Can I read Unsupervised Video Summarization Techniques on EtoBox?

Unsupervised Video Summarization Techniques by Laith Qasem is a document available to read on EtoBox.

What is Unsupervised Video Summarization Techniques about?

This document proposes an unsupervised framework for video summarization using keyframe extraction and video skimming. It extracts features from video frames using both traditional computer vision techniques like histograms and SIFT, as well as deep learning features from a CNN. These features are then clustered using K-means or Gaussian clustering to select keyframes. Video skims of 1.5 seconds around each keyframe are combined to generate the final summary. The framework is tested on the SumMe dataset and

Author

Laith Qasem

Language

EN