Comparison between Recurrent Networks and Temporal Convolutional Networks Approaches for Skeleton-Based Action Recognition

Comparison between Recurrent Networks and Temporal Convolutional Networks Approaches for Skeleton-Based Action Recognition

Action recognition plays an important role in various applications such as video monitoring, automatic video indexing, crowd analysis, human-machine interaction, smart homes and personal assistive robotics. In this paper, we propose improvements to some methods for human action recognition from vide...

Full description

Bibliographic Details
Main Authors: Mihai Nan, Mihai Trăscău, Adina Magda Florea, Cezar Cătălin Iacob
Format: Article
Language:English
Published: MDPI AG 2021-03-01
Series:Sensors
Subjects:
action recognition
sequence-to-sequence
temporal convolutional networks
recurrent networks
Online Access:https://www.mdpi.com/1424-8220/21/6/2051

Internet

https://www.mdpi.com/1424-8220/21/6/2051

Similar Items