Content area

Abstract

User-generated videos (UGVs) uploaded from mobile phones to social media sites like YouTube and TikTok are short and non-repetitive. We summarize a transitory UGV into several keyframes in linear time via fast graph sampling based on Gershgorin disc alignment (GDA). Specifically, we first model a sequence of \(N\) frames in a UGV as an \(M\)-hop path graph \(\mathcal{G}^o\) for \(M \ll N\), where the similarity between two frames within \(M\) time instants is encoded as a positive edge based on feature similarity. Towards efficient sampling, we then "unfold" \(\mathcal{G}^o\) to a \(1\)-hop path graph \(\mathcal{G}\), specified by a generalized graph Laplacian matrix \(\mathcal{L}\), via one of two graph unfolding procedures with provable performance bounds. We show that maximizing the smallest eigenvalue \(\lambda_{\min}(\mathbf{B})\) of a coefficient matrix \(\mathbf{B} = \textit{diag}\left(\mathbf{h}\right) + \mu \mathcal{L}\), where \(\mathbf{h}\) is the binary keyframe selection vector, is equivalent to minimizing a worst-case signal reconstruction error. We maximize instead the Gershgorin circle theorem (GCT) lower bound \(\lambda^-_{\min}(\mathbf{B})\) by choosing \(\mathbf{h}\) via a new fast graph sampling algorithm that iteratively aligns left-ends of Gershgorin discs for all graph nodes (frames). Extensive experiments on multiple short video datasets show that our algorithm achieves comparable or better video summarization performance compared to state-of-the-art methods, at a substantially reduced complexity.

Details

1009240
Business indexing term
Title
Graph Unfolding and Sampling for Transitory Video Summarization via Gershgorin Disc Alignment
Publication title
arXiv.org; Ithaca
Publication year
2024
Publication date
Aug 3, 2024
Section
Computer Science; Electrical Engineering and Systems Science
Publisher
Cornell University Library, arXiv.org
Source
arXiv.org
Place of publication
Ithaca
Country of publication
United States
University/institution
Cornell University Library arXiv.org
e-ISSN
2331-8422
Source type
Working Paper
Language of publication
English
Document type
Working Paper
Publication history
 
 
Online publication date
2024-08-06
Milestone dates
2024-08-03 (Submission v1)
Publication history
 
 
   First posting date
06 Aug 2024
ProQuest document ID
3089694188
Document URL
https://www.proquest.com/working-papers/graph-unfolding-sampling-transitory-video/docview/3089694188/se-2?accountid=208611
Full text outside of ProQuest
Copyright
© 2024. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Last updated
2024-08-07
Database
ProQuest One Academic