Knowledge Graphs for Semantic-Aware Anomaly Detection in Video

Nesen, Alina; Bhargava, Bharat

doi:10.1109/aike48582.2020.00018

Cited by 6 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, Markovitz et al [19] went one step further and implemented a deep spatio-temporal graph AE allowing them to cluster graphical human pose estimations, and further detect abnormal outliers yielding a frame-level accuracy of 0.752 during tests on the ShanghaiTech dataset. Nesen and Bhargava [20] on the other hand, assign anomaly scores to objects in a frame by means of a two-step process: At first, all objects are detected in the given image by means of an off-the-shelf object detector [21]. Secondly, semantic correlation scores for all object-pairs in the frame are derived from ConceptNet [22].…”

Section: Graphs In Video Anomaly Detectionmentioning

confidence: 99%

A graph-based approach to video anomaly detection from the perspective of superpixels

Siemon

Nasrollahi

Moeslund

2023

Fifteenth International Conference on Machine Vision (ICMV 2022)

View full text Add to dashboard Cite

Video Anomaly Detection refers to the concept of discovering activities in a video feed that deviate from the usual visible pattern. It is a very well-studied and explored field in the domain of Computer Vision and Deep Learning, in which automated learning-based systems are capable of detecting certain kinds of anomalies at an accuracy greater than 90%. Deep Learning based Artificial Neural Network models, however, suffer from very low interpretability. In order to address and design a possible solution for this issue, this work proposes to shape the given problem by means of graphical models. Given the high flexibility of compositing easily interpretable graphs, a great variety of techniques exist to build a model representing spatial as well as temporal relationships occurring in the given video sequence. The experiments conducted on common anomaly detection benchmark datasets show that significant performance gains can be achieved through simple re-modelling of individual graph components. In contrast to other video anomaly detection approaches, the one presented in this work focuses primarily on the exploration of the possibility to shift the way we currently look at and process videos when trying to detect anomalous events.

show abstract