# 2D bidirectional gated recurrent unit convolutional Neural networks for end-to-end violence detection In videos

arXiv: https://arxiv.org/abs/2409.07588 · HTML: https://mlsanity.com/paper/2409.07588/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 27 references that are in the map.
- First posted on arXiv 11 Sep 2024.

## Builds on (most cited first, 7 of 7)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Learning to Detect Violent Videos using Convolutional Long Short-Term Memory](https://mlsanity.com/paper/1709.06531/) (2017)
- [LP-3DCNN: Unveiling Local Phase in 3D Convolutional Neural Networks](https://mlsanity.com/paper/1904.03498/) (2019)
- [Memory Visualization for Gated Recurrent Neural Networks in Speech Recognition](https://mlsanity.com/paper/1609.08789/) (2016)
- [Exploring Temporal Differences in 3D Convolutional Neural Networks](https://mlsanity.com/paper/1909.03309/) (2019)

## Built on by (most cited first, 2 of 2)

- [Uni-AdaFocus: Spatial-temporal Dynamic Computation for Video Recognition](https://mlsanity.com/paper/2412.11228/) (2024)
- [SurgAnt-ViVQA: Learning to Anticipate Surgical Events through GRU-Driven Temporal Cross-Attention](https://mlsanity.com/paper/2511.03178/) (2025)

## Abstract (arXiv)

Abnormal behavior detection, action recognition, fight and violence detection in videos is an area that has attracted a lot of interest in recent years. In this work, we propose an architecture that combines a Bidirectional Gated Recurrent Unit (BiGRU) and a 2D Convolutional Neural Network (CNN) to detect violence in video sequences. A CNN is used to extract spatial characteristics from each frame, while the BiGRU extracts temporal and local motion characteristics using CNN extracted features from multiple frames. The proposed end-to-end deep learning network is tested in three public datasets with varying scene complexities. The proposed network achieves accuracies up to 98%. The obtained results are promising and show the performance of the proposed end-to-end approach.