deeplearningpapers
object detection
two-stage
one-stage
keypoint detection/pose estimation
-
CPN: Cascaded Pyramid Network for Multi-Person Pose Estimation
- code here
-
Simple Baselines for Human Pose Estimation and Tracking
- code here
Training Tricks
face detection
scene text detection and recognition
end to end
-
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
-
TextBoxes++: A Single-Shot Oriented Scene Text Detector
- code here
-
Rosetta: Large Scale System for Text Detection and Recognition in Images