Cycle-SUM: Cycle-Consistent Adversarial LSTM Networks for Unsupervised Video Summarization

Authors

  • Li Yuan National University of Singapore
  • Francis EH Tay National University of Singapore
  • Ping Li Hangzhou Dianzi University
  • Li Zhou National University of Singapore
  • Jiashi Feng National University of Singapore

DOI:

https://doi.org/10.1609/aaai.v33i01.33019143

Abstract

In this paper, we present a novel unsupervised video summarization model that requires no manual annotation. The proposed model termed Cycle-SUM adopts a new cycleconsistent adversarial LSTM architecture that can effectively maximize the information preserving and compactness of the summary video. It consists of a frame selector and a cycle-consistent learning based evaluator. The selector is a bi-direction LSTM network that learns video representations that embed the long-range relationships among video frames. The evaluator defines a learnable information preserving metric between original video and summary video and “supervises” the selector to identify the most informative frames to form the summary video. In particular, the evaluator is composed of two generative adversarial networks (GANs), in which the forward GAN is learned to reconstruct original video from summary video while the backward GAN learns to invert the processing. The consistency between the output of such cycle learning is adopted as the information preserving metric for video summarization. We demonstrate the close relation between mutual information maximization and such cycle learning procedure. Experiments on two video summarization benchmark datasets validate the state-of-theart performance and superiority of the Cycle-SUM model over previous baselines.

Downloads

Published

2019-07-17

How to Cite

Yuan, L., Tay, F. E., Li, P., Zhou, L., & Feng, J. (2019). Cycle-SUM: Cycle-Consistent Adversarial LSTM Networks for Unsupervised Video Summarization. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 9143-9150. https://doi.org/10.1609/aaai.v33i01.33019143

Issue

Section

AAAI Technical Track: Vision