PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.

Pytorch porting of C3D network, with Sports1M weights

Video Platform for Action Recognition and Object Detection in Pytorch

Real-World Anomaly Detection in Surveillance Videos

C3D for Keras + TensorFlow

Video-friendly caffe -- comes with the most recent version of Caffe (as of Jan 2019), a video reader, 3D(ND) pooling layer, and an example training script for C3D network and UCF-101 data

Abnormal Human Behaviors Detection/ Road Accident Detection From Surveillance Videos/ Real-World Anomaly Detection in Surveillance Videos/ C3D Feature Extraction

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

A one stop shop for all of your activity recognition needs.

Violence Detection using 3D Convolutional Neural Networks

Large-scale, Fast and Accurate Shot Boundary Detection through Spatio-temporal Convolutional Neural Networks

What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment [CVPR 2019]

A PyTorch implementation of R2Plus1D and C3D based on CVPR 2017 paper "A Closer Look at Spatiotemporal Convolutions for Action Recognition" and CVPR 2014 paper "Learning Spatiotemporal Features with 3D Convolutional Networks"

Information of public available data sets for biomechanics.

My experimentation around action recognition in videos. Contains Keras implementation for C3D network based on original paper "Learning Spatiotemporal Features with 3D Convolutional Networks", Tran et al. and it includes video processing pipelines coded using mPyPl package. Model is being benchmarked on popular UCF101 dataset and achieves result…

Inflated 3D ConvNets for video understanding

Video Representation Learning by Recognizing Temporal Transformations. In ECCV, 2020.

C3D-LSTM implementation in PyTorch [WACV 2019]

An Online Web Game "You Perform, I Guess!" based on C3D Model

Extract and visualize gait data