Video Summarization Using Fully Convolutional Sequence Networks
This provides a tool for video search, retrieval, and browsing by summarizing videos, though it appears incremental as it adapts existing semantic segmentation networks.
The paper tackles video summarization by formulating it as a sequence labeling problem and proposes fully convolutional sequence models instead of recurrent ones, achieving effectiveness demonstrated through experiments on two benchmark datasets.
This paper addresses the problem of video summarization. Given an input video, the goal is to select a subset of the frames to create a summary video that optimally captures the important information of the input video. With the large amount of videos available online, video summarization provides a useful tool that assists video search, retrieval, browsing, etc. In this paper, we formulate video summarization as a sequence labeling problem. Unlike existing approaches that use recurrent models, we propose fully convolutional sequence models to solve video summarization. We firstly establish a novel connection between semantic segmentation and video summarization, and then adapt popular semantic segmentation networks for video summarization. Extensive experiments and analysis on two benchmark datasets demonstrate the effectiveness of our models.