Feature fusion over hyperbolic graph convolution networks for video summarisation

Author:

Wu GuangLi1ORCID,Wang ShengTao12,Xu ShiPeng1

Affiliation:

1. School of Cyberspace Security Gansu University of Political Science and Law Lanzhou China

2. Gansu O.M.Y. Information Technology Co. LTD Lanzhou Jiaotong University Science and Technology Park Incubation Building Lanzhou China

Abstract

AbstractA novel video summarisation method called the Hyperbolic Graph Convolutional Network (HVSN) is proposed, which addresses the challenges of summarising edited videos and capturing the semantic consistency of video shots at different time points. Unlike existing methods that use linear video sequences as input, HVSN leverages Hyperbolic Graph Convolutional Networks (HGCNs) and an adaptive graph convolutional adjacency matrix network to learn and aggregate features from video shots. Moreover, a feature fusion mechanism based on the attention mechanism is employed to facilitate cross‐module feature fusion. To evaluate the performance of the proposed method, experiments are conducted on two benchmark datasets, TVSum and SumMe. The results demonstrate that HVSN achieves state‐of‐the‐art performance, with F1‐scores of 62.04% and 50.26% on TVSum and SumMe, respectively. The use of HGCNs enables the model to better capture the complex spatial structures of video shots, and thus contributes to the improved performance of video summarisation.

Funder

Natural Science Foundation of Gansu Province

Publisher

Institution of Engineering and Technology (IET)

Subject

Computer Vision and Pattern Recognition,Software

Reference40 articles.

1. VSUMM: A mechanism designed to produce static video summaries and a novel evaluation method

2. Spatio-temporal feature-based keyframe detection from video shots using spectral clustering

3. Video summarization generation model based on improved bi‐directional long short‐term memory network;WU G.L.;J. Comput. Appl.,2021

4. Video summarization generation based on self‐attention mechanism and random forest regression;WU G.L.;Comput. Eng. Appl.,2022

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3