J. de Curtó i Díaz

I've had numerous research appointments, namely at the Department of Computer Science and Engineering at CUHK and at Carnegie Mellon. As well as at the EE and CS Departments at City University of Hong Kong.

I was a doctoral student in the Laboratory of Computer Vision at ETH Zürich. Previously I completed my master (with distinction) in Electrical Engineering at City University of Hong Kong, where I did an exchange at the School of Computer Science at Carnegie Mellon. I developed my master thesis at the ML Dept. and as part of the MS program, I also interned at the Robotics. At City University of Hong Kong, I received several awards: the Top Achiever 2015, MS Internship Sponsorship 2014 and MS Entrance Scholarship 2013/14.

I hold a 5-year degree in Engineering of Telecommunication from Universitat Autònoma de Barcelona and Universitat Politècnica de Catalunya. I also worked as Research Scientist at CELLS ALBA Synchrotron. I had near perfect top nationwide scores in the university entrance examinations and baccalaureate.

e-mail  /  cv  /  scholar.google  /  twitter

I'm broadly interested in computer vision and machine learning. I develop models that extract high-level information of the world to assist robots and automated learning machines such as self-driving cars. Representative publications are highlighted.

Dr. of Crosswise proposes a new architecture to reduce over-parametrization in Neural Networks. It introduces an operand for rapid computation in the framework of Deep Learning that leverages learned weights.

In order to boost network convergence of DCGAN and achieve good-looking high-resolution results we propose a new layered network, HDCGAN, that incorporates current state-of-the-art techniques for this effect.

Recognitions:
State-of-the-art in synthetic image generation on CelebA 128x128 (MS-SSIM). 2017.
State-of-the-art in synthetic image generation on CelebA 64x64 (FID). 2017.

We propose a novel approach to address the problem of Simultaneous Detection and Segmentation. We use an efficient and accurate procedure that exploits the feature information of the hierarchy using Locality Sensitive Hashing.

McKernel introduces a framework to use kernel approximates in the mini-batch setting with Stochastic Gradient Descent (SGD) as an alternative to Deep Learning.

Master of Science.
City University of Hong Kong. Carnegie Mellon.

5-year Degree in Engineering of Telecommunication.
Universitat Autònoma de Barcelona. Universitat Politècnica de Catalunya.

A curated list of papers in Robotics.

Template from Barron.