Name
Abstract | ||
|---|---|---|
This paper presents methods for automatically creating pictorial video summaries that resemble comic books. The relative importance of video segments is computed from their length and novelty. Image and audio analysis is used to automatically detect and emphasize meaningful events. Based on this importance measure, we choose relevant keyframes. Selected keyframes are sized by importance, and then efficiently packed into a pictorial summary. We present a quantitative measure of how well a summary captures the salient events in a video, and show how it can be used to improve our summaries. The result is a compact and visually pleasing summary that captures semantically important events, and is suitable for printing or Web access. Such a summary can be further enhanced by including text captions derived from OCR or other methods. We describe how the automatically generated summaries are used to simplify access to a large collection of videos. |
Year | DOI | Venue |
|---|---|---|
1999 | 10.1145/319463.319654 | ACM Multimedia Conference |
Keywords | Field | DocType |
video manga,pleasing summary,video segment,pictorial summary,quantitative measure,selected keyframes,relevant keyframes,web access,relative importance,pictorial video summary,semantically meaningful video summary,importance measure,web accessibility,audio analysis | Computer vision,Comics,Information retrieval,Computer science,Web access,Audio analyzer,Video tracking,Artificial intelligence,Novelty,Multimedia,Salient | Conference |
ISBN | Citations | PageRank |
1-58113-151-8 | 180 | 13.72 |
References | Authors | |
15 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Shingo Uchihashi | 1 | 431 | 41.70 |
| Jonathan Foote | 2 | 1625 | 176.16 |
| Andreas Girgensohn | 3 | 1724 | 185.73 |
| John Boreczky | 4 | 599 | 51.87 |