Skip to content

Towards efficient and objective work sampling: recognizing workers' activities in site surveillance with two-stream convnets

License

Notifications You must be signed in to change notification settings

eric4note/worksampling

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Towards efficient and objective work sampling: recognizing workers' activities in site surveillance with two-stream convnets

  1. A demo concerning our idea can be found at https://www.youtube.com/watch?v=6wF8EM6cU6E

  2. The cateogized/labelled 16 activities, which are sptiotemporally segemented in to 3-second clips can be downloaded at: https://drive.google.com/open?id=13VB3FASmgNVz82nNvmH_mNf8ADtgB_kC

  3. The streamed flow fields and RGB images can be downloaded at: https://drive.google.com/open?id=0B1Mszlp0nZZoYUc5SnZvTFNJSEk

  4. The six models for the three splits can be found at: https://drive.google.com/open?id=0B1Mszlp0nZZoYUc5SnZvTFNJSEk

About

Towards efficient and objective work sampling: recognizing workers' activities in site surveillance with two-stream convnets

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published