基于多粒度视频信息和注意力机制的视频场景识别

视频场景识别是机器学习和计算机视觉一个重要的研究领域.但是当前对于视频场景识别的探索工作还远远不够，而且目前提出的模型大都使用视频级的特征信息，忽略了多粒度的视频特征关联.本文提出了一种基于多粒度的视频特征的注意力机制的模型架构，可以动态高效的利用各维度视频信息之间存在的丰富的语义关联，提高识别准确度.本文在中国多媒体大会（CCF ChinaMM 2019）最新推出的VideoNet数据集上进行了实验，实验结果表明基于多粒度的视频特征的注意力机制的模型与传统方法相比具有明显的优越性.

Video Scene Recognition with Multi-Granularity Video Features and Attention Mechanism

Video scene recognition has attracted much attention in the field of machine learning and computer vision. It is not only an important practical application, but also a challenge for image understanding in the field of computer vision. Nevertheless, current exploration of video scene recognition has not been unable to meet the needs of production environment. And most proposed models only use video-level feature information, while ignore association of multi-granularity video feature. In this study, we propose an architecture of attention mechanism with multi-granularity video features, which can make use of the rich semantic association among the various dimensions of video information dynamically and efficiently, and improve the performance of the model. The experiments are conducted on the latest VideoNet dataset released by CCF China MM 2019. The result shows that the proposed model based on attention mechanism model with multi-granularity video features outperforms the previous methods.