Transductive zero-shot action recognition via visually connected graph convolutional networks
Publication Type
Journal Article
Publication Date
8-2021
Abstract
With the explosive growth of action categories, zero-shot action recognition aims to extend a well-trained model to novel/unseen classes. To bridge the large knowledge gap between seen and unseen classes, in this brief, we visually associate unseen actions with seen categories in a visually connected graph, and the knowledge is then transferred from the visual features space to semantic space via the grouped attention graph convolutional networks (GAGCNs). In particular, we extract visual features for all the actions, and a visually connected graph is built to attach seen actions to visually similar unseen categories. Moreover, the proposed grouped attention mechanism exploits the hierarchical knowledge in the graph so that the GAGCN enables propagating the visual-semantic connections from seen actions to unseen ones. We extensively evaluate the proposed method on three data sets: HMDB51, UCF101, and NTU RGB + D. Experimental results show that the GAGCN outperforms state-of-the-art methods.
Keywords
Visualization, Feature extraction, Semantics, Correlation, Computational modeling, Learning systems, Explosives, Action recognition, graph convolutional network (GCN), zero-shot learning (ZSL)
Discipline
Information Security
Research Areas
Information Systems and Management
Publication
IEEE Transactions on Neural Networks and Learning Systems
Volume
32
Issue
8
First Page
3761
Last Page
3769
ISSN
2162-237X
Identifier
10.1109/TNNLS.2020.3015848
Publisher
Institute of Electrical and Electronics Engineers
Citation
XU, Yangyang; HAN, Chu; QIN, Jing; XU, Xuemiao; HAN, Guoqiang; and HE, Shengfeng.
Transductive zero-shot action recognition via visually connected graph convolutional networks. (2021). IEEE Transactions on Neural Networks and Learning Systems. 32, (8), 3761-3769.
Available at: https://ink.library.smu.edu.sg/sis_research/7883
Additional URL
https://doi.org/10.1109/TNNLS.2020.3015848