3D Action Recognition Using Data Visualization And Convolutional Neural Networks
Keywords
3D action recognition; Convolutional neural networks; Data visualization; Skeleton data
Abstract
It remains a challenge to efficiently represent spatial-temporal data for 3D action recognition. To solve this problem, this paper presents a new skeleton-based action representation using data visualization and convolutional neural networks, which contains four main stages. First, skeletons from an action sequence are mapped as a set of five dimensional points, containing three dimensions of location, one dimension of time label and one dimension of joint label. Second, these points are encoded as a series of color images, by visualizing points as RGB pixels. Third, convolutional neural networks are adopted to extract deep features from color images. Finally, action class score is calculated by fusing selected deep features. Extensive experiments on three benchmark datasets show that our method achieves state-of-the-art results.
Publication Date
8-28-2017
Publication Title
Proceedings - IEEE International Conference on Multimedia and Expo
Number of Pages
925-930
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/ICME.2017.8019438
Copyright Status
Unknown
Socpus ID
85030225316 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85030225316
STARS Citation
Liu, Mengyuan; Chen, Chen; and Liu, Hong, "3D Action Recognition Using Data Visualization And Convolutional Neural Networks" (2017). Scopus Export 2015-2019. 7533.
https://stars.library.ucf.edu/scopus2015/7533