Convolutional-de-convolutional neural networks for recognition of surgical workflow

HIGHLIGHTS

• who: Kun-hua Zhong from the Nanjing University of Posts and Telecommunications, China have published the paper: Convolutional-de-convolutional neural networks for recognition of surgical workflow, in the Journal: (JOURNAL)
• what: The authors describe how to train the CDC network using unmarked video. From the results in Table 2, the approach has the shortest transition delay .
• how: The authors proposed an unsupervised method for training Convolutional-De-Convolutional (CDC) networks to sort surgical workflow frames which are simultaneously rolled out in space (for semantic abstraction) and temporal convolution (for frame-level resolution . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.