Unsupervised object-level video summarization with online motion auto-encoder

Yujia Zhang, Xiaodan Liang, Dingwen Zhang, Min Tan, Eric P. Xing

Research output: Contribution to journalArticlepeer-review

67 Scopus citations

Abstract

Unsupervised video summarization plays an important role on digesting, browsing, and searching the ever-growing videos every day, and the underlying fine-grained semantic and motion information (i.e., objects of interest and their key motions) in online videos has been barely touched. In this paper, we investigate a pioneer research direction towards the fine-grained unsupervised object-level video summarization. It can be distinguished from existing pipelines in two aspects: extracting key motions of participated objects, and learning to summarize in an unsupervised and online manner. To achieve this goal, we propose a novel online motion Auto-Encoder (online motion-AE) framework that functions on the super-segmented object motion clips. Comprehensive experiments on a newly-collected surveillance dataset and public datasets have demonstrated the effectiveness of our proposed method.

Original languageEnglish
Pages (from-to)376-385
Number of pages10
JournalPattern Recognition Letters
Volume130
DOIs
StatePublished - Feb 2020
Externally publishedYes

Keywords

  • Object-level video summarization
  • Online motion auto-encoder
  • Stacked sparse LSTM auto-encoder

Fingerprint

Dive into the research topics of 'Unsupervised object-level video summarization with online motion auto-encoder'. Together they form a unique fingerprint.

Cite this