Group606-DL/Warnify-VisualModel

I3D implemetation in Keras + video preprocessing (rgb and optical flows) to detect violence in videos with weak labels (Weakly Supervised) on XD-Violence dataset (Multi-Label, Multi-class and untrimmed videos) using Keras

25
/ 100
Experimental

This project helps security personnel or content moderators automatically identify violent content within untrimmed videos. It takes raw video footage as input and outputs a determination of whether violence is present, making it easier to manage large volumes of video data. This is designed for professionals responsible for monitoring video feeds or reviewing user-generated content.

No commits in the last 6 months.

Use this if you need to flag potentially violent segments in long, unedited videos without having to manually watch every second.

Not ideal if you need precise identification of specific types of violence or an explanation for why a segment was flagged, as it focuses on overall violence detection.

video-surveillance content-moderation security-monitoring incident-detection
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

8

Forks

2

Language

Jupyter Notebook

License

Last pushed

Jul 04, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Group606-DL/Warnify-VisualModel"

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