AI Video Action Recognition

Powered by Facebook's TimeSformer model, this application can identify and classify human actions in video clips with state-of-the-art accuracy.

How to Access the Live Demo

This GitHub Pages site shows the project information. To actually upload videos and test the AI model, you need to run the application locally or deploy it to a cloud platform.

Choose one of the deployment options below to start using the video action recognition feature!

How to Use the App

Run Locally

Download and run the application on your computer. This gives you full control and doesn't require any cloud credits.

Setup Guide

Google Colab

Run the app in Google Colab with GPU acceleration. Perfect for quick testing without local installation.

Open Colab

Hugging Face Spaces

Try the live demo hosted on Hugging Face Spaces. Upload your video directly in the browser.

Live Demo

Key Features

AI-Powered Recognition

Uses Facebook's TimeSformer model fine-tuned on Kinetics-400 dataset with 400+ action classes for accurate predictions.

Real-Time Processing

Efficiently processes videos using GPU acceleration when available, with fallback to CPU for universal compatibility.

Easy Upload

Simple drag-and-drop interface supporting multiple video formats (MP4, MOV, AVI, MKV) up to 200MB.

Detailed Results

Get top-k predictions with confidence scores and visual feedback for better understanding of model decisions.

400+ Actions

Recognizes sports, daily activities, musical performances, exercise, work activities, and social interactions.

Open Source

Complete source code available on GitHub with detailed documentation and setup instructions.

Local Installation

1. Clone the Repository

git clone https://github.com/u-justine/VideoActionRecognition.git

2. Setup Environment

cd VideoActionRecognition && python3 -m venv .venv && source .venv/bin/activate

3. Install Dependencies

pip install -r requirements.txt

4. Run the Application

./run_app.sh
Pro Tips
  • If dependencies fail to install, run ./run_fix.sh first
  • The app will open at http://localhost:8501 in your browser
  • Use GPU-enabled environment for faster processing