University of Oulu

Peng, W., Hong, X., Chen, H., & Zhao, G. (2020). Learning Graph Convolutional Network for Skeleton-Based Human Action Recognition by Neural Searching. Proceedings of the AAAI Conference on Artificial Intelligence, 34(03), 2669-2676. https://doi.org/10.1609/aaai.v34i03.5652

Learning graph convolutional network for skeleton-based human action recognition by neural searching

Saved in:
Author: Peng, Wei1; Hong, Xiaopeng2,3,1; Chen, Haoyu1;
Organizations: 1CMVS, University of Oulu, Finland
2School of Cyber Science and Engineering, Faculty of Electronic and Information Engineering, Xi’an Jiaotong University, PRC
3Research Center for Artificial Intelligence, Peng Cheng Laboratory
4School of Information and Technology, Northwest University, PRC
Format: article
Version: published version
Access: open
Online Access: PDF Full Text (PDF, 0.7 MB)
Persistent link: http://urn.fi/urn:nbn:fi-fe202104099803
Language: English
Published: Association for the Advancement of Artificial Intelligence, 2021
Publish Date: 2021-04-09
Description:

Abstract

Human action recognition from skeleton data, fuelled by the Graph Convolutional Network (GCN) with its powerful capability of modeling non-Euclidean data, has attracted lots of attention. However, many existing GCNs provide a pre-defined graph structure and share it through the entire network, which can loss implicit joint correlations especially for the higher-level features. Besides, the mainstream spectral GCN is approximated by one-order hop such that higher-order connections are not well involved. All of these require huge efforts to design a better GCN architecture. To address these problems, we turn to Neural Architecture Search (NAS) and propose the first automatically designed GCN for this task. Specifically, we explore the spatial-temporal correlations between nodes and build a search space with multiple dynamic graph modules. Besides, we introduce multiple-hop modules and expect to break the limitation of representational capacity caused by one-order approximation. Moreover, a corresponding sampling- and memory-efficient evolution strategy is proposed to search in this space. The resulted architecture proves the effectiveness of the higher-order approximation and the layer-wise dynamic graph modules. To evaluate the performance of the searched model, we conduct extensive experiments on two very large scale skeleton-based action recognition datasets. The results show that our model gets the state-of-the-art results in term of given metrics.

see all

ISBN Print: 978-1-57735-835-0
Pages: 2669 - 2676
DOI: 10.1609/aaai.v34i03.5652
OADOI: https://oadoi.org/10.1609/aaai.v34i03.5652
Host publication: Proceedings of the 43th AAAI Conference on Artificial Intelligence. February 7–12, 2020, New York, USA
Conference: AAAI Conference on Artificial Intelligence
Type of Publication: A4 Article in conference proceedings
Field of Science: 113 Computer and information sciences
Subjects:
Funding: This work was supported by the Academy of Finland ICT 2023 project (Grant No. 313600), Tekes Fidipro program (Grant No. 1849/31/2015) and Business Finland project (Grant No. 3116/31/2017), Infotech Oulu, and the National Natural Science Foundation of China (Grants No. 61772419). As well, the authors wish to acknowledge CSCIT Center for Science, Finland, for computational resources.
Academy of Finland Grant Number: 313600
Detailed Information: 313600 (Academy of Finland Funding decision)
Copyright information: © 2020, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.