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

This paper focuses on the challenging problem of 3D pose estimation of adiverse spectrum of articulated objects from single depth images. A novelstructured prediction approach is considered, where 3D poses are represented asskeletal models that naturally operate on manifolds. Given an input depthimage, the problem of predicting the most proper articulation of underlyingskeletal model is thus formulated as sequentially searching for the optimalskeletal configuration. This is subsequently addressed by convolutional neuralnets trained end-to-end to render sequential prediction of the joint locationsas regressing a set of tangent vectors of the underlying manifolds. Ourapproach is examined on various articulated objects including human hand,mouse, and fish benchmark datasets. Empirically it is shown to deliver highlycompetitive performance with respect to the state-of-the-arts, while operatingin real-time (over 30 FPS).

Learning to Search on Manifolds for 3D Pose Estimation of Articulated Objects