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/

Global: Zendy Tools annual

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

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Traditional action recognition models are constructed around the paradigm of2D perspective imagery. Though sophisticated time-series models have pushed thefield forward, much of the information is still not exploited by confining thedomain to 2D. In this work, we introduce a novel representation of motion as avoxelized 3D vector field and demonstrate how it can be used to improveperformance of action recognition networks. This volumetric representation is anatural fit for 3D CNNs, and allows out-of-plane data augmentation techniquesduring training of these networks. Both the construction of this representationfrom RGB-D video and inference can be run in real time. We demonstrate superiorresults using this representation with our network design on the open-sourceNTU RGB+D dataset where it outperforms state-of-the-art on both of the definedevaluation metrics. Furthermore, we experimentally show how the out-of-planeaugmentation techniques create viewpoint invariance and allow the model trainedusing this representation to generalize to unseen camera angles. Code isavailable here: https://github.com/mpeven/ntu_rgb.

Action Recognition Using Volumetric Motion Representations