Aarhus Universitets segl

English

Du er her: AU » Om AU » Organisation » Temporal Attention-Augmented Graph Convolutional Network ...

Om AU

Temporal Attention-Augmented Graph Convolutional Network for Efficient Skeleton-Based Human Action Recognition

Publikation: Bidrag til bog/antologi/rapport/proceeding › Konferencebidrag i proceedings › Forskning › peer review

Links

DOI

Graph convolutional networks (GCNs) have been very successful in modeling non-Euclidean data structures, like sequences of body skeletons forming actions modeled as spatio-temporal graphs. Most GCN-based action recognition methods use deep feed-forward networks with high computational complexity to process all skeletons in an action. This leads to a high number of floating point operations (ranging from 16G to 100G FLOPs) to process a single sample, making their adoption in restricted computation application scenarios infeasible. In this paper, we propose a temporal attention module (TAM) for increasing the efficiency in skeleton-based action recognition by selecting the most informative skeletons of an action at the early layers of the network. We incorporate the TAM in a lightweight GCN topology to further reduce the overall number of computations. Experimental results on two benchmark datasets show that the proposed method outperforms with a large margin the baseline GCN-based method while having ×2.9 less number of computations. Moreover, it performs on par with the state-of-the-art with up to ×9.6 less number of computations.

OriginalsprogEngelsk
TitelProceedings of ICPR 2020 - 25th International Conference on Pattern Recognition
Antal sider8
ForlagIEEE
Udgivelsesår2021
Sider7907-7914
Artikelnummer9412091
ISBN (trykt)978-1-7281-8809-6
ISBN (Elektronisk)978-1-7281-8808-9
DOI
StatusUdgivet - 2021
Begivenhed2020 25th International Conference on Pattern Recognition (ICPR) - Virtual, Milano, Italien
Varighed: 10 jan. 2021 → 15 jan. 2021
https://www.micc.unifi.it/icpr2020/?utm_source=researchbib

Konference

Konference2020 25th International Conference on Pattern Recognition (ICPR)
LokationVirtual
LandItalien
ByMilano
Periode10/01/2021 → 15/01/2021
Internetadresse

Se relationer på Aarhus Universitet Citationsformater

ID: 222817986