Leakage-Safe Re-Evaluation of Deep Video Models for Violence Detection in Smart-City CCTV Surveillance

Bareen Haval; Sarkar Hasan Ahmed

doi:10.65542/djei.v2i3.82

Authors

Bareen Haval Artificiel Intelligence Department, Duhok Polytechnic University https://orcid.org/0009-0006-3696-6095
Sarkar Hasan Ahmed Computer Networks Department, Sulaimani Polytechnic University https://orcid.org/0000-0001-5729-073X

DOI:

https://doi.org/10.65542/djei.v2i3.82

Keywords:

violence detection, video surveillance, data leakage, SCVD dataset, reproducibility, X3D

Abstract

Urban CCTV networks produce more video than human operators can watch, so automatic detection of physical violence has become an active research goal whose progress is measured on shared benchmark datasets; the integrity of those benchmarks is therefore as important as the models tested on them. This study audits the Smart-City CCTV Violence Detection (SCVD) dataset and re-evaluates two deep video models on a corrected version of it. The contribution is methodological: a leakage-auditing and benchmark-reconstruction procedure for video datasets, not a new detection architecture; the two models are evaluated to measure what the leakage conceals. The official train/test division leaks: 287 test clips are byte-for-byte copies of training clips, and a model trained on this division scored a meaningless F1 of 1.000. The benchmark was rebuilt in two stages, first removing exact duplicates with a cryptographic hash and then grouping near-identical clips with a perceptual hash and connected-component analysis, so that clips from one scene cannot fall on both sides of the split. On the corrected benchmark, an efficient three-dimensional network (X3D-S, pre-trained on Kinetics-400) reached a mean F1 of 0.894 (±0.020) and was far steadier across random seeds than a ResNet18+LSTM baseline, whose F1 ranged from 0.751 to 0.894. These findings show that published SCVD scores are inflated by leakage and provide an honest, reproducible baseline for real-time urban violence detection.

References

1. Aremu, T.; Zhiyuan, L.; Alameeri, R.; Khan, M.; Saddik, A. El SSIVD-Net: A Novel Salient Super Image Classification and Detection Technique for Weaponized Violence. In Proceedings of the Science and Information Conference; Springer, 2024; pp. 16–35. DOI: https://doi.org/10.1007/978-3-031-62269-4_2

2. Negre, P.; Alonso, R.S.; González-Briones, A.; Prieto, J.; Rodríguez-González, S. Literature Review of Deep-Learning-Based Detection of Violence in Video. Sensors 2024, 24, 4016. DOI: https://doi.org/10.3390/s24124016

3. Kapoor, S.; Narayanan, A. Leakage and the Reproducibility Crisis in Machine-Learning-Based Science. Patterns 2023, 4. DOI: https://doi.org/10.1016/j.patter.2023.100804

4. Rendón-Segador, F.J.; Álvarez-García, J.A.; Salazar-González, J.L.; Tommasi, T. Crimenet: Neural Structured Learning Using Vision Transformer for Violence Detection. Neural networks 2023, 161, 318–329. DOI: https://doi.org/10.1016/j.neunet.2023.01.048

5. Liu, Z.; Ning, J.; Cao, Y.; Wei, Y.; Zhang, Z.; Lin, S.; Hu, H. Video Swin Transformer. In Proceedings of the Proceedings of the IEEE/CVF conference on computer vision and pattern recognition; 2022; pp. 3202–3211. DOI: https://doi.org/10.1109/CVPR52688.2022.00320

6. Tong, Z.; Song, Y.; Wang, J.; Wang, L. Videomae: Masked Autoencoders Are Data-Efficient Learners for Self-Supervised Video Pre-Training. Adv. Neural Inf. Process. Syst. 2022, 35, 10078–10093. DOI: https://doi.org/10.52202/068431-0732

7. Wang, L.; Huang, B.; Zhao, Z.; Tong, Z.; He, Y.; Wang, Y.; Wang, Y.; Qiao, Y. Videomae v2: Scaling Video Masked Autoencoders with Dual Masking. In Proceedings of the Proceedings of the IEEE/CVF conference on computer vision and pattern recognition; 2023; pp. 14549–14560. DOI: https://doi.org/10.1109/CVPR52729.2023.01398

8. Senadeera, D.C.; Yang, X.; Li, S.; Awais, M.; Kollias, D.; Slabaugh, G. Dual Branch Videomamba with Gated Class Token Fusion for Violence Detection. arXiv preprint arXiv:2506.03162 2025.

