The search functionality is under construction.
The search functionality is under construction.

Open Access
Recent Advances in Video Action Recognition with 3D Convolutions

Kensho HARA

  • Full Text Views

    71

  • Cite this
  • Free PDF (663.4KB)

Summary :

The performance of video action recognition has improved significantly in recent decades. Current recognition approaches mainly utilize convolutional neural networks to acquire video feature representations. In addition to the spatial information of video frames, temporal information such as motions and changes is important for recognizing videos. Therefore, the use of convolutions in a spatiotemporal three-dimensional (3D) space for representing spatiotemporal features has garnered significant attention. Herein, we introduce recent advances in 3D convolutions for video action recognition.

Publication
IEICE TRANSACTIONS on Fundamentals Vol.E104-A No.6 pp.846-856
Publication Date
2021/06/01
Publicized
2020/12/07
Online ISSN
1745-1337
DOI
10.1587/transfun.2020IMP0012
Type of Manuscript
Special Section INVITED PAPER (Special Section on Image Media Quality)
Category

Authors

Kensho HARA
  the National Instutite of Advanced Industrial Science and Technology

Keyword