Learning features combination for human action recognition from skeleton sequences
Human action recognition is a challenging task due to the complexity of human movements
and to the variety among the same actions performed by distinct subjects. Recent …
and to the variety among the same actions performed by distinct subjects. Recent …
A discussion on the validation tests employed to compare human action recognition methods using the msr action3d dataset
This paper aims to determine which is the best human action recognition method based on
features extracted from RGB-D devices, such as the Microsoft Kinect. A review of all the …
features extracted from RGB-D devices, such as the Microsoft Kinect. A review of all the …
MDSC-Net: Multi-modal Discriminative Sparse Coding Driven RGB-D Classification Network
In this paper, we propose a novel sparsity-driven deep neural network to solve the RGB-D
image classification problem. Different from existing classification networks, our network …
image classification problem. Different from existing classification networks, our network …
Human action recognition in videos using stable features
Human action recognition is still a challenging problem and researchers are focusing to
investigate this problem using different techniques. We propose a robust approach for …
investigate this problem using different techniques. We propose a robust approach for …
Elliptical density shape model for hand gesture recognition
Recently, the Microsoft Kinect sensor has provided the whole new type of data in computer
vision, the depth information. The most important contribution of depth information is to …
vision, the depth information. The most important contribution of depth information is to …
Abnormal activity detection based on dense spatial-temporal features and improved one-class learning
TN Nguyen, NQ Ly - Proceedings of the 8th International Symposium on …, 2017 - dl.acm.org
Abnormal activity detection is an important issue in video surveillance. The abnormal activity
could be a predictable activity or unpredictable activity. This paper focuses on unpredictable …
could be a predictable activity or unpredictable activity. This paper focuses on unpredictable …
Machine Learning for Human Action Recognition and Pose Estimation based on 3D Information
D Luvizon - 2019 - theses.hal.science
3D human action recognition is a challenging task due to the complexity of human
movements and to the variety on poses and actions performed by distinct subjects. Recent …
movements and to the variety on poses and actions performed by distinct subjects. Recent …
[PDF][PDF] A robust approach for action recognition based on spatio-temporal features in RGB-D sequences
Recognizing human action is attractive research topic in computer vision since it plays an
important role on the applications such as human-computer interaction, intelligent …
important role on the applications such as human-computer interaction, intelligent …
Modality Representation Learning for Geometry Feature of Skeleton Based Human Action
S Qiu, H Liu, H Tong - 2021 IEEE International Conference on …, 2021 - ieeexplore.ieee.org
Existing skeleton-based human action recognition has achieved enormous progress thanks
to the accessible 3D skeleton capturing device and deep learning methods. One of the …
to the accessible 3D skeleton capturing device and deep learning methods. One of the …
[PDF][PDF] A discussion on the validation tests employed to compare human action recognition methods using the MSR Action3D dataset
This paper aims to determine which is the best human action recognition method based on
features extracted from RGB-D devices, such as the Microsoft Kinect. A review of all the …
features extracted from RGB-D devices, such as the Microsoft Kinect. A review of all the …