Segmental multi-way local pooling for video recognition

Ilseo Kim, Sangmin Oh, Arash Vahdat, Kevin J. Cannons, A. Perera, Greg Mori
{"title":"Segmental multi-way local pooling for video recognition","authors":"Ilseo Kim, Sangmin Oh, Arash Vahdat, Kevin J. Cannons, A. Perera, Greg Mori","doi":"10.1145/2502081.2502167","DOIUrl":null,"url":null,"abstract":"In this work, we address the problem of complex event detection on unconstrained videos. We introduce a novel multi-way feature pooling approach which leverages segment-level information. The approach is simple and widely applicable to diverse audio-visual features. Our approach uses a set of clusters discovered via unsupervised clustering of segment-level features. Depending on feature characteristics, not only scene-based clusters but also motion/audio-based clusters can be incorporated. Then, every video is represented with multiple descriptors, where each descriptor is designed to relate to one of the pre-built clusters. For classification, intersection kernel SVMs are used where the kernel is obtained by combining multiple kernels computed from corresponding per-cluster descriptor pairs. Evaluation on TRECVID'11 MED dataset shows a significant improvement by the proposed approach beyond the state-of-the-art.","PeriodicalId":20448,"journal":{"name":"Proceedings of the 21st ACM international conference on Multimedia","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2013-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 21st ACM international conference on Multimedia","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2502081.2502167","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7

Abstract

In this work, we address the problem of complex event detection on unconstrained videos. We introduce a novel multi-way feature pooling approach which leverages segment-level information. The approach is simple and widely applicable to diverse audio-visual features. Our approach uses a set of clusters discovered via unsupervised clustering of segment-level features. Depending on feature characteristics, not only scene-based clusters but also motion/audio-based clusters can be incorporated. Then, every video is represented with multiple descriptors, where each descriptor is designed to relate to one of the pre-built clusters. For classification, intersection kernel SVMs are used where the kernel is obtained by combining multiple kernels computed from corresponding per-cluster descriptor pairs. Evaluation on TRECVID'11 MED dataset shows a significant improvement by the proposed approach beyond the state-of-the-art.
视频识别的分段多路局部池化
在这项工作中,我们解决了在无约束视频上的复杂事件检测问题。我们引入了一种新的多路特征池化方法,该方法利用了段级信息。该方法简单,可广泛应用于各种视听特征。我们的方法使用一组通过对段级特征的无监督聚类发现的聚类。根据特征特征,不仅可以合并基于场景的集群,还可以合并基于动作/音频的集群。然后,每个视频用多个描述符表示,其中每个描述符被设计为与预构建的集群之一相关。对于分类,使用交集核支持向量机,其中核是通过组合从相应的每簇描述符对计算的多个核来获得的。对TRECVID'11 MED数据集的评估表明,该方法的显著改进超出了最先进的水平。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信