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 language | English |
|---|---|
| Pages (from-to) | 376-385 |
| Number of pages | 10 |
| Journal | Pattern Recognition Letters |
| Volume | 130 |
| DOIs | |
| State | Published - Feb 2020 |
| Externally published | Yes |
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
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver