TY - GEN
T1 - PREDICTING HUMAN MOTION USING KEY SUBSEQUENCES
AU - Li, Menghao
AU - Pei, Mingtao
AU - Liang, Wei
N1 - Publisher Copyright:
© 2022 IEEE
PY - 2022
Y1 - 2022
N2 - Human motion prediction is an important task in computer vision, and has a wide range of applications, such as autonomous driving and human-robot interaction. Usually, human motion tends to repeat itself and follows patterns that are well-represented by a few short key subsequences. Based on the above observations, we propose an attention-based feed-forward network, which is explicitly guided by the key subsequences, for human motion prediction. Specifically, we obtain the key subsequences by clustering, extract motion attention by the similarity between the observed poses and the motion context of corresponding key subsequences, and aggregate the relevant key subsequences by a graph convolutional network to predict human motion. Experimental results on public human motion datasets show that our method achieves better performance over state-of-the-art methods in motion prediction.
AB - Human motion prediction is an important task in computer vision, and has a wide range of applications, such as autonomous driving and human-robot interaction. Usually, human motion tends to repeat itself and follows patterns that are well-represented by a few short key subsequences. Based on the above observations, we propose an attention-based feed-forward network, which is explicitly guided by the key subsequences, for human motion prediction. Specifically, we obtain the key subsequences by clustering, extract motion attention by the similarity between the observed poses and the motion context of corresponding key subsequences, and aggregate the relevant key subsequences by a graph convolutional network to predict human motion. Experimental results on public human motion datasets show that our method achieves better performance over state-of-the-art methods in motion prediction.
KW - Attention
KW - Clustering
KW - Human motion prediction
UR - http://www.scopus.com/inward/record.url?scp=85134021718&partnerID=8YFLogxK
U2 - 10.1109/ICASSP43922.2022.9747885
DO - 10.1109/ICASSP43922.2022.9747885
M3 - Conference contribution
AN - SCOPUS:85134021718
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 1835
EP - 1839
BT - 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022
Y2 - 23 May 2022 through 27 May 2022
ER -