A data-driven approach to quantifying natural human motion
ACM SIGGRAPH 2005 Papers
Unsupervised analysis of activity sequences using event-motifs
Proceedings of the 4th ACM international workshop on Video surveillance and sensor networks
Visual inference of human emotion and behaviour
Proceedings of the 9th international conference on Multimodal interfaces
Incremental and adaptive abnormal behaviour detection
Computer Vision and Image Understanding
Detecting abnormal activities in video sequences
Proceedings of the 2008 Ambi-Sys workshop on Ambient media delivery and interactive television
Unsupervised view and rate invariant clustering of video sequences
Computer Vision and Image Understanding
A novel sequence representation for unsupervised analysis of human activities
Artificial Intelligence
Learning to recognize video-based spatiotemporal events
IEEE Transactions on Intelligent Transportation Systems
n-grams of action primitives for recognizing human behavior
CAIP'07 Proceedings of the 12th international conference on Computer analysis of images and patterns
Behavior histograms for action recognition and human detection
Proceedings of the 2nd conference on Human motion: understanding, modeling, capture and animation
Fast population game dynamics for dominant sets and other quadratic optimization problems
SSPR&SPR'10 Proceedings of the 2010 joint IAPR international conference on Structural, syntactic, and statistical pattern recognition
Video scene detection using graph-based representations
Image Communication
Anomalous video event detection using spatiotemporal context
Computer Vision and Image Understanding
Graph-based quadratic optimization: A fast evolutionary approach
Computer Vision and Image Understanding
Dominant sets based movie scene detection
Signal Processing
Human behavior clustering for anomaly detection
Frontiers of Computer Science in China
A comprehensive study of visual event computing
Multimedia Tools and Applications
Unsupervised video surveillance
ACCV'10 Proceedings of the 2010 international conference on Computer vision - Volume Part I
Expert Systems with Applications: An International Journal
Spatio-temporal segmentation using dominant sets
EMMCVPR'05 Proceedings of the 5th international conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
Visual exploration of time-series data with shape space projections
EuroVis'11 Proceedings of the 13th Eurographics / IEEE - VGTC conference on Visualization
Hi-index | 0.01 |
We present a novel representation and method for detecting and explaining anomalous activities in a video stream. Drawing from natural language processing, we introduce a representation of activities as bags of event n-grams, where we analyze the global structural information of activities using their local event statistics. We demonstrate how maximal cliques in an undirected edge-weighted graph of activities, can be used in an unsupervised manner, to discover regular sub-classes of an activity class. Based on these discovered sub-classes, we formulate a definition of anomalous activities and present a way to detect them. Finally, we characterize each discovered sub-class in terms of its "most representative member," and present an information-theoretic method to explain the detected anomalies in a human-interpretable form.