Skip to content

Ivan020121/CIKP

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CIKP: A Contrastive IMU-Keypoint Pretraining Framework for Unsafe Behavior Recognition of Scaffolding Workers

Three-stage cross-modal alignment training strategy

  • Stage 1: Supervised Representation Learning
  • Stage 2: Contrastive Learning
  • Stage 3: Classifier Refinement

Environment

  • python == 3.9
  • pytorch == 2.2.0
  • mamba-ssm == 2.2.6.post3
  • scikit-learn == 1.3.0
  • pandas == 2.2.2
  • numpy == 1.26.4

Usage

The detailed descriptions about the folders are as following:

Folder name Description
imunet The source code of TFusion
kpnet The source code of MSTGCN
data The processed datasets
figure The architecture of CIKP
checkpoint The save model weights after training

To evaluate CIKP on a dataset, run the corresponding test.ipynb in the code folder:

python test.ipynb

Dataset

About

A Contrastive IMU-Keypoint Pretraining Framework for Unsafe Behavior Recognition of Scaffolding Workers

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors