no code implementations • 7 Oct 2016 • A. Mahendran, H. Bilen, J. F. Henriques, A. Vedaldi
In this short note we introduce ResearchDoom, an implementation of the Doom first-person shooter that can extract detailed metadata from the game.
no code implementations • 10 May 2015 • S. Tsogkas, I. Kokkinos, G. Papandreou, A. Vedaldi
We also investigate the performance of our approach ``in the wild'', without information concerning the objects' bounding boxes, using an object detector to guide a multi-scale segmentation scheme.
1 code implementation • 1 Jan 2015 • O. M. Parkhi, A. Vedaldi, A. Zisserman
The goal of this paper is face recognition -- from either a single photograph or from a set of faces tracked in a video.
Ranked #4 on Face Verification on Labeled Faces in the Wild (using extra training data)