V

Videomae Base Badminton Strokes Finetuned Stroke Classification 10

Developed by yexter
A video action classification model fine-tuned based on MCG-NJU/videomae-base, specializing in badminton stroke recognition
Downloads 78
Release Time : 1/20/2025

Model Overview

This model is a video classification model based on the VideoMAE architecture, specifically fine-tuned for badminton stroke classification tasks. It achieves an accuracy of 85.51% on the evaluation set.

Model Features

High-precision action recognition
Achieves 85.51% accuracy in badminton stroke classification tasks
Based on VideoMAE architecture
Utilizes an efficient video masked autoencoder pre-training architecture, suitable for video understanding tasks
Lightweight fine-tuning
Efficient fine-tuning on the base model to adapt to specific domain tasks

Model Capabilities

Video action classification
Badminton stroke recognition
Temporal video analysis

Use Cases

Sports analysis
Badminton training analysis
Automatically identifies the types of strokes performed by athletes
Helps coaches analyze athletes' technical movements
Match action statistics
Counts the frequency of various stroke types during matches
Provides data support for tactical analysis
Smart sports equipment
Intelligent training assistance
Integrated into training equipment for real-time feedback on movement quality
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase