A Deep Regression Architecture with Two-Stage Re-initialization for High Performance Facial Landmark Detection
Citations
1,278 citations
512 citations
371 citations
357 citations
Cites background or methods from "A Deep Regression Architecture with..."
...The second one is the Two-stage Re-initialisation Deep Regression Network (TR-DRN) [39]....
[...]
...Also, our CNN-6/7 model is much faster than most existing DNNbased facial landmark localisation approaches such as TRDRN [39]....
[...]
...The speed of TR-DRN is 83 fps on an NVIDIA GeForce GTX Titan X card....
[...]
...The second one is the Two-stage Re-initialisation Deep Regression Network (TR-DRN) [41]....
[...]
...The result is better than CCL in terms accuracy but worse than DAC-CSR and TR-DRN....
[...]
221 citations
References
13,037 citations
12,531 citations
11,866 citations
"A Deep Regression Architecture with..." refers methods in this paper
...PReLU [10] is adopted as the activation functions....
[...]
11,732 citations
10,161 citations
"A Deep Regression Architecture with..." refers methods in this paper
...The above four models are all implemented on Caffe platform [15]....
[...]