Citation

Rendón-Segador FJ, Álvarez-García JA, Salazar-González JL, Tommasi T. Neural. Netw. 2023; 161: 318-329.

Copyright

(Copyright © 2023, Elsevier Publishing)

DOI

10.1016/j.neunet.2023.01.048

PMID

36774869

Abstract

The state of the art in violence detection in videos has improved in recent years thanks to deep learning models, but it is still below 90% of average precision in the most complex datasets, which may pose a problem of frequent false alarms in video surveillance environments and may cause security guards to disable the artificial intelligence system. In this study, we propose a new neural network based on Vision Transformer (ViT) and Neural Structured Learning (NSL) with adversarial training. This network, called CrimeNet, outperforms previous works by a large margin and reduces practically to zero the false positives. Our tests on the four most challenging violence-related datasets (binary and multi-class) show the effectiveness of CrimeNet, improving the state of the art from 9.4 to 22.17 percentage points in ROC AUC depending on the dataset. In addition, we present a generalisation study on our model by training and testing it on different datasets. The obtained results show that CrimeNet improves over competing methods with a gain of between 12.39 and 25.22 percentage points, showing remarkable robustness.

Language: en

Keywords

Adversarial Learning; Deep learning; Neural Structured Learning; Violence detection; Vision Transformer