Abstract | ||
---|---|---|
We propose a novel end-to-end deep architecture for face landmark detection, based on a deep convolutional and deconvolutional network followed by carefully designed recurrent network structures. The pipeline of this architecture consists of three parts. Through the first part, we encode an input face image to resolution-preserved deconvolutional feature maps via a deep network with stacked convol... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/TCSVT.2016.2645723 | IEEE Transactions on Circuits and Systems for Video Technology |
Keywords | DocType | Volume |
Feature extraction,Face,Shape,Visualization,Computer architecture,Pipelines,Image resolution | Journal | 28 |
Issue | ISSN | Citations |
5 | 1051-8215 | 4 |
PageRank | References | Authors |
0.44 | 26 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hanjiang Lai | 1 | 234 | 17.67 |
Shengtao Xiao | 2 | 88 | 6.45 |
Yan Pan | 3 | 179 | 19.23 |
Zhen Cui | 4 | 580 | 41.43 |
Jiashi Feng | 5 | 2165 | 140.81 |
Chunyan Xu | 6 | 169 | 18.10 |
Jian Yin | 7 | 861 | 97.01 |
Shuicheng Yan | 8 | 9701 | 359.54 |