How to Find Interesting Locations in Video: A Spatiotemporal Interest Point 
Detector Learned from Human Eye movements

Kienzle, W; Schölkopf, B; Wichmann, F; Franz, MO; Hamprecht,; A., F.; Schnörr, C.; Jähne, B.

doi:10.1007/978-3-540-74936-3_41

アイテム詳細

登録内容を編集ファイル形式で保存

一時保存へ追加

このアイテムの新しいバージョンが利用可能です:
https://pure.mpg.de/pubman/item/item_1790249_3

詳細要約

公開

会議論文

How to Find Interesting Locations in Video: A Spatiotemporal Interest Point Detector Learned from Human Eye movements

MPS-Authors

/persons/resource/persons84012

Kienzle, W
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons84193

Schölkopf, B
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons84314

Wichmann, F
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons83919

Franz, MO
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;

External Resource

There are no locators available

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

フルテキスト (公開)

公開されているフルテキストはありません

付随資料 (公開)

There is no public supplementary material available

引用

Kienzle, W., Schölkopf, B., Wichmann, F., & Franz, M. (2007). How to Find Interesting Locations in Video: A Spatiotemporal Interest Point Detector Learned from Human Eye movements. Pattern Recognition: 29th DAGM Symposium, 405-414.

引用: https://hdl.handle.net/11858/00-001M-0000-0013-CBE3-B

要旨

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 emphlearning 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.