Open-source Video Understanding Model videomae-base-ssv2-finetuned-rwf2000 - Accurately Detect Violent Behaviors in Videos

Videomae Base Ssv2 Finetuned Rwf2000

Developed by lmazzon70

A video understanding model based on the VideoMAE architecture, fine-tuned on the RWF-2000 dataset for violence detection tasks

Video Processing

Transformers

#Video Action Recognition #Fine-tuning Models #Spatiotemporal Feature Extraction

Downloads 30

Release Time : 1/9/2023

Model Overview

This model is a video classification model based on the VideoMAE architecture, specifically fine-tuned for violence detection tasks. It can analyze video content and identify violent behaviors.

Model Features

Video Violence Detection

A video understanding model optimized specifically for violence detection tasks

Self-supervised Pre-training

Utilizes the VideoMAE self-supervised pre-training architecture with excellent video feature extraction capabilities

Efficient Fine-tuning

Fine-tuned on the RWF-2000 dataset to adapt to specific violence detection tasks

Model Capabilities

Video Content Analysis

Violence Behavior Recognition

Video Classification

Use Cases

Public Safety

Surveillance Video Analysis

Automatically analyzes violent behaviors in surveillance videos

Accuracy 45.71%

Content Moderation

Video Content Filtering

Automatically identifies and filters violent content uploaded by users

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.419	0.25	800	0.6122	0.76
1.2475	1.25	1600	1.4005	0.6038
0.0131	2.25	2400	1.2546	0.685
0.1379	3.25	3200	0.9228	0.7712

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご

Videomae Base Ssv2 Finetuned Rwf2000

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 videomae-base-ssv2-finetuned-rwf2000

🚀 Quick Start

📚 Documentation

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

📄 License