Open-source alternatives to VTHCL

An efficient video loader for deep learning with smart shuffling that's super easy to digest

:platewithcutlery: Annotations for the public release of the EPIC-KITCHENS-100 dataset

C3D is a modified version of BVLC caffe to support 3D ConvNets.

VMZ: Model Zoo for Video Modeling

SlowFast is a PyTorch video understanding framework and spatiotemporal neural network library. It serves as a toolset for video action recognition, enabling the training and evaluation of models designed to classify complex activities and objects within video sequences. The framework is distinguished by its use of dual-pathway spatiotemporal sampling to capture both slow and fast motions. It supports self-supervised video learning for pre-training models on unlabeled data and employs multigrid spatiotemporal training to optimize learning across multiple spatial and temporal resolutions. The

Long-Term Feature Banks for Detailed Video Understanding

Non-local Neural Networks for Video Classification

Code release for "Convolutional Two-Stream Network Fusion for Video Action Recognition", CVPR 2016.

A repository of common methods, datasets, and tasks for video research

Long-term Temporal Convolutions for Action Recognition, TPAMI 2018

Train action classification model based on individual frames

Code and training data for our ECCV 2016 paper on Unsupervised Learning

PyTorch implementation of the R2Plus1D convolution based ResNet architecture described in the paper "A Closer Look at Spatiotemporal Convolutions for Action Recognition"

This project is a PyTorch implementation of 3D residual networks designed for video action recognition. It provides a spatiotemporal architecture that analyzes both spatial frames and temporal motion to classify human activities within video clips. The system includes a distributed model training framework to accelerate learning across multiple compute nodes. It supports the deployment and fine-tuning of pre-trained model weights, allowing the adaptation of existing networks to specific new datasets. The codebase covers the full pipeline for spatiotemporal learning, including video dataset p

Joint-task Self-supervised Learning for Temporal Correspondence (NeurIPS 2019)

Human action classification for video, offline and natively on iOS via Core ML

Temporal Relation Networks

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

An open-source toolbox for action understanding based on PyTorch

mmaction2 is a PyTorch video understanding toolbox designed for training and evaluating deep learning models. It serves as a framework for action recognition, temporal localization, and spatio-temporal action detection, providing specialized tools for both pixel-based video analysis and skeleton-based action recognition. The project distinguishes itself through a modular architecture featuring registry-based component discovery and hierarchical, config-driven model assembly. It supports multi-modal feature fusion, integrating RGB frames, optical flow, and audio, and includes capabilities for