9. Rendón-Segador, F.J.; Álvarez-García, J.A.; Soria-Morillo, L.M. Transformer and Adaptive Threshold Sliding Window for Improving Violence Detection in Videos. Sensors 2024, 24, 5429. DOI: https://doi.org/10.3390/s24165429

10. Srivastava, N.; Hinton, G.; Krizhevsky, A.; Sutskever, I.; Salakhutdinov, R. Dropout: A Simple Way to Prevent Neural Networks from Overfitting. The journal of machine learning research 2014, 15, 1929–1958.

11. Wang, J.; Zhao, D.; Li, H.; Wang, D. Lightweight Violence Detection Model Based on 2D CNN with Bi-Directional Motion Attention. Applied Sciences 2024, 14, 4895. DOI: https://doi.org/10.3390/app14114895

12. Huszar, V.D.; Adhikarla, V.K.; Negyesi, I.; Krasznay, C. Toward Fast and Accurate Violence Detection for Automated Video Surveillance Applications. IEEE Access 2023, 11, 18772–18793. DOI: https://doi.org/10.1109/ACCESS.2023.3245521

13. Khan, M.; El Saddik, A.; Gueaieb, W.; De Masi, G.; Karray, F. VD-Net: An Edge Vision-Based Surveillance System for Violence Detection. IEEE Access 2024, 12, 43796–43808. DOI: https://doi.org/10.1109/ACCESS.2024.3380192

14. Salman, M.; Abbas, N.; Ur Rahman, S.I.; Al Alshaikh, M.; Saudagar, A.K.J. An Embedded Deep Learning Framework for Real-Time Violence Detection and Alert Generation. Sci. Rep. 2026. DOI: https://doi.org/10.1038/s41598-026-44939-x

15. Qi, B.; Wu, B.; Sun, B. Automated Violence Monitoring System for Real-Time Fistfight Detection Using Deep Learning-Based Temporal Action Localization. Sci. Rep. 2025, 15, 29497. DOI: https://doi.org/10.1038/s41598-025-12531-4

16. Azim, R.; Abbas, N.; Alkahtani, H.K.; Qahmash, A. An Explainable Deep Learning Framework for Video Violence Detection Using Unsupervised Keyframe Selection and Attention-Based CNN. Sci. Rep. 2026. DOI: https://doi.org/10.1038/s41598-026-40977-7

17. Andrade, J.P.F.; Si, T.; Cavalcanti, A.P.; Nascimento, A.C.A.; Miranda, P.B.C. SUSAN: A Deep Learning-Based Architecture for Violence Detection against Women in Surveillance Videos. Expert Syst. Appl. 2025, 280, 127337. DOI: https://doi.org/10.1016/j.eswa.2025.127337

18. McKeown, S.; Buchanan, W.J. Hamming Distributions of Popular Perceptual Hashing Techniques. Forensic Science International: Digital Investigation 2023, 44, 301509. DOI: https://doi.org/10.1016/j.fsidi.2023.301509

19. Huillcen Baca, H.A.; Palomino Valdivia, F. de L.; Gutierrez Caceres, J.C. Efficient Human Violence Recognition for Surveillance in Real Time. Sensors 2024, 24, 668. DOI: https://doi.org/10.3390/s24020668

20. Wang, Y.; Li, K.; Li, X.; Yu, J.; He, Y.; Chen, G.; Pei, B.; Zheng, R.; Wang, Z.; Shi, Y. Internvideo2: Scaling Foundation Models for Multimodal Video Understanding. In Proceedings of the European conference on computer vision; Springer, 2024; pp. 396–416. DOI: https://doi.org/10.1007/978-3-031-73013-9_23

21. Madan, N.; Møgelmose, A.; Modi, R.; Rawat, Y.S.; Moeslund, T.B. Foundation Models for Video Understanding: A Survey. arXiv preprint arXiv:2405.03770 2024. DOI: https://doi.org/10.36227/techrxiv.171769139.99464428/v1

22. Bardes, A.; Garrido, Q.; Ponce, J.; Chen, X.; Rabbat, M.; LeCun, Y.; Assran, M.; Ballas, N. Revisiting Feature Prediction for Learning Visual Representations from Video. arXiv preprint arXiv:2404.08471 2024.

