Imperial College London


Faculty of EngineeringDepartment of Computing

Professor in Machine Learning & Computer Vision



+44 (0)20 7594 8461s.zafeiriou Website CV




375Huxley BuildingSouth Kensington Campus






BibTex format

author = {Wang, M and Shu, Z and Cheng, S and Panagakis, Y and Samaras, D and Zafeiriou, S},
doi = {10.1007/s11263-019-01163-7},
journal = {International Journal of Computer Vision},
pages = {743--762},
title = {An adversarial neuro-tensorial approach for learning disentangled representations},
url = {},
volume = {127},
year = {2019}

RIS format (EndNote, RefMan)

AB - Several factors contribute to the appearance of an object in a visual scene, including pose, illumination, and deformation, among others. Each factor accounts for a source of variability in the data, while the multiplicative interactions of these factors emulate the entangled variability, giving rise to the rich structure of visual object appearance. Disentangling such unobserved factors from visual data is a challenging task, especially when the data have been captured in uncontrolled recording conditions (also referred to as “in-the-wild”) and label information is not available. In this paper, we propose a pseudo-supervised deep learning method for disentangling multiple latent factors of variation in face images captured in-the-wild. To this end, we propose a deep latent variable model, where the multiplicative interactions of multiple latent factors of variation are explicitly modelled by means of multilinear (tensor) structure. We demonstrate that the proposed approach indeed learns disentangled representations of facial expressions and pose, which can be used in various applications, including face editing, as well as 3D face reconstruction and classification of facial expression, identity and pose.
AU - Wang,M
AU - Shu,Z
AU - Cheng,S
AU - Panagakis,Y
AU - Samaras,D
AU - Zafeiriou,S
DO - 10.1007/s11263-019-01163-7
EP - 762
PY - 2019///
SN - 0920-5691
SP - 743
TI - An adversarial neuro-tensorial approach for learning disentangled representations
T2 - International Journal of Computer Vision
UR -
UR -
VL - 127
ER -