aleflabo/MoCoDAD

The official PyTorch implementation of the IEEE/CVF International Conference on Computer Vision (ICCV) '23 paper Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection.

38
/ 100
Emerging

This project helps security personnel or surveillance operators automatically detect unusual or suspicious activities in video footage. It takes recorded video data, processes the detected human movements (skeletons), and identifies actions that deviate from normal patterns, flagging them as potential anomalies. It is designed for those who monitor public spaces, workplaces, or restricted areas for safety and security.

No commits in the last 6 months.

Use this if you need to automate the detection of unusual human behaviors in surveillance videos to improve security and response times.

Not ideal if you need to detect anomalies in videos without human subjects or if your primary focus is on object detection rather than human motion.

video-surveillance security-monitoring anomaly-detection human-behavior-analysis safety-management
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

93

Forks

11

Language

Jupyter Notebook

License

MIT

Last pushed

Aug 01, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/aleflabo/MoCoDAD"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.