Jordi Pont-Tuset bio photo

Jordi Pont-Tuset

I'm from a small town near Girona, Catalunya. Currently in Zürich, Switzerland. Passionate about computer vision, technology, running, and mountains.

Twitter   G. Scholar LinkedIn Github e-Mail Google+

All Posts

CVPR 2018: Are GANs the new deep?

It’s that time of the year when a major vision conference releases the papers to the public, so it’s time to check how deep learning is doing in their titles...

ICCV 2017: GANs et al. growing strong

Once more, let’s plot the evolution of deep learning in the major vision conferences. Here you can check the previous posts of the saga. Here the plot using...

CVPR 2017: Deep learning and the new kids in class

So here we are again to measure the presence of deep learning in the major vision conferences, with one more to the list. Here you can check the previous pos...

ECCV 2016: Deep learning, pit stop or plateau?

This is my customary update of percentage of deep-learning papers in the major vision conferences. At CVPR 2015, I described its exponential growth, after IC...

XKCD plots: Deep learning evolution

As a follower of XKCD comics, I knew I needed to try the matplotlib XKCD style. I’ll use it to plot the evolution of the percentage of deep-learning papers i...

Building MatCaffe on Mac OS X El Capitan

So if you’re into computer vision, you are likely dealing with some deep-learning flavoured techniques. This means that you are possibly struggling to compil...

CVPR 2016: Deep learning takes over again?

This is my customary update of percentage of deep-learning papers in the major vision conferences. At CVPR 2015, I described its exponential growth, and afte...

ICCV 2015: Has deep learning reached a plateau in computer vision?

Just after CVPR 2015, I described the exponential growth that deep learning had in vision paper (see the original blog post) by analyzing the paper titles. ...

Word to LaTeX, with Equations

Maybe you have some old documents with nasty equations written in Word, but now you need to re-use them in LaTeX (maybe for your dissertation), and of course...

Solving Sudoku puzzles like a pro (part II)

In part I of this post, I described how to detect and locate a Sudoku grid in the image, and then finding all the grid locations where the numbers and gaps a...

CVPR 2015: Is deep learning in fashion? Scraping vision papers

It is quite obvious that so-called deep learning is in fashion, especially in some fields of computer vision. In this post we would like to quantitatively ev...

Adding flags to the mex Matlab 2014 compiler

Up until Matlab 2013b, one could modify the C/C++ mex compilation flags by editing the mexopts.sh file, usually found in ~/.matlab/mexopts.sh. A common examp...

Moving a lot of files under Linux (aka messing with MS COCO)

Microsoft COCO is a recent annotated database for object detection, segmentation, tagging, etc. It’s one order of magnitude larger than previous similar data...

Solving Sudoku puzzles like a pro (part I)

In the following tutorials I’ll explain how to solve Sudoku puzzles using C++ and OpenCV. We’ll build a program that captures the webcam video, looks for a S...

My experience in building a personal academic website

In this post I’ll share some of my experiences building my personal academic website. I started with the following requirements:

Compile CPLEX in C++ with C++11 Functionalities

CPLEX is a pretty awesome optimization toolbox from IBM, and it is free for academic use. It can be called from C++ (apart from Matlab, Python, etc.), but it...