Learning rare behaviours

Authors:
Jian Li;Timothy M. Hospedales;Shaogang Gong;Tao Xiang
Affiliations:
School of EECS, Queen Mary University of London, London, UK;School of EECS, Queen Mary University of London, London, UK;School of EECS, Queen Mary University of London, London, UK;School of EECS, Queen Mary University of London, London, UK
Venue:
ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part II
Year:
2010

Citing 11
Cited 0

Latent dirichlet allocation

The Journal of Machine Learning Research
Beyond Tracking: Modelling Activity and Understanding Behaviour

International Journal of Computer Vision
Outlier detection by active learning

Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining
A Neural Network-Based Novelty Detector for Image Sequence Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
A general method for human activity recognition in video

Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
Video Behavior Profiling for Anomaly Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Statistical Debugging Using Latent Topic Models

ECML '07 Proceedings of the 18th European conference on Machine Learning
Unsupervised Activity Perception in Crowded and Complicated Scenes Using Hierarchical Bayesian Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Evaluation methods for topic models

ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Probabilistic Modeling of Scene Dynamics for Applications in Visual Surveillance

IEEE Transactions on Pattern Analysis and Machine Intelligence
Estimating Likelihoods for Topic Models

ACML '09 Proceedings of the 1st Asian Conference on Machine Learning: Advances in Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a novel approach to detect and classify rare behaviours which are visually subtle and occur sparsely in the presence of overwhelming typical behaviours. We treat this as a weakly supervised classification problem and propose a novel topic model: Multi-Class Delta Latent Dirichlet Allocation which learns to model rare behaviours from a few weakly labelled videos as well as typical behaviours from uninteresting videos by collaboratively sharing features among all classes of footage. The learned model is able to accurately classify unseen data. We further explore a novel method for detecting unknown rare behaviours in unseen data by synthesising new plausible topics to hypothesise any potential behavioural conflicts. Extensive validation using both simulated and real-world CCTV video data demonstrates the superior performance of the proposed framework compared to conventional unsupervised detection and supervised classification approaches.