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

We propose AffordanceNet, a new deep learning approach to simultaneouslydetect multiple objects and their affordances from RGB images. OurAffordanceNet has two branches: an object detection branch to localize andclassify the object, and an affordance detection branch to assign each pixel inthe object to its most probable affordance label. The proposed frameworkemploys three key components for effectively handling the multiclass problem inthe affordance mask: a sequence of deconvolutional layers, a robust resizingstrategy, and a multi-task loss function. The experimental results on thepublic datasets show that our AffordanceNet outperforms recent state-of-the-artmethods by a fair margin, while its end-to-end architecture allows theinference at the speed of 150ms per image. This makes our AffordanceNet wellsuitable for real-time robotic applications. Furthermore, we demonstrate theeffectiveness of AffordanceNet in different testing environments and in realrobotic applications. The source code is available athttps://github.com/nqanh/affordance-net

AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection