Please use this identifier to cite or link to this item: http://bura.brunel.ac.uk/handle/2438/24566
Title: HMANet: Hyperbolic Manifold Aware Network for Skeleton-Based Action Recognition
Authors: Chen, J
Zhao, C
Wang, Q
Meng, H
Keywords: action recognition;hyperbolic manifold;Poincaré model;Riemannian geometry;spatio-temporal features
Issue Date: 2-May-2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Citation: Chen, J. et al. (2023) 'HMANet: Hyperbolic Manifold Aware Network for Skeleton-Based Action Recognition', IEEE Transactions on Cognitive and Developmental Systems, 15 (2), pp. 602 - 614. doi: 10.1109/tcds.2022.3171550.
Abstract: Skeleton-based action recognition has attracted significant attentions in recent years. To model the skeleton data, most popular methods utilize graph convolutional networks to fuse nodes located in different parts of the graph to obtain rich geometric information. However, these methods cannot be generalized to different graph structures due to their dependencies on the input of the topological structure. In this article, we design a novel hyperbolic manifold aware network without introducing a dynamic graph. Instead, it leverages Riemannian geometry attributes of a hyperbolic manifold. Specifically, this method utilizes the Poincaré model to embed the tree-like structure of the skeleton into a hyperbolic space to automatically capture hierarchical features, which may explore the underlying manifold of the data. To extract spatio-temporal features in the network, the features in manifold space are projected to a tangent space, and a tangent space features translation method based on the Levi–Civita connection was proposed. In addition, we introduce the geometric knowledge of Riemannian manifolds to further explain how features are transformed in the tangent space. Finally, we conduct experiments on several 3-D skeleton data sets with different structures, successfully verifying the effectiveness and advancement of the proposed method.
URI: https://bura.brunel.ac.uk/handle/2438/24566
DOI: https://doi.org/10.1109/tcds.2022.3171550
ISSN: 2379-8920
Other Identifiers: ORCiD: Jinghong Chen https://orcid.org/0000-0001-8650-790X
ORCiD: Chong Zhao https://orcid.org/0000-0002-9655-6454
ORCiD: Qicong Wang https://orcid.org/0000-0001-7324-0433
ORCiD: Hongying Meng https://orcid.org/0000-0002-8836-1382
Appears in Collections:Dept of Electronic and Electrical Engineering Research Papers

Files in This Item:
File Description SizeFormat 
FullText.pdfCopyright © 2022 Institute of Electrical and Electronics Engineers (IEEE). Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. See: https://journals.ieeeauthorcenter.ieee.org/become-an-ieee-journal-author/publishing-ethics/guidelinesand-policies/post-publication-policies/19.19 MBAdobe PDFView/Open


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