LAMP

Aymen’s paper on Context Proposals for Saliency Detection got accepted for CVIU. This work shows how to extend object proposals with context proposals which allow for a precise description of the object’s context. It is shown that these can significantly improve the performance of saliency detection.

The papers ‘Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting‘ has been accepted for ICPR 2018. See here for the (project page) and a BLOG post. Also ‘Weakly Supervised Domain-Specific Color Naming Based on Attention‘ with (project page) has been accepted for publication at ICPR 2018 in Beijing. The paper ‘Learning Illuminant Estimation from Object Recognition‘ has been accepted for ICIP..

Our work on ‘Binary Patterns Encoded Convolutional Neural Networks for Texture Recognition and Remote Sensing Scene Classification‘ has been accepted for publication in ISPRS Journal of Photogrammetry and Remote Sensing.

The presentation at the world mobile congress on the CVPR paper on crowd counting received quite some press coverage.

Members of LAMP got four accepted CVPR 2018 papers. The papers ‘Mix and match networks: encoder-decoder alignment for zero-pair imagetranslation‘ has been accepted, for more information see the project page and this BLOG POST. Xialei has a paper on crowd counting: ‘Leveraging Unlabeled Data for Crowd Counting by Learning to Rank‘ or see the project page.

Also Aitor Alvarez got his paper ‘On the Duality Between Retinex and Image Dehazing‘ accepted in collaboration with Adrian Galdran from INESC TEC Porto, Portugal and Javier Vazquez-Corral, Marcelo Bertalmıo from Universitat Pompeu Fabra. Also Abel Gonzalez got his paper ‘Objects as context for detecting their semantic parts’. The research was performed in his previous group CALVIN with Vitorrio Ferrari.

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.

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

The papers ‘RankIQA: Learning from Rankings for No-reference Image Quality Assessment‘ and ‘Domain-adaptive deep network compression‘ have been accepted for ICCV, see here for a BLOG post on this research. . 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).

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‘.