Structural-attentioned LSTM for action recognition based on skeleton

Pengcheng Wang; Shaobin Li

doi:10.1117/12.2513868

29 October 2018 Structural-attentioned LSTM for action recognition based on skeleton

Pengcheng Wang, Shaobin Li

Proceedings Volume 10836, 2018 International Conference on Image and Video Processing, and Artificial Intelligence; 108361A (2018) https://doi.org/10.1117/12.2513868
Event: 2018 International Conference on Image, Video Processing and Artificial Intelligence, 2018, Shanghai, China

Abstract

In this paper, the Spatio-Temporal graph of Structural-RNN[6] is developed and applied to action recognition task. We proposed a Structural-Attentioned LSTM network by adding joints, changing the specific connection mode in the original spatio-temporal graph, and introducing attention mechanism to enable the network to select edges with best representation of action automatically. We take multiple experiments on the public dataset JHMDB[10] to verify the validity of our model, achieved good results when only limited features were used.

Citation Download Citation

Pengcheng Wang and Shaobin Li "Structural-attentioned LSTM for action recognition based on skeleton", Proc. SPIE 10836, 2018 International Conference on Image and Video Processing, and Artificial Intelligence, 108361A (29 October 2018); https://doi.org/10.1117/12.2513868

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available