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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Advancements in convolutional neural networks (CNNs) have made significantstrides toward achieving high performance levels on multiple object recognitiontasks. While some approaches utilize information from the entire scene topropose regions of interest, the task of interpreting a particular region orobject is still performed independently of other objects and features in theimage. Here we demonstrate that a scene's 'gist' can significantly contributeto how well humans can recognize objects. These findings are consistent withthe notion that humans foveate on an object and incorporate information fromthe periphery to aid in recognition. We use a biologically inspired two-partconvolutional neural network ('GistNet') that models the fovea and periphery toprovide a proof-of-principle demonstration that computational objectrecognition can significantly benefit from the gist of the scene as contextualinformation. Our model yields accuracy improvements of up to 50% in certainobject categories when incorporating contextual gist, while only increasing theoriginal model size by 5%. This proposed model mirrors our intuition about howthe human visual system recognizes objects, suggesting specific biologicallyplausible constraints to improve machine vision and building initial stepstowards the challenge of scene understanding.

Learning Scene Gist with Convolutional Neural Networks to Improve Object Recognition