期刊
PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19)
卷 -, 期 -, 页码 827-835出版社
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3343031.3350938
关键词
Multi-video summarization; Graph convolutional network; Class imbalance problem
资金
- Natural Science Foundation of Guangdong Province [2016A030310053]
- Hong Kong Polytechnic University Grant G-UAEU
- communication platform at the Third Afflicated Hospital of SUN Yat-Sen University
- Shenzhen high-level overseas talents program
- National Engineering Laboratory for Big Data System Computing Technology
Multi-video summarization, which tries to generate a single summary for a collection of video, is an important task in dealing with ever-growing video data. In this paper, we are the first to propose a graph convolutional network for multi-video summarization. The novel network measures the importance and relevance of each video shot in its own video as well as in the whole video collection. The important node sampling method is proposed to emphasize the effective features which are more possible to be selected as the final video summary. Two strategies are proposed to integrate into the network to solve the inherent class imbalance problem in the task of video summarization. The loss regularization for diversity is used to encourage a diverse summary to be generated. Extensive experiments are carried out, and in comparison with traditional and recent graph models and the state-of-the-art video summarization methods, our proposed model is effective in generating a representative summary for multiple videos with good diversity. It also achieves state-of-the-art performance on two standard video summarization datasets.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据