Nikeytas/Videomae Crime Detector Maxdata V1 This model is a fine tuned version of MCG NJU/videomae base on the UCF Crime dataset with event based binary classification . It achieves the following results on the evaluation set: Loss : 0.8405 Accuracy : 0.7292 Precision : 0.7289 Recall : 0.7292 F1 Score : 0.7287 🎯 Model Overview This VideoMAE model has been fine tuned for binary violence detection in video content. The model classifies videos into two categories: Violent Crime (1): Videos containing violent criminal activities Non Violent Incident (0): Videos with non violent or normal activities The model is based on the VideoMAE architecture and has been specifically trained on a curated subset of the UCF Crime dataset with event based categorization for realistic crime detection scenarios. 📊 Dataset & Training Dataset Composition Total Videos : 600 Violent Crime Videos : 300 Non Violent Incident Videos : 300 Class Balance : 50.0% violent crimes Event Distribution : Abuse : 28 videos Arrest : 18 videos Arson : 16 videos Assault : 62 videos Burglary : 120 videos Explosion : 54 videos Fighting : 48 videos RoadAccidents : 58 videos Robbery : 184 videos Shoplifting : 36 videos Steali…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy