How to find interesting locations in video: a spatiotemporal interest point detector learned from human eye movements

Authors:
Wolf Kienzle;Bernhard Schölkopf;Felix A. Wichmann;Matthias O. Franz
Affiliations:
Max-Planck Institut für biologische Kybernetik, Abteilung Empirische Inferenz, Tübingen;Max-Planck Institut für biologische Kybernetik, Abteilung Empirische Inferenz, Tübingen;Technische Universität Berlin, Fakultät IV, FB Modellierung Kognitiver Prozesse, Berlin and Bernstein Center for Computational Neuroscience, Berlin;Max-Planck Institut für biologische Kybernetik, Abteilung Empirische Inferenz, Tübingen
Venue:
Proceedings of the 29th DAGM conference on Pattern recognition
Year:
2007

Citing 10
Cited 6

A Model of Saliency-Based Visual Attention for Rapid Scene Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Evaluation of Interest Point Detectors

International Journal of Computer Vision - Special issue on a special section on visual surveillance
On the Localization of 3D Anatomical Point Landmarks in Medical Imagery Using Multi-step Differential Approaches

Mustererkennung 1997, 19. DAGM-Symposium
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Recognizing Human Actions: A Local SVM Approach

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
On Space-Time Interest Points

International Journal of Computer Vision
Efficient Visual Event Detection Using Volumetric Features

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Learning an Interest Operator from Human Eye Movements

CVPRW '06 Proceedings of the 2006 Conference on Computer Vision and Pattern Recognition Workshop
Behavior recognition via sparse spatio-temporal features

ICCCN '05 Proceedings of the 14th International Conference on Computer Communications and Networks
Is bottom-up attention useful for object recognition?

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition

A dataset and evaluation methodology for visual saliency in video

ICME'09 Proceedings of the 2009 IEEE international conference on Multimedia and Expo
Probabilistic Multi-Task Learning for Visual Saliency Estimation in Video

International Journal of Computer Vision
A learned saliency predictor for dynamic natural scenes

ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part III
Learning attention based saliency in videos from human eye movements

WMVC'09 Proceedings of the 2009 international conference on Motion and video computing
Event detection and recognition for semantic annotation of video

Multimedia Tools and Applications
Dynamic eye movement datasets and learnt saliency models for visual action recognition

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

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.