HO-GCN: Human–Object Adaptive Topological Interaction GCN for escalator dangerous behavior recognition
Authors:
- Jinjing GuJGJinjing Gu
- Chaobin HuangCHChaobin Huang
- Zhengpeng ZhaoZZZhengpeng Zhao
- Yuanyuan PuYPYuanyuan Pu
- Xin DengXDXin Deng
- 9 September 2026
- journal article
- Published by Elsevier in Image and Vision Computing
- Vol. 175
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (52102382)
- National Natural Science Foundation of China (52562046)
- Humanities and Social Sciences Youth Foundation, Ministry of Education (25XJCZH003)
This publication has 35 references indexed in Scilit:
- MM-Net: Facial expression recognition based on multi-level and multi-scale attention mechanismsPattern Recognition Letters, 2026
- MCNet: A unified multi-center graph convolutional network based on skeletal behavior recognitionAlexandria Engineering Journal, 2025
- TSCANet: a two-stream context aggregation network for weakly-supervised temporal action localizationThe Journal of Supercomputing, 2024
- Global-Local Motion Transformer for Unsupervised Skeleton-Based Action Learning2022
- Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN2018
- Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks2017
- A New Representation of Skeleton Sequences for 3D Action Recognition2017
- Skeleton based action recognition with convolutional neural network2015
- Hierarchical recurrent neural network for skeleton based action recognition2015
- LabelMe: A Database and Web-Based Tool for Image AnnotationInternational Journal of Computer Vision, 2007