Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Pose-Guided Graph Convolutional Networks for Skeleton-Based Action Recognitionopen access

Authors
Chen, HanJiang, YifanKo, Hanseok
Issue Date
2022
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Keywords
Convolutional neural networks; Training; Three-dimensional displays; Correlation; Pose estimation; Feature extraction; Data models; Skeletons; Action recognition; attention mechanism; feature fusion; graph convolutional networks; human skeleton; pose information
Citation
IEEE ACCESS, v.10, pp.111725 - 111731
Indexed
SCIE
SCOPUS
Journal Title
IEEE ACCESS
Volume
10
Start Page
111725
End Page
111731
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/146099
DOI
10.1109/ACCESS.2022.3214812
ISSN
2169-3536
Abstract
Graph convolutional networks (GCN), which can model the human body skeletons as spatial and temporal graphs, have shown remarkable potential in skeleton-based action recognition. However, in the existing GCN-based methods, graph-structured representation of the human skeleton makes it difficult to be fused with other modalities, especially in the early stages. This may limit their scalability and performance in action recognition tasks. In addition, the pose information, which naturally contains informative and discriminative clues for action recognition, is rarely explored together with skeleton data in existing methods. In this work, we proposed pose-guided GCN (PG-GCN), a multi-modal framework for high-performance human action recognition. In particular, a multi-stream network is constructed to simultaneously explore the robust features from both the pose and skeleton data, while a dynamic attention module is designed for early-stage feature fusion. The core idea of this module is to utilize a trainable graph to aggregate features from the skeleton stream with that of the pose stream, which leads to a network with more robust feature representation ability. Extensive experiments show that the proposed PG-GCN can achieve state-of-the-art performance on the NTU RGB+D 60 and NTU RGB+D 120 datasets.
Files in This Item
There are no files associated with this item.
Appears in
Collections
College of Engineering > School of Electrical Engineering > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Ko, Han seok photo

Ko, Han seok
공과대학 (전기전자공학부)
Read more

Altmetrics

Total Views & Downloads

BROWSE