Spatio-Temporal Proximity Distribution Kernels for Action Recognition
نویسندگان
چکیده
Spatio-temporal local feature based bag of visual words algorithm (BOVW) has shown promising results in complex human action classification. However, one key disadvantage of BOVW is geometrical unconstraint, which makes it impossible to recognize different actions with the same features but different spatial-temporal distribution of these features. In this paper, we exploit the spatio-temporal proximity distribution of local features in 3D space to characterize geometric context of action class. The obtained spatio-temporal proximity matrix models both the appearance and geometrics of human actions. Moreover, a spatio-temporal proximity distribution kernel (ST-PDK) is proposed to measure the similarity of videos, which satisfies Mercer condition and is directly incorporated into the kernel function of the SVM classifier. Our algorithm achieves the highest classification accuracy on KTH dataset, one of the most challenging and popular action datasets.
منابع مشابه
A New Class of Spatial Covariance Functions Generated by Higher-order Kernels
Covariance functions and variograms play a fundamental role in exploratory analysis and statistical modelling of spatial and spatio-temporal datasets. In this paper, we construct a new class of spatial covariance functions using the Fourier transform of some higher-order kernels. Moreover, we extend this class of spatial covariance functions to the spatio-temporal setting using the idea used in...
متن کاملTensor Representations via Kernel Linearization for Action Recognition from 3D Skeletons (Extended Version)
In this paper, we explore tensor representations that can compactly capture higherorder relationships between skeleton joints for 3D action recognition. We first define RBF kernels on 3D joint sequences, which are then linearized to form kernel descriptors. The higher-order outer-products of these kernel descriptors form our tensor representations. We present two different kernels for action re...
متن کاملAction Recognition Using Local Spatio- Temporal Oriented Energy Features and Additive Kernel SVMs
Spatio-temporal oriented energy features have been proved to be an efficient feature for action recognition. It has satisfied performance on most of public databases. However, the oriented energy features were used as holistic action features for template matching in many literatures. In the paper, we proposed an action representation based on local spatio-temporal oriented energy features, and...
متن کاملAction recognition via spatio-temporal local features: A comprehensive study
Local methods based on spatio-temporal interest points (STIPs) have shown their effectiveness for human action recognition. The bag-of-words (BoW) model has been widely used and dominated in this field. Recently, a large number of techniques based on local features including improved variants of the BoW model, sparse coding (SC), Fisher kernels (FK), vector of locally aggregated descriptors (VL...
متن کاملSkepxels: Spatio-temporal Image Representation of Human Skeleton Joints for Action Recognition
Human skeleton joints are popular for action analysis since they can be easily extracted from videos to discard background noises. However, current skeleton representations do not fully benefit from machine learning with CNNs. We propose “Skepxels” a spatio-temporal representation for skeleton sequences to fully exploit the “local” correlations between joints using the 2D convolution kernels of...
متن کامل