A novel two-level interactive action recognition model based on inertial data fusion
Currently, the majority of solutions for human interactive action recognition typically rely on
machine vision methods, thus leading to limited application scenarios for accurate …
machine vision methods, thus leading to limited application scenarios for accurate …
Toward Realistic 3D Human Motion Prediction With a Spatio-Temporal Cross-Transformer Approach
Human motion prediction intends to predict how humans move given a historical sequence
of 3D human motions. Recent transformer-based methods have attracted increasing …
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
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 …
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 …
convolutional neural networks (CNNs) has proven to be effective. However, among existing …
DivDiff: A Conditional Diffusion Model for Diverse Human Motion Prediction
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 …
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
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 …
enhancing and fusing diverse skeleton features from distinct levels. Graph convolutional …
Towards Efficient and Diverse Generative Model for Unconditional Human Motion Synthesis
Recent generative methods have revolutionized the way of human motion synthesis, such
as Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), and …
as Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), and …
Unsupervised video-based action recognition using two-stream generative adversarial network
Video-based action recognition faces many challenges, such as complex and varied
dynamic motion, spatio-temporal similar action factors, and manual labeling of archived …
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 …
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 …
Spatial Transformer Fully Convolutional Network (STFCN) for human action recognition …