Back
How to Find Interesting Locations in Video: A Spatiotemporal Interest Point Detector Learned from Human Eye movements
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 emph{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.
@inproceedings{4486, title = {How to Find Interesting Locations in Video: A Spatiotemporal Interest Point Detector Learned from Human Eye movements}, journal = {Pattern Recognition: 29th DAGM Symposium}, booktitle = {Pattern Recognition}, 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 emph{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.}, pages = {405-414}, editors = {FA Hamprecht and C Schn{\"o}rr and B J{\"a}hne}, publisher = {Springer}, organization = {Max-Planck-Gesellschaft}, school = {Biologische Kybernetik}, address = {Berlin, Germany}, month = sep, year = {2007}, slug = {4486}, author = {Kienzle, W. and Sch{\"o}lkopf, B. and Wichmann, F. and Franz, MO.}, month_numeric = {9} }