G. Tolias - Γ. Τόλιας

Giorgos Tolias

I am an assistant professor at the Czech Technical University in Prague and a member of the Visual Recognition Group (VRG). Before I was a postdoc at the LinkMedia team of Inria Rennes. I obtained my Ph.D from the National Technical University of Athens where I worked with the Image and Video Analysis Team (IVA). My research is on computer vision with a focus on large scale visual recognition.


Oct2020: New but old: Python implementation of ASMK: sota retrieval approach with local descriptors since 2013!

Jul2021:Two papers accepted at ECCV 2020: local descriptors for instance recognition (oral) and learning with few clean and many noisy examples.

Jan2020:The Vision and Sports Summer School is back: VS3 2020

Jan2020:I will serve as an Area Chair for ECCV 2020.

Oct2019:Talk at the Large-Scale Visual Place Recognition and Image-Based Localization tutorial at ICCV 2019.

Jul2019:One paper accepted at ICCV 2019 on targeted mismatch attacks: paper and code.

Mar2019:Two papers accepted at CVPR 2019: deep local descriptors and semi-supervised deep learning.

Nov2018:Our local descriptor paper was accepted at IJCV.

Oct2018:Code, training data, and models available for deep shape matching.

Oct2018:Hybrid diffusion accepcted to ACCV 2018.

Sep2018:Code available for our Mining on Manifolds CVPR 2018 paper.

Jul2018:One paper on Deep Shape Matching accepted at ECCV 2018.

Jun2018: Our team was ranked 3rd in the Google Landmark Recognition Challenge: see presentation

May2018: Our work on image retrieval with CNNs is accepted at PAMI. Available implementations in MatConvNet and PyTorch.

Mar2018: Three papers accepted at CVPR 2018: Mining on Manifolds, Fast Spectral Ranking, and Revisiting Oxford and Paris.

Jan2018: Co-organizing the Large-Scale Landmark Recognition: A Challenge at CVPR 2018.

A.B@cmp.felk.cvut.cz (replace A by giorgos and B by tolias)
Karlovo namesti 13, 121 35 Praha 2, Czech Republic
Office: G3 (building G, room 3),