Encoding for human action recognition

HIGHLIGHTS

• who: Agglomerative Clustering and colleagues from the Department of Computer Engineering, University of Engineering and Technology, Taxila, PakistanDepartment of Computer Science, University of KwaZulu-Natal, Durban, South Africa have published the Article: Encoding for Human Action Recognition, in the Journal: (JOURNAL)
• what: The authors propose a novel codebook generation and hybrid encoding scheme for classification of action videos. The authors explore different CNN architectures for extracting spatio-temporal features. The authors propose a Vector of Locally Aggregated Descriptors and fuse it with locality-based coding to form a hybrid feature vector. The aim of this . . .
  

   

  

  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.