Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks

Faster R-CNN

R-CNN: Regions with Convolutional Neural Network Features

Total Text Dataset. It consists of 1555 images with more than 3 different text orientations: Horizontal, Multi-Oriented, and Curved, one of a kind.

SPP_net : Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

Code release for "Spatiotemporal Residual Networks for Video Action Recognition", NIPS16 & "Spatiotemporal Multiplier Networks for Video Action Recognition", CVPR17.

Implement for ``Learning Deep Features via Congenerous Cosine Loss for Person Recognition''

ORION: Orientation-boosted Voxel Nets for 3D Object Recognition

samf code