본문 바로가기
  • Home

ADD-Net: Attention Based 3D Dense Network for Action Recognition

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2019, 24(6), pp.21-28
  • DOI : 10.9708/jksci.2019.24.06.021
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : April 30, 2019
  • Accepted : May 30, 2019
  • Published : June 28, 2019

Qiaoyue Man 1 Young Im Cho 1

1가천대학교

Accredited

ABSTRACT

Recent years with the development of artificial intelligence and the success of the deep model, they have been deployed in all fields of computer vision. Action recognition, as an important branch of human perception and computer vision system research, has attracted more and more attention. Action recognition is a challenging task due to the special complexity of human movement, the same movement may exist between multiple individuals. The human action exists as a continuous image frame in the video, so action recognition requires more computational power than processing static images. And the simple use of the CNN network cannot achieve the desired results. Recently, the attention model has achieved good results in computer vision and natural language processing. In particular, for video action classification, after adding the attention model, it is more effective to focus on motion features and improve performance. It intuitively explains which part the model attends to when making a particular decision, which is very helpful in real applications. In this paper, we proposed a 3D dense convolutional network based on attention mechanism(ADD-Net), recognition of human motion behavior in the video.

Citation status

* References for papers published after 2023 are currently being built.