This isn't really face recognition, this is face verification. In computer vision, face recognition usually means tell me who this person is (in psychology it means "have you seen this person before?"). Face verification gives an algorithm (or a person) two images of faces and asks, "Are these the same person?"
Their result is impressive, and it improves a bit over Facebook's recent result on the same dataset with their DeepFace system (97.35% for DeepFace vs 97.53% for people vs 98.52% for the system discussed in the article).
Also, it is interesting that they are not using deep learning for this. They are using a Discriminative Gaussian Process Latent Variable Model.
Their result is impressive, and it improves a bit over Facebook's recent result on the same dataset with their DeepFace system (97.35% for DeepFace vs 97.53% for people vs 98.52% for the system discussed in the article).
Also, it is interesting that they are not using deep learning for this. They are using a Discriminative Gaussian Process Latent Variable Model.