Teo de Campos

Publications Students Projects Datasets Demos

In July 2016, I moved to the University of Brasilia, where I took a post of Professor Adjunto. However, I still keep a link with the CVSSP/University of Surrey, as a "visiting researcher", where I had worked as a senior research fellow from 2009 to 2016.
From March 2013 to April 2014 I'd also worked in the Machine Learning group at the University of Sheffield.
Previously, I have worked in the research laboratories of Xerox, Microsoft and Sharp.
I completed my DPhil in 2006 at the University of Oxford and my award winning MPhil thesis at the University of Sao Paulo, in 2001.
My research interests include a wide range of computer vision applications, and my current focus include transfer learning, anomaly detection, head tracking for spatial audio and semantic image segmentation.

Please follow this link for a better looking webpage which includes my contact information, but beware that it was generated (semi-)automatically and may not be updated.

See if I'm available.


Google scholar is probably the most up to date page for my list of publications, but it may not point to freely available PDF files or my papers.
The links below offer alternatives, which may include links to demonstrations, datasets, etc.

Students and collaborators

Here is a list of people who work or had worked closely with me or under my (co-)supervision:


(showing the period in which I have been involved, not the duration of the project as a whole):

Relevant activities I've been involved with:



Head/Face Tracking

Here a some demos that I made to evaluate other people's head/face trackers

3D Trackers from my PhD

ACASVA project videos

In the video below, I present a short summary of some of the main aspects of this project:

The video below demonstrates tracking, court detection, homography computation and event detection:

Here is another video, showing the annotation tool that I have developed:

Images as sets of locally weighted features

Follow this link for a talk I presented at Microsoft Research in Cambridge, 2010.

(Fig. 6 of US 2010/0189354)
Last modified: 25 October 2016