120 Open source projects that are alternatives of or similar to Action_recognition_zoo

This repo allocate DAPs code of our ECCV 2016 publication

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

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

Video Classification based on PyTorch

temporal action detection with SSN

Paper list of activity prediction and related area

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

Video Platform for Action Recognition and Object Detection in Pytorch

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

🍴 Annotations for the EPIC KITCHENS-55 Dataset.

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

Apply ML to the skeletons from OpenPose; 9 actions; multiple people. (WARNING: I'm sorry that this is only good for course demo, not for real world applications !!! Those ary very difficult !!!)

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

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

Data preparation and loader for AMASS

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

Explore Action Recognition

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

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

Video classification tools using 3D ResNet

TensorFlow code for finetuning I3D model on UCF101.

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

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

Gluon CV Toolkit

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

3D ResNets for Action Recognition

A collection of recent video understanding datasets, under construction!

A lightweight network for body/hand action recognition

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

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

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

Weakly Supervised Action Recognition and Detection

HAKE-Action in PyTorch

ActionVLAD for video action classification (CVPR 2017)

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

A list of the Human-Object Interaction Learning studies.

EPIC-KITCHENS-55 baselines for Action Recognition

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

Training Toolbox for Caffe

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

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

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

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

An open-source toolbox for action understanding based on PyTorch

Temporal Segment Networks (TSN) in PyTorch

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

Action recognition.基于C3D的视频动作识别

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

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

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

Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101

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

PyTorch implementation of two-stream networks for video action recognition

C3D for Keras + TensorFlow

Tools for movie and video research

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

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

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

Dynamic Image Networks for Action Recognition

Trajectory-pooled Deep-Convolutional Descriptors