From the past few decades, Human activity recognition (HAR) is one of the vital research areas in computer vision in which much research is ongoing. The researcher's focus is …
Recently, numerous methods have been introduced for three-dimensional (3-D) action recognition using handcrafted feature descriptors coupled traditional classifiers. However …
In this paper, we propose a novel space-time geometric representation of human landmark configurations and derive tools for comparison and classification. We model the temporal …
S Karthick - Journal of Advanced Research in Dynamical and …, 2017 - researchgate.net
Machine Learning play one of the vital role in current technological world. Metric Training or learning is a key problem in machine learning techniques. So far nonlinear metric learning …
Artificial Intelligence (AI) systems are increasingly pervasive: Internet of Things, in-car intelligent devices, robots, and virtual assistants, and their large-scale adoption makes it …
B Chopin, N Otberdout, M Daoudi… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
In this work we propose a novel solution for 3D skeleton-based human motion prediction. The objective of this task consists in forecasting future human poses based on a prior …
Person re-identification is typically performed using 2D still images or videos, where photometric appearance is the main visual cue used to discover the presence of a target …
H Zhang, Y Hou, W Zhang - 2022 IEEE International …, 2022 - ieeexplore.ieee.org
In this paper, we investigate unsupervised representation learning for skeleton action recognition, and develop a simple yet effective framework: SKeletal Twins (SKT), which is …
B Chopin, N Otberdout, M Daoudi… - 2021 16th IEEE …, 2021 - ieeexplore.ieee.org
Human motion prediction aims to forecast future human poses given a prior pose sequence. The discontinuity of the predicted motion and the performance deterioration in long-term …