University Of Tasmania

File(s) under permanent embargo

Hierarchical topic modeling with Pose-transition feature for action recognition using 3D skeleton data

journal contribution
posted on 2023-05-22, 05:44 authored by Huynh-The, T, Hua, C-H, Tu, NA, Hur, T, Bang, J, Kim, D, Muhammad Bilal AminMuhammad Bilal Amin, Byeong KangByeong Kang, Seung, H, Shin, S-Y, Kim, E-S, Lee, S
Despite impressive achievements in image processing and artificial intelligence in the past decade, understanding video-based action remains a challenge. However, the intensive development of 3D computer vision in recent years has brought more potential research opportunities in pose-based action detection and recognition. Thanks to the advantages of depth camera devices like the Microsoft Kinect sensor, we developed an effective approach to in-depth analysis of indoor actions using skeleton information, in which skeleton-based feature extraction and topic model-based learning are two major contributions. Geometric features, i.e. joint distance, joint angle, and joint-plane distance are calculated in the spatio-temporal dimension. These features are merged into two types, called pose and transition features, and then are provided to codebook construction to convert sparse features into visual words by k-means clustering. An efficient hierarchical model is developed to describe the full correlation of feature - poselet - action based on Pachinko Allocation Model. This model has the potential to uncover more hidden poselets, which have been recognized as the valuable information and help to differentiate pose-sharing actions. The experimental results on several well-known datasets, such as MSR Action 3D, MSR Daily Activity 3D, Florence 3D Action, UTKinect-Action 3D, and NTU RGB+D Action Recognition, demonstrate the high recognition accuracy of the proposed method. Our method outperforms state-of-the-art methods in the field in most dataset benchmarks.


Ministry of Trade, Industry and Energy


Publication title

Information Sciences








School of Information and Communication Technology


Elsevier Science Inc

Place of publication

360 Park Ave South, New York, USA, Ny, 10010-1710

Repository Status

  • Restricted

Socio-economic Objectives

Information systems, technologies and services not elsewhere classified