About me

Joost van de Weijer
Position: Senior Scientist
Centre de Visió per Computador
Universitat Autònoma de Barcelona
Edifici O, Campus UAB
08193 – Bellaterra – Cerdanyola – Spain
Fax: +34 93 581 1670
Tel: +34 93 581 3036
E-mail: joost AT cvc DOT uab DOT es
I am the leader of the Learning and Machine Perception Team (LAMP) and a senior researcher at the Computer Vision Center (Universitat Autònoma de Barcelona). My main research interest is in applying color imaging theory to the field of computer vision: color constancy, color naming, object recognition, recoloring algorithms, color feature detection and color feature extraction.

An overview of my publications is available in Google Scholar.

Latest Publication

  • M. Masana, J. van de Weijer, L. Herranz, A. D. Bagdanov, and J. M. Alvarez, “Domain-adaptive deep network compression,” in International conference on computer vision (iccv), 2017.
    [PDF] | [URL] | [Bibtex]
    title={Domain-adaptive deep network compression},
    author={Masana, Marc and van de Weijer, Joost and Herranz, Luis and Bagdanov, Andrew D and Alvarez, Jose M},
    booktitle={International conference on Computer Vision (ICCV)},
    url = {https://github.com/mmasana/DALR}

  • X. Liu, J. van de Weijer, and A. D. Bagdanov, “Rankiqa: learning from rankings for no-reference image quality assessment,” in International conference on computer vision (iccv), 2017.
    [PDF] | [URL] | [Bibtex]
    title={RankIQA: Learning from Rankings for No-reference Image Quality Assessment},
    author={Liu, Xialei and van de Weijer, Joost and Bagdanov, Andrew D},
    booktitle={International conference on Computer Vision (ICCV)},
    url = {https://github.com/xialeiliu/RankIQA}

  • M. Mozerov and J. van de Weijer, “Improved recursive geodesic distance computation for edge preserving filter,” Ieee transactions on image processing, vol. 26, iss. 8, pp. 3696-3706, 2017.
    [PDF] | [DOI [DOI]] | [URL] | [Bibtex]
    title={Improved Recursive Geodesic Distance Computation for Edge Preserving Filter},
    author={Mozerov, Mikhail and van de Weijer, Joost},
    journal={IEEE Transactions on Image Processing},
    doi = "10.1109/TIP.2017.2705427",
    url = {http://www.cvc.uab.es/~mozerov/IGDF/INDEX.htm}


I will serve as an area chair for ICCV 2017.


I will serve as an area chair for ECCV 2016 and ICPR 2016.

Hand-on Deep Learning Course

We are organizing a course on hands-on deep learning.

Color in Texture and Material Recognition

We are organizing a special section on “Color in Texture and Material Recognition” in the Journal of Electronic Imaging.

TIP on Fast Bilateral Filtering

Our paper on ‘Global color sparseness and a local statistics prior for fast bilateral filtering’ got accepted by TIP. The pdf and code are available here.

ICCV paper

One paper got accepted at ICCV. The paper ‘From emotions to action units with hidden and semi-hidden-task learning’ can be found on this project web page.

TIP on action recognition

Our paper on ‘“Recognizing actions through action-specific person detection’ investigates the usage of transfer learning for action recognition. The paper and supplementary material can be found here.

Scientific Advisor

I am scientific advisor for Wide Eyes Technologies, a start-up company in Barcelona in the field of online fashion applications.