A compact and discriminative face track descriptor

Conference item

Our goal is to learn a compact, discriminative vector representation of a face track, suitable for the face recognition tasks of verification and classification. To this end, we propose a novel face track descriptor, based on the Fisher Vector representation, and demonstrate that it has a number of favourable properties. First, the descriptor is suitable for tracks of both frontal and profile faces, and is insensitive to their pose. Second, the descriptor is compact due to discriminative dimensionality reduction, and it can be further compressed using binarization. Third, the descriptor can be computed quickly (using hard quantization) and its compact size and fast computation render it very suitable for large scale visual repositories. Finally, the descriptor demonstrates good generalization when trained on one dataset and tested on another, reflecting its tolerance to the dataset bias. In the experiments we show that the descriptor exceeds the state of the art on both face verification task (YouTube Faces without outside training data, and INRIA-Buffy benchmarks), and face classification task (using the Oxford-Buffy dataset).

Authors: Parkhi, OM; Simonyan, K; Vedaldi, A; Zisserman, A

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: IEEE
• Host title: 2014 IEEE Conference on Computer Vision and Pattern Recognition
• Pages: 1693-1700
• Publication date: 2014-09-25
• Acceptance date: 2014-03-01
• Event title: 27th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014)
• Event location: Columbus, OH, USA
• Event website: https://cvpr2014.thecvf.com/
• Event start date: 2014-06-23
• Event end date: 2014-06-28
• DOI: 10.1109/cvpr.2014.219
• EISSN: 1063-6919
• EISBN: 9781479951185
• Language: English
• Keywords: binary encoding; encoding; vectors; YouTube Faces dataset; fisher vectors; YouTube; training; face; robustness; face recognition; metric learning; face verification