English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

The computer vision community is currently focusing on solving actionrecognition problems in real videos, which contain thousands of samples withmany challenges. In this process, Deep Convolutional Neural Networks (D-CNNs)have played a significant role in advancing the state-of-the-art in variousvision-based action recognition systems. Recently, the introduction of residualconnections in conjunction with a more traditional CNN model in a singlearchitecture called Residual Network (ResNet) has shown impressive performanceand great potential for image recognition tasks. In this paper, we investigateand apply deep ResNets for human action recognition using skeletal dataprovided by depth sensors. Firstly, the 3D coordinates of the human body jointscarried in skeleton sequences are transformed into image-based representationsand stored as RGB images. These color images are able to capture thespatial-temporal evolutions of 3D motions from skeleton sequences and can beefficiently learned by D-CNNs. We then propose a novel deep learningarchitecture based on ResNets to learn features from obtained color-basedrepresentations and classify them into action classes. The proposed method isevaluated on three challenging benchmark datasets including MSR Action 3D,KARD, and NTU-RGB+D datasets. Experimental results demonstrate that our methodachieves state-of-the-art performance for all these benchmarks whilst requiringless computation resource. In particular, the proposed method surpassesprevious approaches by a significant margin of 3.4% on MSR Action 3D dataset,0.67% on KARD dataset, and 2.5% on NTU-RGB+D dataset.

Exploiting deep residual networks for human action recognition from skeletal data