🚗 Detect driver distractions in images for improved road safety by predicting behavior like texting, talking, and reaching behind the wheel.

Human action classification system with pose-based (MediaPipe) and video-based (3D CNN) models. Features 100+ architectures for real-time pose classification and temporal models pretrained on UCF-101/HMDB51.

Enhancing Human Action Recognition with GAN-based Data Augmentation

RehabAI: An AI-Powered Web App for Remote Physical Therapy

[AAAI-2024] HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors

A real-time inferencing of multistreaming YOWOv3(Spatio Temporal Action Detection task) using (UCF101-24) dataset. The repo is extension of https://github.com/Hope1337/YOWOv3, https://arxiv.org/pdf/2408.02623

Code repository for the paper "Interaction-aware Scene Debiasing for Action Recognition"

Activity Recognition using Temporal Optical Flow Convolutional Features and Multi-Layer LSTM

An AI-powered Human Action Recognition system that classifies 15 common human activities using deep learning and computer vision. Built with TensorFlow, Keras, and OpenCV, the system supports real-time predictions from live camera feeds or uploaded images/videos through a user-friendly PyQt interface.

Surveillance Perspective Human Action Recognition Dataset: 7759 Videos from 14 Action Classes, aggregated from multiple sources, all cropped spatio-temporally and filmed from a surveillance-camera like position.

A Human Action Recognition (HAR) model combining 3D CNN and LSTM networks to accurately recognize actions in videos using spatial-temporal feature extraction. Trained on UCF-50 and outperforming existing architectures.

This repository contains the implementation of a system for Human Action Recognition (HAR) using depth map data. The system is designed to assist individuals with dementia in bathroom settings by recognizing human actions in a privacy-preserving manner.

Human Action Recognition example using TensorFlow on smartphone sensors dataset and an LSTM RNN. Classifying the type of movement amongst six activity categories - Hirakawa

This repository provides implementation of a baseline method and our proposed methods for efficient Skeleton-based Human Action Recognition.

Implementation of ST-GCN for continuous inference and a novel lightweight realtime RT-ST-GCN

Real-Time Spatio-Temporally Localized Activity Detection by Tracking Body Keypoints

Human Activity Recognition Research Repository

11000-Image-Video-caption-data-of-human-action

Master project for MSIT 2024 - Towards Efficient Human Action Recognition: The Role of Keyframe Selection in Video Processing