I am a postdoctoral fellow at MIT at Poggio's lab in 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. Afterwards, I did a postdoc in NUS, in which I was part time present at MIT in Poggio's lab.


Curriculum Vitae



My colleagues and I develop computational models of human visual perception. This will help to understand the principles of human intelligence and learning, and design intelligent machines.

We work on the hypothesis that the computations done in the human and artificial visual systems, aim at reducing the amount of examples used to learn to recognize objects. We develop models based on our hypothesis, that will unify the differe artificial visual systems, and also model the computations done in the human visual system. Namely, we are currently building and analyzing computational models of object recognition that take into account aspects of human visual attention and memory.


Working Papers

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

Recent Publications

Selected Publications

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

M. Jiang, X. Boix, J. Xu, G. Roig, L. Van Gool, Q. Zhao. Learning to Predict Sequences of Human Visual Fixations  TNNLS 2016.

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.

Email:  xboix at mit dot edu

Address:  MIT 46-5189, 43 Vassar Street,

                MA 02139, Cambridge, USA