Abstract Three-dimensional (3D) human pose estimation involves estimating the articulated 3D joint locations of a human body from an image or video. Due to its widespread …
Human skeleton, as a compact representation of human action, has received increasing attention in recent years. Many skeleton-based action recognition methods adopt GCNs to …
One essential problem in skeleton-based action recognition is how to extract discriminative features over all skeleton joints. However, the complexity of the recent State-Of-The-Art …
W Ji, J Li, S Yu, M Zhang, Y Piao… - Proceedings of the …, 2021 - openaccess.thecvf.com
Complex backgrounds and similar appearances between objects and their surroundings are generally recognized as challenging scenarios in Salient Object Detection (SOD). This …
Human activity recognition (HAR) systems attempt to automatically identify and analyze human activities using acquired information from various types of sensors. Although several …
X Shu, B Xu, L Zhang, J Tang - IEEE Transactions on Pattern …, 2022 - ieeexplore.ieee.org
In the semi-supervised skeleton-based action recognition task, obtaining more discriminative information from both labeled and unlabeled data is a challenging problem …
P Pareek, A Thakkar - Artificial Intelligence Review, 2021 - Springer
Abstract Human Action Recognition (HAR) involves human activity monitoring task in different areas of medical, education, entertainment, visual surveillance, video retrieval, as …
One essential problem in skeleton-based action recognition is how to extract discriminative features over all skeleton joints. However, the complexity of the State-Of-The-Art (SOTA) …
Research on depth-based human activity analysis achieved outstanding performance and demonstrated the effectiveness of 3D representation for action recognition. The existing …