In collaboration with my colleagues in Barcelona, we will present two papers at the upcoming International Conference on Computer Vision in Venice. The first is an approach to domain-adaptive CNN compression:
M. Masana, J. van de Weijer, L. Herranz, A. D. Bagdanov, Jose M. Alvarez, “Domain-adaptive deep network compression.” In: Proceedings of ICCV 2017 (to appear).
And the second is a technique for no-reference image quality assessment that learns from image rankings using an accelerated Siamese network training procedure that we propose:
Xialei Liu, Joost van de Weijer and Andrew D. Bagdanov, “RankIQA: Learning from Rankings for No-reference Image Quality Assessment.” In: Proceedings of ICCV 2017 (to appear).
See you in Venice!