• search
    search
  • reviewers
    reviewers
  • feeds
    feeds
  • assignments
    assignments
  • settings
  • logout

Automatic content understanding with cascaded spatial-temporal deep framework for capsule endoscopy videos.

Honghan ChenXiao WuTao GanQiang Peng
Published in: Neurocomputing (2017)
Keyphrases
  • spatial temporal
  • capsule endoscopy
  • video sequences
  • action recognition
  • video shots
  • computer vision
  • spatial and temporal
  • computer aided
  • human actions
  • information retrieval
  • high level
  • spatio temporal