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

In this paper, we propose a novel approach to enhance the 3D body poseestimation of a person computed from videos captured from a single wearablecamera. The key idea is to leverage high-level features linking first- andthird-views in a joint embedding space. To learn such embedding space weintroduce First2Third-Pose, a new paired synchronized dataset of nearly 2,000videos depicting human activities captured from both first- and third-viewperspectives. We explicitly consider spatial- and motion-domain features,combined using a semi-Siamese architecture trained in a self-supervisedfashion. Experimental results demonstrate that the joint multi-view embeddedspace learned with our dataset is useful to extract discriminatory featuresfrom arbitrary single-view egocentric videos, without needing domain adaptationnor knowledge of camera parameters. We achieve significant improvement ofegocentric 3D body pose estimation performance on two unconstrained datasets,over three supervised state-of-the-art approaches. Our dataset and code will beavailable for research purposes.

Enhancing Egocentric 3D Pose Estimation with Third Person Views