vivit-b-16x2-kinetics400-finetuned-cctv-surveillance Open-source Model - for Precise Action Recognition in CCTV Surveillance

Vivit B 16x2 Kinetics400 Finetuned Cctv Surveillance

Developed by ratchy-oak

A video action recognition model based on the ViViT architecture, fine-tuned specifically for CCTV surveillance scenarios, excelling in action recognition tasks.

Video Processing

Transformers

Open Source License:MIT #Video Action Recognition #High-Precision Surveillance #CCTV Analysis

Downloads 1,939

Release Time : 6/10/2024

Model Overview

This model is a video classification model based on the ViViT architecture, pre-trained on the Kinetics-400 dataset and fine-tuned for surveillance scenarios. It is suitable for action recognition and behavior analysis tasks in videos.

Model Features

High-Precision Action Recognition

Achieves 95.59% accuracy and 94.30% F1 score on the evaluation dataset.

Optimized for Surveillance Scenarios

Fine-tuned specifically for CCTV surveillance scenarios, making it ideal for security applications.

Efficient Video Processing

Based on the ViViT architecture, it effectively processes temporal information in videos.

Model Capabilities

Video Action Recognition

Behavior Analysis

Anomaly Detection

Use Cases

Security Surveillance

Anomaly Detection

Detects abnormal or suspicious activities in surveillance videos.

High accuracy in recognizing various abnormal behavior patterns.

Personnel Behavior Analysis

Analyzes activity patterns of individuals within monitored areas.

Capable of identifying common behaviors such as walking, running, and loitering.

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Recall	Precision
1.5836	0.12	504	0.3644	0.9206	0.8850	0.9206	0.8799
0.3767	1.12	1008	0.2586	0.9265	0.8994	0.9265	0.8831
0.2063	2.12	1512	0.2190	0.9294	0.9097	0.9294	0.9002
0.4514	3.12	2016	0.2217	0.9529	0.9419	0.9529	0.9380
0.2678	4.12	2520	0.1919	0.9529	0.9419	0.9529	0.9380
0.2311	5.12	3024	0.1797	0.9412	0.9252	0.9412	0.9141
0.5256	6.12	3528	0.1690	0.9559	0.9430	0.9559	0.9333
0.539	7.12	4032	0.1678	0.9529	0.9398	0.9529	0.9297

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

Vivit B 16x2 Kinetics400 Finetuned Cctv Surveillance

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 vivit-b-16x2-kinetics400-finetuned-cctv-surveillance

🚀 Quick Start

📚 Documentation

Model description

Intended uses & limitations

Training and evaluation data

🔧 Technical Details

Training procedure

Training hyperparameters

Training results

Framework versions

📄 License