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 develops and evaluates a novel method that allows for thedetection of affordances in a scalable and multiple-instance manner on visuallyrecovered pointclouds. Our approach has many advantages over alternativemethods, as it is based on highly parallelizable, one-shot learning that isfast in commodity hardware. The approach is hybrid in that it uses a geometricrepresentation together with a state-of-the-art deep learning method capable ofidentifying 3D scene saliency. The geometric component allows for a compact andefficient representation, boosting the performance of the deep networkarchitecture which proved insufficient on its own. Moreover, our approachallows not only to predict whether an input scene affords or not theinteractions, but also the pose of the objects that allow these interactions totake place. Our predictions align well with crowd-sourced human judgment asthey are preferred with 87% probability, show high rates of improvement withalmost four times (4x) better performance over a deep learning-only baselineand are seven times (7x) faster than previous art.

What can I do here? Leveraging Deep 3D saliency and geometry for fast and scalable multiple affordance detection