How to find interesting locations in video: a spatiotemporal interest point detector learned from human eye movements
Kienzle Wolf, Scholkopf Bernhard, Wichmann Felix and Franz Matthias
In: DAGM 2007, 12 - 14 Sep 2007, Heidelberg, Germany.

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.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.

[Edit]