Video Summarization Using Fully Convolutional Sequence Networks

TL;DR

This paper introduces a novel fully convolutional sequence model for video summarization, framing it as a sequence labeling task and adapting semantic segmentation networks to improve summary quality.

Contribution

It proposes a new fully convolutional approach for video summarization, connecting it with semantic segmentation and demonstrating effectiveness on benchmark datasets.

Findings

Outperforms existing methods on benchmark datasets

Establishes a novel connection between semantic segmentation and video summarization

Demonstrates the effectiveness of fully convolutional models for sequence labeling tasks

Abstract

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.