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 recent years, a deep learning framework has been widely used for objectpose estimation. While quaternion is a common choice for rotationrepresentation of 6D pose, it cannot represent an uncertainty of theobservation. In order to handle the uncertainty, Bingham distribution is onepromising solution because this has suitable features, such as a smoothrepresentation over SO(3), in addition to the ambiguity representation.However, it requires the complex computation of the normalizing constants. Thisis the bottleneck of loss computation in training neural networks based onBingham representation. As such, we propose a fast-computable andeasy-to-implement loss function for Bingham distribution. We also show not onlyto examine the parametrization of Bingham distribution but also an applicationbased on our loss function.

Probabilistic Rotation Representation With an Efficiently Computable Bingham Loss Function and Its Application to Pose Estimation