Mostrar el registro sencillo del ítem
Artículo
CrimeNet: Neural Structured Learning using Vision Transformer for violence detection
dc.creator | Rendón Segador, Fernando José | es |
dc.creator | Álvarez García, Juan Antonio | es |
dc.creator | Salazar González, Jose Luis | es |
dc.creator | Tommasi, Tatiana | es |
dc.date.accessioned | 2023-02-09T10:39:25Z | |
dc.date.available | 2023-02-09T10:39:25Z | |
dc.date.issued | 2023-02-02 | |
dc.identifier.citation | Rendón Segador, F.J., Álvarez García, J.A., Salazar González, J.L. y Tommasi, T. (2023). CrimeNet: Neural Structured Learning using Vision Transformer for violence detection. Neural Networks, February 2023, 1-24. https://doi.org/10.1016/j.neunet.2023.01.048. | |
dc.identifier.issn | 1879-2782 | es |
dc.identifier.uri | https://hdl.handle.net/11441/142567 | |
dc.description.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. | es |
dc.description.sponsorship | MCIN/AEI/ 10.13039/501100011033 and by the “European Union NextGenerationEU/PRTR ” HORUS project - Grant n. PID2021-126359OB-I00 | es |
dc.format | application/pdf | es |
dc.format.extent | 24 | es |
dc.language.iso | eng | es |
dc.publisher | Elsevier | es |
dc.relation.ispartof | Neural Networks, February 2023, 1-24. | |
dc.subject | Deep learning | es |
dc.subject | Neural Structured Learning | es |
dc.subject | Vision Transformer | es |
dc.subject | Violence detection | es |
dc.subject | Adversarial Learning | es |
dc.title | CrimeNet: Neural Structured Learning using Vision Transformer for violence detection | es |
dc.type | info:eu-repo/semantics/article | es |
dcterms.identifier | https://ror.org/03yxnpp24 | |
dc.type.version | info:eu-repo/semantics/publishedVersion | es |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | es |
dc.contributor.affiliation | Universidad de Sevilla. Departamento de Lenguajes y Sistemas Informáticos | es |
dc.relation.projectID | DISARM project - Grant n. PDC2021-121197 | es |
dc.relation.projectID | HORUS project - Grant n. PID2021-126359OB-I00 | es |
dc.relation.publisherversion | https://www.sciencedirect.com/science/article/pii/S0893608023000606?via%3Dihub | es |
dc.identifier.doi | 10.1016/j.neunet.2023.01.048 | es |
dc.contributor.group | Universidad de Sevilla. TIC134: Sistemas Informáticos. | es |
dc.journaltitle | Neural Networks | es |
dc.publication.volumen | February 2023 | es |
dc.publication.initialPage | 1 | es |
dc.publication.endPage | 24 | es |
dc.contributor.funder | Ministerio de Ciencia e Innovación (MICIN). España | es |
dc.contributor.funder | European Union (UE) | es |
Ficheros | Tamaño | Formato | Ver | Descripción |
---|---|---|---|---|
1-s2.0-S0893608023000606-main.pdf | 1.528Mb | [PDF] | Ver/ | |
Este registro aparece en las siguientes colecciones
Este documento está protegido por los derechos de propiedad intelectual e industrial. Sin perjuicio de las exenciones legales existentes, queda prohibida su reproducción, distribución, comunicación pública o transformación sin la autorización del titular de los derechos, a menos que se indique lo contrario.