Videomae Base Finetuned Ucf101 Subset
A video classification model fine-tuned on a subset of UCF101 based on the VideoMAE base model
Downloads 14
Release Time : 2/24/2023
Model Overview
This model is a video classification model fine-tuned on a subset of the UCF101 dataset based on the VideoMAE base architecture, primarily used for video action recognition tasks.
Model Features
Efficient Video Representation Learning
Utilizes the VideoMAE architecture to learn spatiotemporal feature representations of videos through masked autoencoder pre-training.
Domain-Specific Fine-tuning
Fine-tuned on a subset of the UCF101 action recognition dataset to adapt to specific video classification tasks.
Lightweight Inference
The base model has a moderate size, making it suitable for practical deployment applications.
Model Capabilities
Video Action Recognition
Spatiotemporal Feature Extraction
Video Classification
Use Cases
Video Analysis
Action Recognition
Recognize human actions in videos
Achieved 83.24% accuracy on the evaluation set
Video Content Classification
Classify and label video content
Featured Recommended AI Models
Š 2025AIbase