Video summarization (VSUMM) has become a popular method in processing massive video data. The key point of VSUMM is to select the key frames to represent the effective contents of a video sequence. The existing methods can only extract the static images of videos as the content summarization, but they ignore the representation of motion information. To cope with these issues, a novel framework for an efficient video content summarization as well as video motion summarization is proposed. Initially, Capsules Net is trained as a spatiotemporal information extractor, and an inter-frames motion curve is generated based on those spatiotemporal features. Subsequently, a transition effects detection method is proposed to automatically segment the video streams into shots. Finally, a self-attention model is introduced to select key-frames sequences inside the shots; thus, key static images are selected as video content summarization, and optical flows can be calculated as video motion summarization. The ultimate experimental results demonstrate that our method is competitive on VSUMM, TvSum, SumMe, and RAI datasets about shot segmentation and video content summarization, and can also represent a good motion summarization result.

中文翻译：

---

用于综合视频摘要的新型关键帧选择框架

视频摘要（VSUMM）已成为处理海量视频数据的流行方法。VSUMM 的关键是选择关键帧来表示视频序列的有效内容。现有方法只能提取视频的静态图像作为内容摘要，而忽略了运动信息的表示。为了解决这些问题，提出了一种用于有效视频内容摘要和视频运动摘要的新框架。最初，Capsules Net 被训练为时空信息提取器，并根据这些时空特征生成帧间运动曲线。随后，提出了一种过渡效果检测方法来自动将视频流分割成镜头。最后，引入了自注意力模型来选择镜头内的关键帧序列；因此，选择关键静态图像作为视频内容摘要，并且可以计算光流作为视频运动摘要。最终的实验结果表明，我们的方法在关于镜头分割和视频内容摘要的 VSUMM、TvSum、SumMe 和 RAI 数据集上具有竞争力，并且也可以代表良好的运动摘要结果。