120 Open source projects that are alternatives of or similar to Keras-for-Co-occurrence-Feature-Learning-from-Skeleton-Data-for-Action-Recognition

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

Official PyTorch code for the ICIP 2021 paper 'Syntactically Guided Generative Embeddings For Zero Shot Skeleton Action Recognition'

NTU-X, which is an extended version of popular NTU dataset

Tools for movie and video research

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

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

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

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

C3D for Keras + TensorFlow

HAKE-Action in PyTorch

EPIC-KITCHENS-55 baselines for Action Recognition

An open-source toolbox for action understanding based on PyTorch

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

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

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

3D ResNets for Action Recognition

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

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

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

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

A lightweight network for body/hand action recognition

ActionVLAD for video action classification (CVPR 2017)

Training Toolbox for Caffe

Weakly Supervised Action Recognition and Detection

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

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

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

A list of the Human-Object Interaction Learning studies.

Temporal Segment Networks (TSN) in PyTorch

TensorFlow code for finetuning I3D model on UCF101.

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

🍴 Annotations for the EPIC KITCHENS-55 Dataset.

Data preparation and loader for AMASS

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

[ICCV 2019 Oral] TA3N: https://github.com/cmhungsteve/TA3N (Most updated repo)

Trajectory-pooled Deep-Convolutional Descriptors

Video Platform for Action Recognition and Object Detection in Pytorch

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

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

Video Classification based on PyTorch

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

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

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

This repo allocate DAPs code of our ECCV 2016 publication

Dynamic Image Networks for Action Recognition

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

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

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

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

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

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

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

Paper list of activity prediction and related area

Video classification tools using 3D ResNet

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

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

Explore Action Recognition

Implementation of "EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition, ICCV, 2019" in PyTorch

Temporal action proposals

Spatio-Temporal Action Localization System