Videomae Open-Source Video Action Recognition Model - Free Deployment for Accurate Video Action Recognition

Videomae Base Short Finetuned Ssv2 Finetuned Rwf2000 Epochs8 Batch8 Fp16

Developed by lmazzon70

Video action recognition model based on VideoMAE architecture, pre-trained on SSv2 dataset and further fine-tuned on RWF-2000 dataset

Video Processing

Transformers

#Video Action Recognition #Fine-tuning Transfer Learning #FP16 Acceleration

Downloads 14

Release Time : 1/11/2023

Model Overview

This is a deep learning model for video action recognition, based on the VideoMAE architecture, pre-trained through self-supervised learning and fine-tuned for specific action recognition tasks.

Model Features

Efficient Video Understanding

Adopts VideoMAE architecture to achieve efficient video representation learning through masked autoencoder

Two-stage Training

Pre-trained on SSv2 dataset first, then fine-tuned on RWF-2000 dataset to enhance task-specific performance

Mixed Precision Training

Uses FP16 mixed precision training to improve training efficiency

Model Capabilities

Video Action Recognition

Temporal Action Analysis

Video Content Understanding

Use Cases

Security Surveillance

Violence Detection

Identify violent behaviors in surveillance videos

Sports Analysis

Athlete Action Recognition

Identify specific movements and techniques of athletes

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4239	0.06	200	0.3879	0.82
0.4179	1.06	400	1.1635	0.6162
0.4329	2.06	600	0.8215	0.63
0.3051	3.06	800	0.5541	0.7412
0.172	4.06	1000	0.4696	0.8363
0.1955	5.06	1200	0.5384	0.78
0.2301	6.06	1400	1.3358	0.635
0.2995	7.06	1600	1.0372	0.7087
0.3789	8.06	1800	0.8670	0.7412
0.2525	9.06	2000	0.5886	0.8225
0.1846	10.06	2200	0.7851	0.735
0.1547	11.06	2400	0.8905	0.7638
0.2501	12.06	2600	0.9807	0.76
0.1046	13.06	2800	1.0419	0.7438
0.0786	14.06	3000	1.0128	0.7538
0.0178	15.06	3200	1.0156	0.75

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 Short Finetuned Ssv2 Finetuned Rwf2000 Epochs8 Batch8 Fp16

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 videomae-base-short-finetuned-ssv2-finetuned-rwf2000-epochs8-batch8-fp16

🚀 Quick Start

📚 Documentation

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

📄 License