Name
Title | ||
|---|---|---|
How to find interesting locations in video: a spatiotemporal interest point detector learned from human eye movements |
Abstract | ||
|---|---|---|
Interest point detection in still images is a well-studied topic in computer vision. In the spatiotemporal domain, however, it is still unclear which features indicate useful interest points. In this paper we approach the problem by learning a detector from examples: we record eye movements of human subjects watching video sequences and train a neural network to predict which locations are likely to become eye movement targets. We show that our detector outperforms current spatiotemporal interest point architectures on a standard classification dataset. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1007/978-3-540-74936-3_41 | DAGM-Symposium |
Keywords | Field | DocType |
current spatiotemporal interest point,interesting location,eye movement target,standard classification dataset,neural network,computer vision,human subject,spatiotemporal domain,useful interest point,spatiotemporal interest point detector,interest point detection,human eye movement,record eye movement,eye movement | Human eye,Computer vision,Interest point detection,Computer science,Eye movement,Eye tracking,Artificial intelligence,Artificial neural network,Detector | Conference |
Volume | ISSN | Citations |
4713 | 0302-9743 | 26 |
PageRank | References | Authors |
1.41 | 11 | 8 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Wolf Kienzle | 1 | 391 | 20.73 |
| Bernhard Schölkopf | 2 | 23120 | 3091.82 |
| F A Wichmann | 3 | 231 | 17.54 |
| Matthias O. Franz | 4 | 630 | 54.80 |
| hamprecht | 5 | 26 | 1.41 |
| f a | 6 | 26 | 1.41 |
| christoph schnorr | 7 | 26 | 1.41 |
| bernd jahne | 8 | 26 | 1.41 |