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 Plus annual

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

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Human action recognition is a challenging problem, particularly when there ishigh variability in factors such as subject appearance, backgrounds andviewpoint. While deep neural networks (DNNs) have been shown to perform well onaction recognition tasks, they typically require large amounts of high-qualitylabeled data to achieve robust performance across a variety of conditions.Synthetic data has shown promise as a way to avoid the substantial costs andpotential ethical concerns associated with collecting and labeling enormousamounts of data in the real-world. However, synthetic data may differ from realdata in important ways. This phenomenon, known as \textit{domain shift}, canlimit the utility of synthetic data in robotics applications. To mitigate theeffects of domain shift, substantial effort is being dedicated to thedevelopment of domain adaptation (DA) techniques. Yet, much remains to beunderstood about how best to develop these techniques. In this paper, weintroduce a new dataset called Robot Control Gestures (RoCoG-v2). The datasetis composed of both real and synthetic videos from seven gesture classes, andis intended to support the study of synthetic-to-real domain shift forvideo-based action recognition. Our work expands upon existing datasets byfocusing the action classes on gestures for human-robot teaming, as well as byenabling investigation of domain shift in both ground and aerial views. Wepresent baseline results using state-of-the-art action recognition and domainadaptation algorithms and offer initial insight on tackling thesynthetic-to-real and ground-to-air domain shifts.

Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances