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

Convolutional neural nets (CNN) are the leading computer vision method forclassifying images. In some cases, it is desirable to classify only a specificregion of the image that corresponds to a certain object. Hence, assuming thatthe region of the object in the image is known in advance and is given as abinary region of interest (ROI) mask, the goal is to classify the object inthis region using a convolutional neural net. This goal is achieved using astandard image classification net with the addition of a side branch, whichconverts the ROI mask into an attention map. This map is then combined with theimage classification net. This allows the net to focus the attention on theobject region while still extracting contextual cues from the background. Thisapproach was evaluated using the COCO object dataset and the OpenSurfacesmaterials dataset. In both cases, it gave superior results to methods thatcompletely ignore the background region. In addition, it was found thatcombining the attention map at the first layer of the net gave better resultsthan combining it at higher layers of the net. The advantages of this methodare most apparent in the classification of small regions which demands a greatdeal of contextual information from the background.

Classifying a specific image region using convolutional nets with an ROI mask as input