CVJul 29, 2019

Meta Learning for Task-Driven Video Summarization

arXiv:1907.12342v11 citations
Originality Incremental advance
AI Analysis

This addresses video summarization for applications needing automated content analysis, but it is incremental as it builds on existing meta learning approaches.

The paper tackles video summarization by proposing MetaL-TDVS, a meta learning method that reformulates the task to improve generalization across videos, achieving superior performance on benchmark datasets compared to state-of-the-art methods.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes