A novel two-level interactive action recognition model based on inertial data fusion

S Qiu, T Fan, J Jiang, Z Wang, Y Wang, J Xu, T Sun… - Information …, 2023 - Elsevier
Currently, the majority of solutions for human interactive action recognition typically rely on
machine vision methods, thus leading to limited application scenarios for accurate …

Toward Realistic 3D Human Motion Prediction With a Spatio-Temporal Cross-Transformer Approach

H Yu, X Fan, Y Hou, W Pei, H Ge… - … on Circuits and …, 2023 - ieeexplore.ieee.org
Human motion prediction intends to predict how humans move given a historical sequence
of 3D human motions. Recent transformer-based methods have attracted increasing …

FT-HID: a large-scale RGB-D dataset for first-and third-person human interaction analysis

Z Guo, Y Hou, P Wang, Z Gao, M Xu, W Li - Neural Computing and …, 2023 - Springer
Abstract Analysis of human interaction is one important research topic of human motion
analysis. It has been studied either using first-person vision (FPV) or third-person vision …

Direction-guided two-stream convolutional neural networks for skeleton-based action recognition

B Su, P Zhang, M Sun, M Sheng - Soft Computing, 2023 - Springer
In skeleton-based action recognition, treating skeleton data as pseudoimages using
convolutional neural networks (CNNs) has proven to be effective. However, among existing …

DivDiff: A Conditional Diffusion Model for Diverse Human Motion Prediction

H Yu, Y Hou, W Pei, YS Ong… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Diverse human motion prediction (HMP) aims to predict multiple plausible future motions
given an observed human motion sequence. It is a challenging task due to the diversity of …

Multi-stream ternary enhanced graph convolutional network for skeleton-based action recognition

J Kong, S Wang, M Jiang, TS Liu - Neural Computing and Applications, 2023 - Springer
A novel mechanism for skeleton-based action recognition is proposed in this paper by
enhancing and fusing diverse skeleton features from distinct levels. Graph convolutional …

Towards Efficient and Diverse Generative Model for Unconditional Human Motion Synthesis

H Yu, W Liu, J Bai, X Gui, Y Hou, YS Ong… - Proceedings of the 32nd …, 2024 - dl.acm.org
Recent generative methods have revolutionized the way of human motion synthesis, such
as Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), and …

Unsupervised video-based action recognition using two-stream generative adversarial network

W Lin, H Zeng, J Zhu, CH Hsia, J Hou… - Neural Computing and …, 2024 - Springer
Video-based action recognition faces many challenges, such as complex and varied
dynamic motion, spatio-temporal similar action factors, and manual labeling of archived …

Spatio-Temporal Information Fusion and Filtration for Human Action Recognition

M Zhang, X Li, Q Wu - Symmetry, 2023 - mdpi.com
Human action recognition (HAR) as the most representative human-centred computer vision
task is critical in human resource management (HRM), especially in human resource …

Human action recognition based on improved FCN framework

Y Cai, H Yu, X Fan, Y Hou… - 2022 8th International …, 2022 - ieeexplore.ieee.org
Human motion recognition is a highly active area of research. In this paper, we propose a
Spatial Transformer Fully Convolutional Network (STFCN) for human action recognition …