ark Lab (London, UK) while maintaining a role fo Scientific Advisor at INESCTEC (Porto, Portugal) and an invited professor at the Computer Science Department in the School of Engineering, University of Porto (Portugal).

My professional activities started in October 2000. Having received my Licenciatura† in Computer Science and Engineering from the University of Porto, I’ve started my career as a network engineer at Vodafone. There I was responsible for the design and operation of the core IP network, serving both internal and (external) corporate customers. In 2005, I’ve joined the IP division of Alcatel-Lucent in Lisbon, where my role was to design and customize network solutions for major telecom carriers in the EMEA region; performing proof-of-concept trials with potential customers. Concurrently to these professional activities, in 2003 I’ve completed an M.A. in Applied Mathematics under the supervision of Prof. André Puga, also at University of Porto. In 2008 I’ve joined the doctoral program on “Intelligent Systems, Robotics and Control” at U.C. San Diego, where I’ve concluded both M.Sc. (2011) and Ph.D. (2015) under the supervision of Prof. Nuno Vasconcelos. During my studies at UCSD I served as a Research and Teaching Assistant; and I was lucky enough to do a brief internship at Telefonica R&D in Barcelona (Spain).

† 5-year undergraduate degree

Research

My research focus lies on Computer Vision. This is, of course, a very broad scope that involves many interesting topics such as: Statistical Signal Processing, Optimization, Machine Learning, and Multimedia. During my graduate program at UCSD, I was doing research on Image Retrieval, Cross-modality and (automatic) Scene Understanding. At INESCTEC, in the VCMI group, I collaborated with students and other researchers in the development of new CAD tools for breast cancer screening. Given the success of deep learning frameworks in many visual recognition tasks, they are being extensively used in medical imaging applications. I’ve lead a small group of students to participate in The Digital Mammography DREAM Challenge for breast cancer screening, achieving an honorable 3rd place in the first round.

At Noah’s Ark Lab my research interests are focused on computational photography. In particular I’m interested in image-to-image restoration techniques, and no-reference image quality metrics from a perceptual standpoint. Many solutions using deep learning frameworks have been recently proposed to address these problems, and to a certain extent with great success. The problem of designing a "no-reference image quality metric" is however a very challenging one. As one can image it is very difficult to come-up with an architecture that mimics the human visual system (HVS) in terms of opinions on image quality. And this is exactly what us and many researchers around the world are trying to do!