Abstract
In this paper, our techniques used in TRECVID'08 on BBC rush summarization are described. Firstly, rush videos are hierarchical modeled using formal language description. Then, shot detection and V-unit determination are applied for video structuring; junk frames within the model are also effectively removed. Thirdly, adaptive clustering is employed to group shots into clusters to remove retakes. Then, each selected shot is ranked according to its length and sum of activity level for summarization. Competitive results have proved the effectiveness and efficiency of our techniques fully implemented in compressed-domain.
| Original language | English |
|---|---|
| Title of host publication | TVS'08 Proc. of the 2nd ACM TRECVID Video Summarisation Workshop |
| Pages | 26-30 |
| Number of pages | 5 |
| DOIs | |
| Publication status | Published - 2008 |
| Event | TRECVid 2008 - , United Kingdom Duration: 1 Feb 2008 → … |
Conference
| Conference | TRECVid 2008 |
|---|---|
| Country/Territory | United Kingdom |
| Period | 1/02/08 → … |
Keywords
- adaptive clustering
- hierarchical modelling
Fingerprint
Dive into the research topics of 'Hierarchical modeling and adaptive clustering for real-time summarization of rush videos in TRECVID’08'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver