Human action recognition is an important yet challenging task. This paper presents a low-cost descriptor called 3D histograms of texture (3DHoTs) to extract discriminant features from a sequence of depth maps. 3DHoTs are derived from projecting depth frames onto three orthogonal Cartesian planes, i.e., the frontal, side, and top planes, and thus compactly characterize the salient information of a specific action, on which texture features are calculated to represent the action. Besides this fast feature descriptor, a new multi-class boosting classifier (MBC) is also proposed to efficiently exploit different kinds of features in a unified framework for action classification. Compared with the existing boosting frameworks, we add a new multi-...
We propose a set of features derived from skeleton track-ing of the human body and depth maps for th...
In this paper, we propose to adopt ConvNets to recognize human actions from depth maps on relatively...
We propose an algorithm which combines the discriminative information from depth images as well as f...
Human action recognition is an important yet challenging task. This paper presents a low-cost descri...
Human action recognition is an important yet challenging task. This paper presents a low-cost descri...
In order to efficiently extract and encode 3D information of human action from depth images, we pres...
This paper presents an effective local spatio-temporal descriptor for action recognition from depth ...
This paper proposes a framework for recognizing human actions from depth video sequences by designin...
This paper presents a local spatio-Temporal descriptor for action recognistion from depth video sequ...
We propose a set of features derived from skeleton track-ing of the human body and depth maps for th...
This paper presents a local spatio-temporal descriptor for action recognition from depth video seque...
In recent years, action recognition based on RGB-D data has attracted increasing attention. Differen...
In this paper, we propose an effective method to recognize human actions from sequences of depth map...
With the introduction of cost-effective depth sensors, a tremendous amount of research has been devo...
With the introduction of cost-effective depth sensors, a tremendous amount of research has been devo...
We propose a set of features derived from skeleton track-ing of the human body and depth maps for th...
In this paper, we propose to adopt ConvNets to recognize human actions from depth maps on relatively...
We propose an algorithm which combines the discriminative information from depth images as well as f...
Human action recognition is an important yet challenging task. This paper presents a low-cost descri...
Human action recognition is an important yet challenging task. This paper presents a low-cost descri...
In order to efficiently extract and encode 3D information of human action from depth images, we pres...
This paper presents an effective local spatio-temporal descriptor for action recognition from depth ...
This paper proposes a framework for recognizing human actions from depth video sequences by designin...
This paper presents a local spatio-Temporal descriptor for action recognistion from depth video sequ...
We propose a set of features derived from skeleton track-ing of the human body and depth maps for th...
This paper presents a local spatio-temporal descriptor for action recognition from depth video seque...
In recent years, action recognition based on RGB-D data has attracted increasing attention. Differen...
In this paper, we propose an effective method to recognize human actions from sequences of depth map...
With the introduction of cost-effective depth sensors, a tremendous amount of research has been devo...
With the introduction of cost-effective depth sensors, a tremendous amount of research has been devo...
We propose a set of features derived from skeleton track-ing of the human body and depth maps for th...
In this paper, we propose to adopt ConvNets to recognize human actions from depth maps on relatively...
We propose an algorithm which combines the discriminative information from depth images as well as f...