slowfast

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.

Yolov5+SlowFast: Realtime Action Detection Based on PytorchVideo

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

A PyTorch implementation of "SlowFast Networks for Video 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"

Code for discovering slow timescale dynamics using the SINDy method

PyTorch implementation of SlowFast network.

[CVPR 2019] SlowFast Networks for Video Recognition

Human Action Recognition

Make AVADataset custom dataset.

An advanced action recognition and Video Classifier

Yolov11 for object detection and Deepsort_oh for object tracking together with official SlowFast for action detection

Implementation of FICC 2024 paper "Benchmarking Jetson Edge Devices with an End-to-end Video-based Anomaly Detection System"

Multimodal version of SlowFast (Vision + Audio inputs)

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