# Meta Learning for Task-Driven Video Summarization

## TL;DR

This paper introduces MetaL-TDVS, a meta learning approach that enhances task-driven video summarization by improving model generalization across different videos, outperforming existing methods on benchmark datasets.

## Contribution

It formulates video summarization as a meta learning problem, enabling better generalization and knowledge transfer across videos, which is a novel approach in the field.

## Key findings

- MetaL-TDVS outperforms state-of-the-art methods on benchmark datasets.
- The method improves generalization ability in video summarization.
- Extensive experiments validate the effectiveness of the proposed approach.

## Abstract

Existing video summarization approaches mainly concentrate on sequential or structural characteristic of video data. However, they do not pay enough attention to the video summarization task itself. In this paper, we propose a meta learning method for performing task-driven video summarization, denoted by MetaL-TDVS, to explicitly explore the video summarization mechanism among summarizing processes on different videos. Particularly, MetaL-TDVS aims to excavate the latent mechanism for summarizing video by reformulating video summarization as a meta learning problem and promote generalization ability of the trained model. MetaL-TDVS regards summarizing each video as a single task to make better use of the experience and knowledge learned from processes of summarizing other videos to summarize new ones. Furthermore, MetaL-TDVS updates models via a two-fold back propagation which forces the model optimized on one video to obtain high accuracy on another video in every training step. Extensive experiments on benchmark datasets demonstrate the superiority and better generalization ability of MetaL-TDVS against several state-of-the-art methods.