Risa Shinoda's starred repositories
layout-parser
A Unified Toolkit for Deep Learning Based Document Image Analysis
pdffigures2
Given a scholarly PDF, extract figures, tables, captions, and section titles.
mmdetection
OpenMMLab Detection Toolbox and Benchmark
Pets-Face-Recognition
Animal identification using face recognition based methods
pytorch-i3d-feature-extraction
Code for I3D Feature Extraction
kinetics_i3d_pytorch
Inflated i3d network with inception backbone, weights transfered from tensorflow