期刊
INTERNATIONAL JOURNAL OF COMPUTER VISION
卷 127, 期 6-7, 页码 743-762出版社
SPRINGER
DOI: 10.1007/s11263-019-01163-7
关键词
Adversarial autoencoder; Disentangled representation; Tensor decomposition
资金
- 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
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据