An Investigation of Skeleton-Based Optical Flow-Guided Features for 3D Action Recognition Using a Multi-Stream CNN Model

J. Ren, N. H. Reyes, A. L.C. Barczak, C. Scogings, M. Liu

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

11 Citations (Scopus)

Abstract

Deep learning-based techniques have recently been found significantly effective for handling skeleton-based action recognition tasks. It was observed that modeling the spatiotemporal variations is the key to effective skeleton-based action recognition approaches. This work proposes an easy and yet effective method for encoding different geometric relational features into static color texture images. Collectively, we refer to these features as skeletal optical flow-guided features. The temporal variations of different features are converted into the color variations of their corresponding images. Then, a multi-stream CNN model is employed to pick up the discriminating patterns that exist in the converted images for subsequent classification. Experimental results demonstrate that our proposed geometric relational features and framework can achieve competitive performances on both MSR Action 3D and NTU RGB+D datasets.

Original languageEnglish
Title of host publication2018 3rd IEEE International Conference on Image, Vision and Computing, ICIVC 2018
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages199-203
Number of pages5
ISBN (Electronic)9781538649916
DOIs
Publication statusPublished - 15 Oct 2018
Externally publishedYes
Event2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - Chongqing, China
Duration: 27 Jun 201829 Jun 2018
Conference number: 3rd

Publication series

Name2018 3rd IEEE International Conference on Image, Vision and Computing, ICIVC 2018

Conference

Conference2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC)
Abbreviated titleICIVC
Country/TerritoryChina
CityChongqing
Period27/06/1829/06/18

Fingerprint

Dive into the research topics of 'An Investigation of Skeleton-Based Optical Flow-Guided Features for 3D Action Recognition Using a Multi-Stream CNN Model'. Together they form a unique fingerprint.

Cite this