514 Open source projects that are alternatives of or similar to Awesome Action Recognition

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…

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

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

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

An open-source toolbox for action understanding based on PyTorch

ActionVLAD for video action classification (CVPR 2017)

Paper list of activity prediction and related area

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

C3D for Keras + TensorFlow

Pytorch implementation of the paper "Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points", F. Baradel, C. Wolf, J. Mille , G.W. Taylor, CVPR 2018

[ICCV 2021 Oral] Deep Evidential Action Recognition

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

HAKE-Action in PyTorch

Activity Recognition from 2D pose using an LSTM RNN

Gluon CV Toolkit

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

temporal action detection with SSN

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

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

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

Tools for movie and video research

TensorFlow code for finetuning I3D model on UCF101.

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.

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

Identifying Visible Actions in Lifestyle Vlogs

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

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

3D ResNets for Action Recognition (CVPR 2018)

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

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

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.

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

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

A collection of recent video understanding datasets, under construction!

Temporal Segments LSTM and Temporal-Inception for Activity Recognition

Temporal Segment Networks (TSN) in PyTorch

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

Data preparation and loader for AMASS

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".

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

YAPO e+ - Yet Another Porn Organizer (extended)

Official PyTorch Implementation of "Ego-Pose Estimation and Forecasting as Real-Time PD Control". ICCV 2019.

Modular image processing pipeline using OpenCV and Python generators powered by Detectron2.

Realtime Multi-Person Pose Estimation data server. Used as a training and validation data provider in training process.

RMPE: Regional Multi-person Pose Estimation, forked from Caffe. Research purpose only.

To process/edit video and audio with Python+FFmpeg. [简单实用] 基于Python+FFmpeg的视频和音频的处理/剪辑。

Demonstrations for the interactive exploration of selected core concepts of audio, image and video processing as well as related topics

Audio/Video Processing Service

separate from 6dpose repo for deployment

Skeleton-based method for activity recognition problem

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

Python scripts for performing 3D human pose estimation using the Mobile Human Pose model in ONNX.

Personalized machine learning on the smartphone

Looking to listen at cocktail party

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

Programmatically generate animated GIF from video in Python(convert video to gif)

StarMap for Category-Agnostic Keypoint and Viewpoint Estimation

Deep-learning approaches to object recognition from 3D data

Convert hardsub to softsub