J. D. Curtó

I've had numerous research appointments, namely at the Department of Computer Science and Engineering at CUHK with Irwin King and Michael R. Lyu and at Carnegie Mellon with Kris M. Kitani. 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 under the supervision of Luc van Gool and later on with John Lygeros. 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. where I was advised by Alex Smola and Chong Wah Ngo. As part of the MS program, I also interned at the Robotics under Fernando de la Torre. At City University of Hong Kong, I received several awards: the Top Achiever 2015, MS Internship Sponsorship 2014 and MS Entrance Scholarship 2013/14.

Besides, during my time in Hong Kong I participated in the Program of Open Mentoring in the Department of Computer Science at The University of Hong Kong with Li-Yi Wei.

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 under Eric Pellegrin. I had near perfect top nationwide scores in the university entrance examinations and baccalaureate.

e-mail  /  cv  /  twitter

profile photo

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.

Doctor of Crosswise: Reducing Over-parametrization in Neural Networks.
Curtó, Zarza, Kitani, King and Lyu.

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.

High-resolution Deep Convolutional Generative Adversarial Networks.
Curtó, Zarza, Torre, King and Lyu.
dataset / supplement / video

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.

Segmentation of Objects by Hashing.
Curtó, Zarza, Smola and Gool.

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: A Library for Approximate Kernel Expansions in Log-linear Time.
Curtó, Zarza, Yang, Smola, Torre, Ngo and Gool.

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

A Library for Fast Kernel Expansions with Applications to Computer Vision and Deep Learning.
Supervisors: Smola and Ngo.
Carnegie Mellon. Pittsburgh. 2014.

Master of Science. City University of Hong Kong.

Construction and Performance of Network Codes.
Supervisor: Vázquez.
Universitat Autònoma de Barcelona. Bellaterra. 2013.
slides / secure network coding

5-year Degree in Engineering of Telecommunication. UAB. UPC.

Template from Barron.