A transformer-based capsule network for 3d part-whole relationship learning

HIGHLIGHTS

• who: Yu Chen et al. from the Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, China have published the research work: A Transformer-Based Capsule Network for 3D Part-Whole Relationship Learning, in the Journal: Entropy 2022, 24, 678. of /2022/
• what: Similar to token (word) states in NLP the authors propose local tokens to encode local geometric information. On this basis the authors design a shape-Transformer-based capsule routing algorithm. The authors performed classification tasks on the deformable 3D object data sets SHREC10 and SHREC15 and the large data set ModelNet40 . . .
  

   

  

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

  Thanks :)

  Username or E-mail:

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