Violence presents humans with an ongoing challenge in human society leading to clashes and deaths of individuals. The ongoing rise of 3D ConvNet architecture enables real-time and fast inference of violent scenarios which this model paves the path!
- Dataset: Utilized Real Life Violence Situations Dataset consisting of 2000 Videos
- Model Architectures: Utilized and fine-tuned efficient_x3d_s
- Results: Achieved average validation accuracy of 1.0 and loss of 0.015
- Pipeline: Designed a pipeline for future inference of videos
Validation Report
Classification Report
To get started with the project, follow these steps:
git clone https://github.com/Ahmaddimran/Histopathological-Lung-and-Colon-Cancer-Detection.git
Dataset -> https://www.kaggle.com/datasets/mohamedmustafa/real-life-violence-situations-dataset/versions/1
Any contribution is welcomed!
This project is licensed under the MIT License. See the LICENSE file for details
M. Soliman, M. Kamal, M. Nashed, Y. Mostafa, B. Chawky, D. Khattab, “ Violence Recognition from Videos using Deep Learning Techniques”, Proc. 9th International Conference on Intelligent Computing and Information Systems (ICICIS'19), Cairo, pp. 79-84, 2019