Name
Abstract | ||
|---|---|---|
Deep generative modelling for robust human body analysis is an emerging problem with many interesting applications, since it enables analysis-by-synthesis and unsupervised learning. However, the latent space learned by such models is typically not human-interpretable, resulting in less flexible models. In this work, we adopt a structured semi-supervised variational auto-encoder approach and present a deep generative model for human body analysis where the pose and appearance are disentangled in the latent space, allowing for pose estimation. Such a disentanglement allows independent manipulation of pose and appearance and hence enables applications such as pose-transfer without being explicitly trained for such a task. In addition, the ability to train in a semi-supervised setting relaxes the need for labelled data. We demonstrate the merits of our generative model on the Human3.6M and ChictopiaPlus datasets. |
Year | Venue | Field |
|---|---|---|
2018 | arXiv: Computer Vision and Pattern Recognition | Computer science,Pose,Unsupervised learning,Artificial intelligence,Generative grammar,Machine learning,Generative model |
DocType | Volume | Citations |
Journal | abs/1804.06364 | 1 |
PageRank | References | Authors |
0.35 | 31 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Rodrigo De Bem | 1 | 17 | 4.66 |
| Arnab Ghosh | 2 | 1 | 0.35 |
| Thalaiyasingam Ajanthan | 3 | 1 | 2.38 |
| Miksik Ondrej | 4 | 403 | 14.28 |
| n siddharth | 5 | 23 | 5.16 |
| Philip H. S. Torr | 6 | 9140 | 636.18 |