violence-detection and Violence-Detection-and-Categorization
These are competing implementations of the same core task—violence detection in video/image data—with the first offering broader environmental hazard detection (violence, fire, crashes) while the second focuses specifically on violence categorization with emphasis on supervised training methodology.
About violence-detection
sukhitashvili/violence-detection
Deep learning based algorithm which is capable of detecting violence in indoor or outdoor environments: fight, fire or car crash and even more
Built on vision-language model principles, it aligns image embeddings with textual descriptions to enable zero-shot generalization—users can detect custom scenarios by adding descriptive labels to `settings.yaml` without retraining. Supports 16+ configurable threat categories and integrates seamlessly into Python projects via a simple API, with optional Streamlit web interface for real-time frame-by-frame video analysis.
About Violence-Detection-and-Categorization
Ashwath0102/Violence-Detection-and-Categorization
Deeply Supervised Practical Implementation of Violence Detection from Videos for Maximizing Performance
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work