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

Additional URL

https://doi.org/10.1109/TNNLS.2020.3015848

This document is currently not available here.

Share

COinS