Journal
INTERNATIONAL JOURNAL OF COMPUTER VISION
Volume 127, Issue 6-7, Pages 743-762Publisher
SPRINGER
DOI: 10.1007/s11263-019-01163-7
Keywords
Adversarial autoencoder; Disentangled representation; Tensor decomposition
Categories
Funding
- EPSRC DTA from Imperial College London
- Partner University Fund
- SUNY2020 Infrastructure Transportation Security Center
- Google Faculty Award
- EPSRC Fellowship DEFORM: Large Scale Shape Analysis of Deformable Models of Humans [EP/S010203/1]
- EPSRC [EP/S010203/1] Funding Source: UKRI
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available