A comparative review of recent kinect-based action recognition algorithms
Video-based human action recognition is currently one of the most active research areas in
computer vision. Various research studies indicate that the performance of action …
computer vision. Various research studies indicate that the performance of action …
Vision-based human action recognition: An overview and real world challenges
Within a large range of applications in computer vision, Human Action Recognition has
become one of the most attractive research fields. Ambiguities in recognizing actions does …
become one of the most attractive research fields. Ambiguities in recognizing actions does …
Learning a deep model for human action recognition from novel viewpoints
Recognizing human actions from unknown and unseen (novel) views is a challenging
problem. We propose a Robust Non-Linear Knowledge Transfer Model (R-NKTM) for human …
problem. We propose a Robust Non-Linear Knowledge Transfer Model (R-NKTM) for human …
3D action recognition from novel viewpoints
We propose a human pose representation model that transfers human poses acquired from
different unknown views to a view-invariant high-level space. The model is a deep …
different unknown views to a view-invariant high-level space. The model is a deep …
Learning action recognition model from depth and skeleton videos
Depth sensors open up possibilities of dealing with the human action recognition problem
by providing 3D human skeleton data and depth images of the scene. Analysis of human …
by providing 3D human skeleton data and depth images of the scene. Analysis of human …
Information fusion for human action recognition via biset/multiset globality locality preserving canonical correlation analysis
In this paper, we study the problem of human action recognition, in which each action is
captured by multiple sensors and represented by multisets. We propose two novel …
captured by multiple sensors and represented by multisets. We propose two novel …
[PDF][PDF] 3D action recognition using multi-temporal depth motion maps and Fisher vector.
This paper presents an effective local spatiotemporal descriptor for action recognition from
depth video sequences. The unique property of our descriptor is that it takes the shape …
depth video sequences. The unique property of our descriptor is that it takes the shape …
Low-rank graph preserving discriminative dictionary learning for image recognition
H Du, L Ma, G Li, S Wang - Knowledge-Based Systems, 2020 - Elsevier
Discriminative dictionary learning plays a key role in sparse representation-based
classification. In this paper, we propose a low-rank graph preserving discriminative …
classification. In this paper, we propose a low-rank graph preserving discriminative …
Multi-temporal depth motion maps-based local binary patterns for 3-D human action recognition
This paper presents a local spatio-temporal descriptor for action recognistion from depth
video sequences, which is capable of distinguishing similar actions as well as co** with …
video sequences, which is capable of distinguishing similar actions as well as co** with …
Action recognition from depth sequences using weighted fusion of 2D and 3D auto-correlation of gradients features
This paper presents a new framework for human action recognition from depth sequences.
An effective depth feature representation is developed based on the fusion of 2D and 3D …
An effective depth feature representation is developed based on the fusion of 2D and 3D …