VideoSAGE: Video Summarization with Graph Representation Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chaves, Jose M. Rojas, Tripathi, Subarna
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910411996004352
author Chaves, Jose M. Rojas
Tripathi, Subarna
author_facet Chaves, Jose M. Rojas
Tripathi, Subarna
contents We propose a graph-based representation learning framework for video summarization. First, we convert an input video to a graph where nodes correspond to each of the video frames. Then, we impose sparsity on the graph by connecting only those pairs of nodes that are within a specified temporal distance. We then formulate the video summarization task as a binary node classification problem, precisely classifying video frames whether they should belong to the output summary video. A graph constructed this way aims to capture long-range interactions among video frames, and the sparsity ensures the model trains without hitting the memory and compute bottleneck. Experiments on two datasets(SumMe and TVSum) demonstrate the effectiveness of the proposed nimble model compared to existing state-of-the-art summarization approaches while being one order of magnitude more efficient in compute time and memory
format Preprint
id arxiv_https___arxiv_org_abs_2404_10539
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle VideoSAGE: Video Summarization with Graph Representation Learning
Chaves, Jose M. Rojas
Tripathi, Subarna
Computer Vision and Pattern Recognition
Artificial Intelligence
We propose a graph-based representation learning framework for video summarization. First, we convert an input video to a graph where nodes correspond to each of the video frames. Then, we impose sparsity on the graph by connecting only those pairs of nodes that are within a specified temporal distance. We then formulate the video summarization task as a binary node classification problem, precisely classifying video frames whether they should belong to the output summary video. A graph constructed this way aims to capture long-range interactions among video frames, and the sparsity ensures the model trains without hitting the memory and compute bottleneck. Experiments on two datasets(SumMe and TVSum) demonstrate the effectiveness of the proposed nimble model compared to existing state-of-the-art summarization approaches while being one order of magnitude more efficient in compute time and memory
title VideoSAGE: Video Summarization with Graph Representation Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2404.10539