arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.11530cs.CVcs.AIcs.IRcs.LGcs.MM
收藏

通过并行注意力的多个特征集进行有监督的视频摘要

Supervised Video Summarization via Multiple Feature Sets with Parallel Attention

TIB -- Leibniz Information Centre for Science and Technology(莱布尼茨科学技术信息中心)

Junaid Ahmed Ghauri, Sherzod Hakimov, Ralph Ewerth

摘要:

为视频中的特定帧或(短)片段分配重要性分数对于摘要至关重要,但也是一项困难的任务。以前的工作只利用一个来源的视觉特征。在本文中,我们提出了一种新的模型架构,结合三个功能集的视觉内容和运动来预测重要性分数。所提出的体系结构在融合运动特征和表示(静态)视觉内容的特征之前利用注意力机制,从图像分类模型导出。全面的实验评估报告两个著名的数据集,SumMe和TVSum。在这种情况下,我们确定了以前的工作如何使用这些基准数据集的方法问题,并提出了一个公平的评估方案,适当的数据分割,可用于未来的工作。当使用具有并行注意力机制的静态和运动特征时,我们改进了SumMe的最新结果,同时与其他数据集的最新结果不相上下。

英文摘要:

The assignment of importance scores to particular frames or (short) segments in a video is crucial for summarization, but also a difficult task. Previous work utilizes only one source of visual features. In this paper, we suggest a novel model architecture that combines three feature sets for visual content and motion to predict importance scores. The proposed architecture utilizes an attention mechanism before fusing motion features and features representing the (static) visual content, i.e., derived from an image classification model. Comprehensive experimental evaluations are reported for two well-known datasets, SumMe and TVSum. In this context, we identify methodological issues on how previous work used these benchmark datasets, and present a fair evaluation scheme with appropriate data splits that can be used in future work. When using static and motion features with parallel attention mechanism, we improve state-of-the-art results for SumMe, while being on par with the state of the art for the other dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