OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

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.

Multimodal version of SlowFast (Vision + Audio inputs)

An advanced action recognition and Video Classifier

Make AVADataset custom dataset.

Yolov5+SlowFast: Realtime Action Detection Based on PytorchVideo

Load a SlowFast model, load the weights and modify the head to be used in another project

Human Action Recognition

Video classification exercise using UCF101 data for training an early-fusion and SlowFast architecture model, both using the PyTorch Lightning framework.

A PyTorch implementation of SlowFast based on ICCV 2019 paper "SlowFast Networks for Video Recognition"

Video Feature Extraction Code for EMNLP 2020 paper "HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training"

Code for discovering slow timescale dynamics using the SINDy method

PyTorch implementation of SlowFast network.

[CVPR 2019] SlowFast Networks for Video Recognition

A PyTorch implementation of "SlowFast Networks for Video Recognition"