23. Balloccu, S.; Schmidtová, P.; Lango, M.; Dušek, O. Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs. In Proceedings of the Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers); 2024; pp. 67–93. DOI: https://doi.org/10.18653/v1/2024.eacl-long.5

24. He, K.; Zhang, X.; Ren, S.; Sun, J. Deep Residual Learning for Image Recognition. In Proceedings of the Proceedings of the IEEE conference on computer vision and pattern recognition; 2016; pp. 770–778. DOI: https://doi.org/10.1109/CVPR.2016.90

25. Carreira, J.; Zisserman, A. Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset. In Proceedings of the proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2017; pp. 6299–6308. DOI: https://doi.org/10.1109/CVPR.2017.502

26. Loshchilov, I.; Hutter, F. Decoupled Weight Decay Regularization. arXiv preprint arXiv:1711.05101 2017.

27. Kingma, D.P.; Ba, J. Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980 2014.

28. Sultani, W.; Chen, C.; Shah, M. Real-World Anomaly Detection in Surveillance Videos. In Proceedings of the Proceedings of the IEEE conference on computer vision and pattern recognition; 2018; pp. 6479–6488. DOI: https://doi.org/10.1109/CVPR.2018.00678

29. Wang, L.; Xiong, Y.; Wang, Z.; Qiao, Y.; Lin, D.; Tang, X.; Van Gool, L. Temporal Segment Networks: Towards Good Practices for Deep Action Recognition. In Proceedings of the European conference on computer vision; Springer, 2016; pp. 20–36. DOI: https://doi.org/10.1007/978-3-319-46484-8_2

30. Russakovsky, O.; Deng, J.; Su, H.; Krause, J.; Satheesh, S.; Ma, S.; Huang, Z.; Karpathy, A.; Khosla, A.; Bernstein, M. Imagenet Large Scale Visual Recognition Challenge. Int. J. Comput. Vis. 2015, 115, 211–252. DOI: https://doi.org/10.1007/s11263-015-0816-y

31. Hochreiter, S.; Schmidhuber, J. Long Short-Term Memory. Neural Comput. 1997, 9, 1735–1780. DOI: https://doi.org/10.1162/neco.1997.9.8.1735

32. Simonyan, K.; Zisserman, A. Two-Stream Convolutional Networks for Action Recognition in Videos. Adv. Neural Inf. Process. Syst. 2014, 27.

33. Tran, D.; Wang, H.; Torresani, L.; Ray, J.; LeCun, Y.; Paluri, M. A Closer Look at Spatiotemporal Convolutions for Action Recognition. In Proceedings of the Proceedings of the IEEE conference on Computer Vision and Pattern Recognition; 2018; pp. 6450–6459. DOI: https://doi.org/10.1109/CVPR.2018.00675

34. Feichtenhofer, C.; Fan, H.; Malik, J.; He, K. Slowfast Networks for Video Recognition. In Proceedings of the Proceedings of the IEEE/CVF international conference on computer vision; 2019; pp. 6202–6211. DOI: https://doi.org/10.1109/ICCV.2019.00630

35. Dosovitskiy, A.; Beyer, L.; Kolesnikov, A.; Weissenborn, D.; Zhai, X.; Unterthiner, T.; Dehghani, M.; Minderer, M.; Heigold, G.; Gelly, S. An Image Is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv preprint arXiv:2010.11929 2020.

36. Loshchilov, I.; Hutter, F. Sgdr: Stochastic Gradient Descent with Warm Restarts. arXiv preprint arXiv:1608.03983 2016.

37. Micikevicius, P.; Narang, S.; Alben, J.; Diamos, G.; Elsen, E.; Garcia, D.; Ginsburg, B.; Houston, M.; Kuchaiev, O.; Venkatesh, G. Mixed Precision Training. arXiv preprint arXiv:1710.03740 2017.

38. Sokolova, M.; Lapalme, G. A Systematic Analysis of Performance Measures for Classification Tasks. Inf. Process. Manag. 2009, 45, 427–437. DOI: https://doi.org/10.1016/j.ipm.2009.03.002