Dynamic time warping-based features with class-specific joint importance maps for action recognition using Kinect depth sensor

H Mohammadzade, S Hosseini… - IEEE Sensors …, 2021 - ieeexplore.ieee.org
This paper proposes a novel 3D action recognition technique that uses time-series
information extracted from depth image sequences for use in systems of human daily activity …

A convolutional autoencoder model with weighted multi-scale attention modules for 3D skeleton-based action recognition

F Khezerlou, A Baradarani, MA Balafar - Journal of Visual Communication …, 2023 - Elsevier
The 3D skeleton sequences of action can be recognized based on series of meaningful
movements including changes in the direction and geometry features of the body pose. In …

Human activity discovery with automatic multi-objective particle swarm optimization clustering with gaussian mutation and game theory

P Hadikhani, DTC Lai, WH Ong - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Despite many advances in Human Activity Recognition (HAR), most existing works are
conducted with supervision. Supervised methods rely on labeled training data. However …

Multi-stream CNNs with orientation-magnitude response maps and weighted inception module for human action recognition

F Khezerlou, A Baradarani, MA Balafar… - 2023 3rd International …, 2023 - ieeexplore.ieee.org
In this paper, a multi-stream convolutional neural network (CNN) is proposed, which is
integrated with multi-modal data acquired from a video camera, Kinect and wearable inertial …

Spatio‐temporal attention modules in orientation‐magnitude‐response guided multi‐stream CNNs for human action recognition

F Khezerlou, A Baradarani, MA Balafar… - IET Image …, 2024 - Wiley Online Library
This paper introduces a new descriptor called orientation‐magnitude response maps as a
single 2D image to effectively explore motion patterns. Moreover, boosted multi‐stream CNN …

[PDF][PDF] A comparative study of supervised and unsupervised approaches in human activity analysis based on skeleton data

MA Hossen, PE Abas - … Journal of Computing and Digital Systems, 2023 - researchgate.net
One of the important areas of machine intelligence research today is human activity
recognition (HAR), with the goal of automatically identifying human activities from various …

[HTML][HTML] Flexible multi-objective particle swarm optimization clustering with game theory to address human activity discovery fully unsupervised

P Hadikhani, DTC Lai, WH Ong - Image and Vision Computing, 2024 - Elsevier
Human activity recognition is a crucial field of study, but current approaches often require
ground truth labels, which are not always available. We propose a new method called the …

A dynamic time warping based kernel for 3D action recognition using Kinect depth sensor

M Akyash, H Mohammadzade… - 2020 28th Iranian …, 2020 - ieeexplore.ieee.org
Since the advent of 3D sensors and the introduction of robust algorithms for extracting
position of skeletal joints out of RGB images, 3D action recognition has attracted a lot of …

Investigation of the unsupervised machine learning techniques for human activity discovery

MA Hossen, OW Hong, W Caesarendra - Proceedings of the 2nd …, 2022 - Springer
Human activity recognition has been considered as the main capability of an intelligent
system in understanding of human activities. Human activity recognition focuses on …

Flexible Multi-Objective Particle Swarm Optimization Clustering with Game Theory to Address Human Activity Recognition Fully Unsupervised

P Hadikhani, DTC Lai, WH Ong… - Authorea …, 2023 - techrxiv.org
Most research in human activity recognition is supervised, while non-supervised
approaches are not completely unsupervised. Moreover, These methods cannot be used in …