Journal on Color Names

In this recent work we investigate how to extend the number of color names beyond the standard set of eleven. The work ‘Beyond Eleven Color Names for Image Understanding‘ is published in Machine Vision and Applications. For more information visit the project website. We also published a workshop paper at WorldCIST conference on color naming for multi-color fashion items.

New postdoc

We are happy to have Abel Gonzalez Garcia join the group as a postdoc.

Review on Computer Vision Techniques in Emergency Situations

Our review article on Computer Vision Techniques in Emergency Situations got accepted in Multimedia Tools and Applications.

2 ICCV 2018 papers accepted

The papers ‘RankIQA: Learning from Rankings for No-reference Image Quality Assessment‘ and ‘Domain-adaptive deep network compression‘ have been accepted for ICCV. Papers and project pages will be soon available. We also have a paper on ‘Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB‘ in the workshop on Physics Based Vision meets Deep Learning (PBDL)

Multimodal Translation Challenge

We obtained first rank on the WMT17 Shared Task on Multimodal Translation in our submission within the M2CR project together with the Le Mans natural language processing group. The system is explained in this WMT2017 paper ‘LIUM-CVC Submissions for WMT17 Multimodal Translation Task‘.

new BMVC accepted

We got a paper accepted with Rada Deeb and Damien Muselet from the Université Jean Monnet at BMVC this year on ‘3D color charts for camera spectral sensitivity estimation’ (pdf).

New TIP accepted

Our paper Improved Recursive Geodesic Distance Computation for Edge Preserving Filter has been accepted for publication in IEEE TIP. Code can be found here.

New Postdoc

We are happy to announce that Luis Herranz has started as a new postdoc on the M2CR project.

WACV2017 paper accepted

Our paper ‘Bandwidth limited object recognition in high resolution imagery (pdf)‘ has been accepted at WACV 2017. The project page with dataset is here.

NIPS wokshop on Adversarial Training

Two papers will be presented at the NIPS workshop on Adversarial Training. “Ensembles of Generative Adversarial Networks” investigates the usage of ensembles for GANs, and shows that they can significantly improve results. “Invertible Conditional GANs for image editing” adds a encoder to a conditional GAN, thereby allowing to do semantic editing of photos. The code is available here.