Convolutional spatio-temporal sequential inference model for human interaction behavior recognition
Frontiers in Computer Science · 15.07.2025 · 7
DOI: 10.3389/fcomp.2025.1576775 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Computer Science, online erschienen am 15.07.2025. Verfasst von Lizhong Jin und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
Human action recognition is a critical task with broad applications and remains a challenging problem due to the complexity of modeling dynamic interactions between individuals. Existing methods, including skeleton sequence-based and RGB video-based models, have achieved impressive accuracy but often suffer from high computational costs and limited effectiveness in modeling human interaction behaviors.
Methods
To address these limitations, we propose a lightweight Convolutional Spatiotemporal Sequence Inference Model (CSSIModel) for recognizing human interaction behaviors. The model extracts features from skeleton sequences using DINet and from RGB video frames using ResNet-18. These multi-modal features are fused and processed using a novel multiscale two-dimensional convolutional peak-valley inference module to classify interaction behaviors.
Results
CSSIModel achieves competitive results across several benchmark datasets: 87.4% accuracy on NTU RGB+D 60 (XSub), 94.1% on NTU RGB+D 60 (XView), 80.5% on NTU RGB+D 120 (XSub), and 84.9% on NTU RGB+D 120 (XSet). These results are comparable to or exceed those of state-of-the-art methods.
Discussion
The proposed method effectively balances accuracy and computational efficiency. By significantly reducing model complexity while maintaining high performance, CSSIModel is well-suited for real-time applications and provides a valuable reference for future research in multi-modal human behavior recognition.
Zitieren
APA
Jin, L., Fan, R., Han, X., & Cui, X. (2025). Convolutional spatio-temporal sequential inference model for human interaction behavior recognition. Frontiers in Computer Science, 7. https://doi.org/10.3389/fcomp.2025.1576775
Vancouver
Jin L, Fan R, Han X, Cui X. Convolutional spatio-temporal sequential inference model for human interaction behavior recognition. Frontiers in Computer Science. 2025;7. doi:10.3389/fcomp.2025.1576775
BibTeX
@article{Jin2025,
author = {Jin, Lizhong and Fan, Rulong and Han, Xiaoling and Cui, Xueying},
title = {Convolutional spatio-temporal sequential inference model for human interaction behavior recognition},
journal = {Frontiers in Computer Science},
year = {2025},
volume = {7},
doi = {10.3389/fcomp.2025.1576775}
}
EUVIMED