wondonghyeon/protest-detection-violence-estimation
Implementation of the model used in the paper Protest Activity Detection and Perceived Violence Estimation from Social Media Images (ACM Multimedia 2017)
Performs multi-task classification on protest imagery using a fine-tuned ImageNet ResNet50 backbone, simultaneously detecting protest presence, identifying visual attributes (signs, police, fire, group size), and predicting continuous violence perception scores. Built on PyTorch with training and batch inference pipelines supporting GPU acceleration, evaluated against the authors' curated UCLA Protest Image Dataset of 40K+ annotated images with 11 binary labels and violence regression targets.
185 stars. No commits in the last 6 months.
Stars
185
Forks
46
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Mar 21, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/wondonghyeon/protest-detection-violence-estimation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
chandran-jr/Violence-Alert-System
🎦A violence detector using MobileNetV2 pretrained model and image enhancement algorithms and...
sukhitashvili/violence-detection
Deep learning based algorithm which is capable of detecting violence in indoor or outdoor...
shreyash2610/Convolutional-Long-Short-Term-Memory-based-IOT-node-for-Violence-Detection
Abstract— Violence detection has been investigated extensively in the literature. Recently, IOT...
Jawabreh0/gun-detection
Basic gun detection algorithm, designed using YOLOv7 with AR-15 guns training data
ash-iiiiish/VIGIl.AI-Violence-WeaponDetectionTool
An AI-Powered System which can detect any type of violence occured in a video file that can be...