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 to predict histograms of object sizes in crowded scenes directlywithout any explicit object instance segmentation. What makes this taskchallenging is the high density of objects (of the same category), which makesinstance identification hard. Instead of explicitly segmenting objectinstances, we show that directly learning histograms of object sizes improvesaccuracy while using drastically less parameters. This is very useful forapplication scenarios where explicit, pixel-accurate instance segmentation isnot needed, but there lies interest in the overall distribution of instancesizes. Our core applications are in biology, where we estimate the sizedistribution of soldier fly larvae, and medicine, where we estimate the sizedistribution of cancer cells as an intermediate step to calculate the tumorcellularity score. Given an image with hundreds of small object instances, weoutput the total count and the size histogram. We also provide a new data setfor this task, the FlyLarvae data set, which consists of 11,000 larvaeinstances labeled pixel-wise. Our method results in an overall improvement inthe count and size distribution prediction as compared to state-of-the-artinstance segmentation method Mask R-CNN.

HistoNet: Predicting size histograms of object instances