Fast Graph Sampling for Short Video Summarization using Gershgorin Disc Alignment
Sadid Sahami, Gene Cheung, Chia-Wen Lin

TL;DR
This paper introduces a fast graph sampling algorithm for short video summarization that leverages Gershgorin disc alignment to efficiently select keyframes, achieving comparable results to state-of-the-art methods with lower computational complexity.
Contribution
The paper proposes a novel graph sampling method based on Gershgorin circle theorem for efficient keyframe selection in video summarization, reducing complexity while maintaining performance.
Findings
Achieves comparable summarization quality to state-of-the-art methods.
Reduces computational complexity significantly.
Validates effectiveness through experimental results.
Abstract
We study the problem of efficiently summarizing a short video into several keyframes, leveraging recent progress in fast graph sampling. Specifically, we first construct a similarity path graph (SPG) , represented by graph Laplacian matrix , where the similarities between adjacent frames are encoded as positive edge weights. We show that maximizing the smallest eigenvalue of a coefficient matrix , where is the binary keyframe selection vector, is equivalent to minimizing a worst-case signal reconstruction error. We prove that, after partitioning into sub-graphs , the smallest Gershgorin circle theorem (GCT) lower bound of corresponding coefficient matrices -- -- is a lower bound…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Image and Video Retrieval Techniques · Video Coding and Compression Technologies · Video Analysis and Summarization
