Straight to the Point: Fast-forwarding Videos via Reinforcement Learning Using Textual Data

CVPR(2020)

引用 6|浏览90
暂无评分
摘要
The rapid increase in the amount of published visual data and the limited time of users bring the demand for processing untrimmed videos to produce shorter versions that convey the same information. Despite the remarkable progress that has been made by summarization methods, most of them can only select a few frames or skims, which creates visual gaps and breaks the video context. In this paper, we present a novel methodology based on a reinforcement learning formulation to accelerate instructional videos. Our approach can adaptively select frames that are not relevant to convey the information without creating gaps in the final video. Our agent is textually and visually oriented to select which frames to remove to shrink the input video. Additionally, we propose a novel network, called Visually-guided Document Attention Network (VDAN), able to generate a highly discriminative embedding space to represent both textual and visual data. Our experiments show that our method achieves the best performance in terms of F1 Score and coverage at the video segment level.
更多
查看译文
关键词
fast-forwarding videos,textual data,published visual data,untrimmed video processing,summarization methods,skims,visual gaps,video context,reinforcement learning formulation,instructional videos,final video,input video,document attention network,highly discriminative embedding space,video segment level
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要