Top 121 action-recognition open source projects

Code/Model release for NIPS 2017 paper "Attentional Pooling for Action Recognition"

A Python module to decode video frames directly, using the FFmpeg C API.

Spatio-Temporal Action Localization System

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

Codes for popular action recognition models, verified on the something-something data set.

[BMVC 2018] iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection

Comprehensive, latest, and deployable video deep learning algorithm, including video recognition, action localization, and temporal action detection tasks. It's a high-performance, light-weight codebase provides practical models for video understanding research and application

[ICCV 2019 (Oral)] Temporal Attentive Alignment for Large-Scale Video Domain Adaptation (PyTorch)

ActionVLAD for video action classification (CVPR 2017)

PyTorch 3D video classification models pre-trained on 65 million Instagram videos

STEP: Spatio-Temporal Progressive Learning for Video Action Detection. CVPR'19 (Oral)

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

Implementation Code of the paper Optical Flow Guided Feature, CVPR 2018

Data preparation and loader for AMASS

Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"

Video Platform for Action Recognition and Object Detection in Pytorch

Dataset and code for the paper "First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations", CVPR 2018.

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

C3D for Keras + TensorFlow

Dynamic Image Networks for Action Recognition

A lightweight network for body/hand action recognition

Timeception for Complex Action Recognition, CVPR 2019 (Oral Presentation)

Weakly Supervised Action Recognition and Detection

Paper list of activity prediction and related area

A list of the Human-Object Interaction Learning studies.

Explore Action Recognition

HAKE: Human Activity Knowledge Engine (CVPR'18/19/20, NeurIPS'20)

Exploration of different solutions to action recognition in video, using neural networks implemented in PyTorch.

An open-source toolbox for action understanding based on PyTorch

TensorFlow code for finetuning I3D model on UCF101.

Skeleton-based Action Recognition Papers and Small Notes and Top 2 Leaderboard for NTU-RGBD

🍴 Annotations for the EPIC KITCHENS-55 Dataset.

keras implementation of inflated 3d from Quo Vardis paper + weights

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

Tools for movie and video research

Trajectory-pooled Deep-Convolutional Descriptors

3D ResNets for Action Recognition

Generic PyTorch Dataset Implementation for Loading, Preprocessing and Augmenting Video Datasets

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

Video Classification based on PyTorch

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

To keep updates with VRU Grand Challenge, please use https://github.com/NExTplusplus/VidVRD-helper

HAKE-Action in PyTorch

This repo allocate DAPs code of our ECCV 2016 publication

[CVPR 2021] TDN: Temporal Difference Networks for Efficient Action Recognition

As a part of the HAKE project, includes the reproduced SOTA models and the corresponding HAKE-enhanced versions (CVPR2020).

EPIC-KITCHENS-55 baselines for Action Recognition

Real time Fight Detection Based on 2D Pose Estimation and RNN Action Recognition

Training Toolbox for Caffe

ResGCN: an efficient baseline for skeleton-based human action recognition.

Detects Chinese traffic police commanding poses 检测中国交警指挥手势

Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection

Use 3D ResNet to extract features of UCF101 and HMDB51 and then classify them.

Video classification tools using 3D ResNet

Temporal Segment Networks (TSN) in PyTorch

Hierarchical Co-occurrence Network with Prototype Loss for Few-shot Learning (PyTorch)

Action recognition.基于C3D的视频动作识别

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

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

temporal action detection with SSN