I am a postdoctoral fellow at MIT at Poggio's lab and a research fellow at the Boston Children's Hostpital - Harvard Medical School at Kremian's lab. I am a member of the Center for Brains, Minds and Machines, and I am also affiliated at the Istituto Italiano di Technologia in the Laboratory for Computational and Statistical Learning.

I obtained the doctorate from ETH Zurich in 2014. I was fortunate to receive the European Intel Doctoral Student Award for my thesis.

 

Curriculum Vitae (2016)

 

 

I contribute to Science of Computer Vision, which is part of Science of Intelligence. Science of Computer Vision studies the computational principles underlying  engineered computer vision algorithms and the human brain. This will help to understand the principles of human and artificial intelligence and learning.

Towards this goal, we are currently building and analyzing computational models of object recognition that include visual attention and short-term memory.

 

Working Papers

E. Ozkan, G. Roig, O. Goksel, X. Boix. Herding Generalizes Diverse M-Best Solutions

Selected Publications

L. Yan, X. Boix, G. Roig, T. Poggio, Q. Zhao. Foveation-based Mechanisms Alleviate Adversarial Examples

M. van den Bergh, X. Boix, G. Roig, L. Van Gool. SEEDS: Superpixels Extracted via Energy-Driven Sampling  IJCV 2015.

OpenCV Challenge Award 2015

X. Boix*, J.M. Gonfaus*, J. van de Weijer, A. Bagdanov, J .Serrat, J. Gonzalez. Harmony Potentials IJCV 2012.

PASCAL VOC Segmentation Challenge Winner 2010.

G. Roig*, X. Boix*, R. De Nijs, S. Ramos, K. Kuhnlenz, L. Van Gool. Active MAP inference in CRFs for efficient semantic segmentation ICCV 2013.

Oral Presentation.

X. Boix*, G. Roig*, S. Diether, L. Van Gool. Self-Adaptable Templates for Feature Coding NIPS 2014.

* means equal contribution

Complete List:

Adversarial examples

Current state-of-the-art techniques for object recognition seem to be very easy to fool by  imperceptible perturbations of the image. In a recent paper we provide new insights, and we introduce a new research direction to solve this fundamental problem.

Record-breaking results on

predicting eye-fixation locations

Our paper about predicting eye-fixation maps reports record-breaking results. Click here to see the demo.

SEEDS Superpixels

available in OpenCV

We released a new version of SEEDS superpixels in OpenCV, which is about 4x faster than previous code. We were lucky to receive the OpenCV Challenge Award.

A. Garcia del Molino, X. Boix, J. Lim, A. Tan. Active Video Summarization: Customized Summaries via On-line Interaction. AAAI 2017.

Email:  xboix at mit dot edu

Address:  MIT 46-5155 43 Vassar Street,

                MA 02139, Cambridge, USA