videomae-base-finetuned-ucf101-subset Open-source Video Understanding Model

Videomae Base Finetuned Ucf101 Subset

Developed by anitavero

A video understanding model fine-tuned on a subset of UCF101 based on the VideoMAE base model, achieving 95.71% accuracy

Video Processing

Transformers

#Video Action Recognition #High Accuracy #UCF101 Fine-tuning

Downloads 14

Release Time : 1/17/2023

Model Overview

This model is a video classification model based on the VideoMAE architecture, specifically fine-tuned for a subset of the UCF101 dataset, suitable for video action recognition tasks

Model Features

High Accuracy

Achieves 95.71% classification accuracy on the evaluation set

Based on VideoMAE Architecture

Utilizes a masked autoencoder pre-training architecture for video understanding

Lightweight Fine-tuning

Requires only a small amount of data for fine-tuning on the base model to achieve excellent performance

Model Capabilities

Video Action Recognition

Video Content Classification

Temporal Feature Extraction

Use Cases

Video Analysis

Action Recognition

Recognize human actions in videos

Achieves 95.71% accuracy on a subset of UCF101

Video Content Classification

Classify and label video content

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.1539	0.25	150	1.0269	0.6
0.6807	1.25	300	0.3809	0.8429
0.1908	2.25	450	0.4966	0.8429
0.445	3.25	600	0.1323	0.9571

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 Finetuned Ucf101 Subset

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 videomae-base-finetuned-ucf101-subset

🚀 Quick Start

📚 Documentation

📄 License

🔧 Technical Details

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions