Action Recognition Python Packages

gluoncv

Gluon CV Toolkit

mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

otx

Build computer vision models in a fraction of the time and with less data.

getitune

Build computer vision models in a fraction of the time and with less data.

modelfeast

Pytorch model zoo for human, include all kinds of 2D CNN, 3D CNN, and CRNN

gluoncv-torch

Gluon CV Toolkit

vidchain

VidChain: High-fidelity multimodal RAG framework featuring the IRIS Intelligence Agent

dlc2action

DLC2Action is a deep learning based action segmentation toolbox. It is designed to work directly on top of markerless pose estimation softwares such as DeepLabCut. It allows to train and evaluate various state-of-the-art action segmentation models on your own data.

ppvideo

Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video tagging and sport action detection.

mmaction

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

paddlevideo

Awesome Video toolkits based on PaddlePaddle

t50metrics

A example Python package

otxmmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark