Human activity recognition using multi-features and multiple kernel learning

By Salah Althloothi, Mohammad H. Mahoor, Xiao Zhang, Richard M. Voyles. 2014

143 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Multimodal Multipart Learning for Action Recognition in Depth Videos (2015, neutral): “This way (8) will be expanded to:”
Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition with Convolutional Neural Networks (2017, background): “…from depth data captured by commodity depth sensors (e.g., Microsoft Kinect TM ) in 2010, many methods [76, 65, 78, 22, 13, 42, 71, 6, 77, 1, 57, 41, 67, 68, 72, 28, 33, 20, 11, 79, 74, 37, 40, 46, 85, 8, 47] for action recognition have been proposed based on depth, RGB or skeleton data.”
A Comprehensive Survey of Vision-Based Human Action Recognition Methods (2019, methodology): “[78] calculated a spherical harmonics representation of depth information in the frequency domain, and fused this with position information of the skeleton joints through a multikernel learning method to model human actions.”
Accurate 3D action recognition using learning on the Grassmann manifold (2015, methodology): “Althloothi et al. [46] represent 3D shape features based on spherical harmonics repre-253 sentation and 3D motion features using kinematic structure from skeleton.”
Human Action Recognition From Various Data Modalities: A Review (2020, methodology): “In the work of [376], shape features extracted via spherical harmonics representations and motion information of the 3D joint positions were fused by Multiple Kernel Learning (MKL), which is a model-based fusion strategy.”
A Human Activity Recognition System Using Skeleton Data from RGBD Sensors (2016, methodology): “Althloothi et al. [16] proposed a method where the data are fused at the kernel level, instead of the feature level, using the Multiple Kernel Learning (MKL) technique.”
Action Recognition From Depth Maps Using Deep Convolutional Neural Networks (2016, methodology): “[22] presented two sets of features: features for shape representation extracted from depth data by using a spherical harmonics representation and features for kinematic structure extracted from skeleton data.”
A discussion on the validation tests employed to compare human action recognition methods using the MSR Action3D dataset (2014, methodology): “ure recognition from depth images using motion and shape features, Qin et al. [43] 2013 81 79 82 80.66 - Human activity recognition using multifeatures and multiple kernel learning, Althloothi et al. [44] 2014 74.3 76.8 86.7 79.27 - View invariant human action recognition using histograms of 3D join”
3D skeleton-based human action classification: A survey (2016, methodology): “The method in [139] focuses on human activity recognition in sequences of RGB-D data.”
Mining Mid-Level Features for Action Recognition Based on Effective Skeleton Representation (2014, methodology): “[19] presented two sets of features, features for shape representation extracted from depth data by using a spherical harmonics representation and features for kinematic structure extracted from skeleton data by estimating 3D joint positions.”