Detecting interesting events using unsupervised density ratio estimation

Authors:
Yuichi Ito;Kris M. Kitani;James A. Bagnell;Martial Hebert
Affiliations:
Nikon Corporation, Shinagawa, Tokyo, Japan;Carnegie Mellon University, Pittsburgh, PA;Carnegie Mellon University, Pittsburgh, PA;Carnegie Mellon University, Pittsburgh, PA
Venue:
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
Year:
2012

Citing 7
Cited 0

Semi-Supervised Adapted HMMs for Unusual Event Detection

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Nonchronological Video Synopsis and Indexing

IEEE Transactions on Pattern Analysis and Machine Intelligence
Direct density-ratio estimation with dimensionality reduction via least-squares hetero-distributional subspace search

Neural Networks
Bayesian filter based behavior recognition in workflows allowing for user feedback

Computer Vision and Image Understanding
Human detection using oriented histograms of flow and appearance

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Sparse reconstruction cost for abnormal event detection

CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Trajectory-Based Anomalous Event Detection

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

Generating meaningful digests of videos by extracting interesting frames remains a difficult task. In this paper, we define interesting events as unusual events which occur rarely in the entire video and we propose a novel interesting event summarization framework based on the technique of density ratio estimation recently introduced in machine learning. Our proposed framework is unsupervised and it can be applied to general video sources, including videos from moving cameras. We evaluated the proposed approach on a publicly available dataset in the context of anomalous crowd behavior and with a challenging personal video dataset. We demonstrated competitive performance both in accuracy relative to human annotation and computation time.