Title
Adversarial Learning Semantic Volume for 2D/3D Face Shape Regression in the Wild.
Abstract
Regression-based methods have revolutionized 2D landmark localization with the exploitation of deep neural networks and massive annotated datasets in the wild. However, it remains challenging for 3D landmark localization due to the lack of annotated datasets and the ambiguous nature of landmarks under the 3D perspective. This paper revisits regression-based methods and proposes an adversarial voxe...
Year
DOI
Venue
2019
10.1109/TIP.2019.2911114
IEEE Transactions on Image Processing
Keywords
Field
DocType
Three-dimensional displays,Two dimensional displays,Face,Heating systems,Shape,Semantics,Task analysis
Voxel,Coordinate vector,ENCODE,Discriminator,Pattern recognition,Regression,Robustness (computer science),Artificial intelligence,Landmark,Semantics,Mathematics
Journal
Volume
Issue
ISSN
28
9
1057-7149
Citations 
PageRank 
References 
0
0.34
16
Authors
3
Name
Order
Citations
PageRank
Hongwen Zhang1132.61
Qi Li25410.18
Zhenan Sun32379139.49