Structured Edge Detection Toolbox

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

RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation

Learning Rich Features from RGB-D Images for Object Detection and Segmentation

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

train test labels for sunrgbd

Deep Filter Banks for Texture Recognition, Description and Segmentation (CVPR15)

Train fully convonlutional neural networks for brain segmentation.