Skip to main content

Attention-Based Recurrent Autoencoder for Motion Capture Denoising.

Zhu, Y., Zhang, F. and Xiao, Z., 2022. Attention-Based Recurrent Autoencoder for Motion Capture Denoising. Journal of Internet Technology, 23 (6), 1325-1333.

Full text available as:

2792-3791-1-PB.pdf - Published Version


DOI: 10.53106/160792642022112306015


To resolve the problem of massive loss of MoCap data from optical motion capture, we propose a novel network architecture based on attention mechanism and recurrent network. Its advantage is that the use of encoder-decoder enables automatic human motion manifold learning, capturing the hidden spatial-temporal relationships in motion sequences. In addition, by using the multi-head attention mechanism, it is possible to identify the most relevant corrupted frames with specific position information to recovery the missing markers, which can lead to more accurate motion reconstruction. Simulation experiments demonstrate that the network model we proposed can effectively handle the large-scale missing markers problem with better robustness, smaller errors and more natural recovered motion sequence compared to the reference method.

Item Type:Article
Uncontrolled Keywords:Motion capture; Attention mechanism; Deep learning; Neural network
Group:Faculty of Media & Communication
ID Code:37857
Deposited By: Symplectic RT2
Deposited On:05 Dec 2022 13:57
Last Modified:05 Dec 2022 13:57


Downloads per month over past year

More statistics for this item...
Repository Staff Only -