Skip to content

federico-rosatelli/PyABD

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Fast & Unsupervised Action Boundary Detection (ABD)

University of Bonn

University of Bonn Author: Federico Rosatelli


About the Project

This repository contains a PyTorch implementation of the CVPR 2022 paper "Fast and Unsupervised Action Boundary Detection for Action Segmentation".

The goal of this project is to solve the Temporal Action Segmentation task without relying on frame-wise ground truth during training. Instead of supervised learning, the method utilizes inherent feature similarities to detect Action Boundaries (Change Points) and clusters temporal segments to label actions. This approach is designed to be efficient, low-latency, and applicable to both offline analysis and online streaming scenarios.

Key Features

  • Unsupervised Learning: Does not require frame-by-frame annotations, leveraging the internal consistency of action features.
  • Boundary Detection: Implements a signal processing approach to find local minima in cosine similarity (Change Point Detection).
  • Robust Refinement: Uses a Weighted Merge strategy (Hierarchical Agglomerative Clustering) to fix over-segmentation while preserving temporal duration weights.
  • Dual Mode:
    • Offline: Processes the entire video at once for maximum accuracy (MoF/F1 evaluation).
    • Online (Simulated): A buffer-based streaming processor that respects causal latency for real-time applications.

Technologies Used

Python PyTorch NumPy SciPy Matplotlib

Getting Started

To run the application locally, ensure you have the necessary dependencies installed:

pip install -r requirements.txt

About

A fast, unsupervised video segmentation tool using PyTorch. It detects action boundaries via feature similarity and refines segments with clustering, requiring no training or labels.

Topics

Resources

Stars

Watchers

Forks

Contributors

Languages