Video Behavior Profiling for Anomaly Detection

By Tao A. Xiang, Shaogang Gong. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008

314 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/dadd2e6846c620f2664d7cb80ece113912730052

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

In Computer Vision and Pattern Recognition

Citations in the corpus

Anomaly Detection and Localization in Crowded Scenes (2014, background): “The authors of [2], [25], and [7] guarantee temporally consistent inference by modeling normal temporal sequences with hidden Markov models (HMMs).”
Video-Based Human Behavior Understanding: A Survey (2013, background): “In such cases, it is common to use the concept of anomaly, namely, a deviation from the learned behaviors [1].”
A survey on activity recognition and behavior understanding in video surveillance (2013, background): “An automated visual surveillance system which can understand and learn behavior from observing activities in a video sequence requires a reliable combination of image processing techniques and artificial intelligence techniques [69, 209].”
A temporal Bayesian model for classifying, detecting and localizing activities in video sequences (2012, methodology): “For example, Topic Modeling or Latent Dirichlet Allocation (LDA) [2] has been used to cluster low level features from videos into activities [25, 27, 24, 10].”
Video-Based Abnormal Human Behavior Recognition—A Review (2012, methodology): “of the sensitivity of tracking to occlusion and tracking errors, approaches that rely on low-level features and their statistics are used to describe behaviors instead of tracks [17], [25], [71].”
Understanding Transit Scenes: A Survey on Human Behavior-Recognition Algorithms (2010, background): “detection [166], [167], as well as events based on group activities [165].”
Trajectory Learning for Activity Understanding: Unsupervised, Multilevel, and Long-Term Adaptive Approach (2011, background): “Xiang and Gong [23] were able to segment videos into clips of different activites based on the spectral similarity of behaviors.”