V

Videomae Base Finetuned Deception Dataset

Developed by NiklasTUM
A video analysis model fine-tuned based on MCG-NJU/videomae-base for deception detection tasks, achieving an accuracy of 70.37%
Downloads 36
Release Time : 4/24/2025

Model Overview

This model is a video classification model based on the VideoMAE architecture, specifically fine-tuned for deception detection tasks. It can analyze video content and determine whether deceptive behavior is present.

Model Features

High Accuracy
Achieves 70.37% accuracy on deception detection tasks
Based on VideoMAE Architecture
Utilizes the efficient VideoMAE self-supervised learning pre-training architecture
Small Batch Training Optimization
Effectively trained on limited hardware resources using gradient accumulation (batch size 16)

Model Capabilities

Video Content Analysis
Deceptive Behavior Detection
Video Classification

Use Cases

Security Monitoring
Interview Video Analysis
Analyze deceptive behavior in job interview videos
70.37% accuracy
Psychological Research
Behavior Analysis
Study the characteristic manifestations of human deceptive behavior
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase