Top 121 action-recognition open source projects

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

Gluon CV Toolkit

PyTorch implementation of two-stream networks for video action recognition

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 !!!)

A collection of recent video understanding datasets, under construction!

Skeleton-based Action Recognition

Action recognition using soft attention based deep recurrent neural networks

A curated list of action recognition and related area resources

This repository host the code for real-time action detection paper

3D ResNets for Action Recognition (CVPR 2018)

[ICCV 2021 Oral] Deep Evidential Action Recognition

A new codebase for Group Activity Recognition. It contains codes for ICCV 2021 paper: Spatio-Temporal Dynamic Inference Network for Group Activity Recognition and some other methods.

Using deep learning to perform action recognition in the sport of tennis.

Implementation of "Slow-Fast Auditory Streams for Audio Recognition, ICASSP, 2021" in PyTorch

Identifying Visible Actions in Lifestyle Vlogs

基于kinect 的人体 动作识别

ICCV 19 Grouped Spatial-Temporal Aggretation for Efficient Action Recognition

Deep Learning for Computer Vision (CommE 5052) in NTU

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

An implementation of the LRCN in Torch

Learning Video Representations from Correspondence Proposals (CVPR 2019 Oral)

End-to-end Temporal Action Detection with Transformer. [Under review for a journal publication]

Deep Convolutional Bidirectional LSTM for Complex Activity Recognition with Missing Data. Human Activity Recognition Challenge. Springer SIST (2020)

No description or website provided.

REPresentAtion bIas Removal (REPAIR) of datasets

code for CVPR-2019 paper: Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics

The official PyTorch implementation of "Context Matters: Self-Attention for sign Language Recognition"

Surveillance System Against Violence

Temporal Convolutional Feature Pyramid Network (TCFPN) & Iterative Soft Boundary Assignment (ISBA), CVPR '18

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

Code for AdaScan: Adaptive Scan Pooling (CVPR 2017)

ICCV2021/2019/2017 论文/代码/解读/直播合集，极市团队整理

Two Stream CNN implemented in Keras using in skeleton-based action recognition with dataset NTU RGB+D

A Repository for maintaining various human skeleton preprocessing steps in numpy and tensorflow along with tensorflow model to learn pose embeddings.

Count pushups from video/webcam. Tech stack: Keypoint detection, BlazePose, action recognition.

experiments on classifying actions using poses

[CVPR2021] UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles

Out-of-Distribution Detection for Generalized Zero-Shot Action Recognition

This repository contains the code implementation used in the paper Temporally Coherent Embeddings for Self-Supervised Video Representation Learning (TCE).

[ECCV 2020] Official Pytorch implementation for "Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification". SOTA results for ZSL and GZSL

A public Python implementation for generating Dynamic Images introduced in 'Dynamic Image Networks for Action Recognition' by Bilen et al.

Code for : [Pattern Recognit. Lett. 2021] "Learn to cycle: Time-consistent feature discovery for action recognition" and [IJCNN 2021] "Multi-Temporal Convolutions for Human Action Recognition in Videos".

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

The collection of pre-trained, state-of-the-art AI models for ailia SDK

GUI based on the python api of openpose in windows using cuda10 and cudnn7. Support body , hand, face keypoints estimation and data saving. Realtime gesture recognition is realized through two-layer neural network based on the skeleton collected from the gui.

Action-Localization, Atomic Visual Actions (AVA) Dataset

[WACV'22] Code repository for the paper "Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting", https://arxiv.org/abs/2106.10137.

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…

Offical implementation of paper "MSAF: Multimodal Split Attention Fusion"

[CVPR 2021] Multi-shot Temporal Event Localization: a Benchmark

PyTorch implementation of a collections of scalable Video Transformer Benchmarks.

The official Codes for NeurIPS 2019 paper. Quanfu Fan, Ricarhd Chen, Hilde Kuehne, Marco Pistoia, David Cox, "More Is Less: Learning Efficient Video Representations by Temporal Aggregation Modules"

Action recognition with C3D network implemented in tensorflow

Video Recognition using Mixed Convolutional Tube (MiCT) on PyTorch with a ResNet backbone

No description or website provided.

Two-stream CNNs for video action recognition implemented in Keras

Keras implementation for Co-occurrence-Feature-Learning-from-Skeleton-Data-for-Action-Recognition

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

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

Temporal action proposals