S
Stefanos Zafeiriou
Researcher at Imperial College London
Publications - 406
Citations - 26443
Stefanos Zafeiriou is an academic researcher from Imperial College London. The author has contributed to research in topics: Facial recognition system & Computer science. The author has an hindex of 60, co-authored 375 publications receiving 17993 citations. Previous affiliations of Stefanos Zafeiriou include Huawei & Aristotle University of Thessaloniki.
Papers
More filters
Journal ArticleDOI
A robust similarity measure for volumetric image registration withźoutliers
Patrick Snape,Stefan Pszczolkowski,Stefanos Zafeiriou,Georgios Tzimiropoulos,Christian Ledig,Daniel Rueckert +5 more
TL;DR: This paper proposes a global similarity measure that is robust to both intensity inhomogeneities and outliers without requiring prior knowledge of the type of outliers and proposes two novel similarity measures based on the cosine of normalised 3D volumetric gradients.
Journal ArticleDOI
PD 2 T: Person-Specific Detection, Deformable Tracking
TL;DR: This work argues that generic fitting per frame is suboptimal and proposes to learn person-specific statistics from the video to improve the generic results, and introduces a meticulously studied pipeline, which is named PD2T, that performs person- specific detection and landmark localisation.
Proceedings Article
4DFAB: a large scale 4D facial expression database for biometric applications
TL;DR: The 4DFAB dataset as mentioned in this paper is a large scale database of dynamic high-resolution 3D faces (over 1,800,000 3D meshes) captured in four different sessions spanning over a five-year period.
Journal ArticleDOI
Variational Infinite Hidden Conditional Random Fields
Konstantinos Bousmalis,Stefanos Zafeiriou,Louis-Philippe Morency,Maja Pantic,Zoubin Ghahramani +4 more
TL;DR: It is shown that the variational HCRF-DPM is able to converge to a correct number of represented hidden states, and performs as well as the best parametric HCRFs—chosen via cross-validation—for the difficult tasks of recognizing instances of agreement, disagreement, and pain in audiovisual sequences.
Proceedings ArticleDOI
Deep Analysis of Facial Behavioral Dynamics
TL;DR: This paper proposes the first, to the best of the knowledge, methodology for extracting lowdimensional latent dimensions that correspond to facial dynamics (i.e., motion of facial parts) and develops appropriate unsupervised and supervised deep autoencoder architectures, which are able to extract features that correspondto facial dynamics.