OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

Gluon CV Toolkit

A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.

3D ResNets for Action Recognition (CVPR 2018)

Code & Models for Temporal Segment Networks (TSN) in ECCV 2016

Train, Evaluate, Optimize, Deploy Computer Vision Models via OpenVINO™

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.

An open-source toolbox for action understanding based on PyTorch

The collection of pre-trained, state-of-the-art AI models for ailia SDK

Temporal Segment Networks (TSN) in PyTorch

Apply ML to the skeletons from OpenPose; 9 actions; multiple people. (WARNING: I'm sorry that this is only good for course demo, not for real world applications !!! Those ary very difficult !!!)

Video classification tools using 3D ResNet

Using two stream architecture to implement a classic action recognition method on UCF101 dataset

A toolbox for skeleton-based action recognition.

temporal action detection with SSN

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

PyTorch implementation of two-stream networks for video action recognition

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

[CVPR 2020 Oral] PyTorch implementation of "Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition"

[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking