V

Videomae Base Finetuned Ucf101 Subset

Developed by burcusu
A video classification model fine-tuned on a subset of UCF101 based on the VideoMAE base model, achieving 95.22% accuracy
Downloads 17
Release Time : 1/15/2023

Model Overview

This model is a video understanding 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 95.22% classification accuracy on the UCF101 subset
Self-supervised Pre-training
Utilizes the VideoMAE architecture with masked autoencoder for pre-training
Efficient Fine-tuning
Performs few-shot fine-tuning on the base model for rapid adaptation to specific tasks

Model Capabilities

Video Action Recognition
Video Content Classification
Spatio-temporal Feature Extraction

Use Cases

Video Analysis
Action Recognition System
Identifies human actions and behaviors in videos
Achieves 95.22% accuracy on the UCF101 subset
Video Content Classification
Automatically classifies and labels video content
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase