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

Crowd counting problem that counts the number of people in an image has beenextensively studied in recent years. In this paper, we introduce a new variantof crowd counting problem, namely "Categorized Crowd Counting", that counts thenumber of people sitting and standing in a given image. Categorized crowdcounting has many real-world applications such as crowd monitoring, customerservice, and resource management. The major challenges in categorized crowdcounting come from high occlusion, perspective distortion and the seeminglyidentical upper body posture of sitting and standing persons. Existing densitymap based approaches perform well to approximate a large crowd, but loseimportant local information necessary for categorization. On the other hand,traditional detection-based approaches perform poorly in occluded environments,especially when the crowd size gets bigger. Hence, to solve the categorizedcrowd counting problem, we develop a novel attention-based deep learningframework that addresses the above limitations. In particular, our approachworks in three phases: i) We first generate basic detection based sitting andstanding density maps to capture the local information; ii) Then, we generate acrowd counting based density map as global counting feature; iii) Finally, wehave a cross-branch segregating refinement phase that splits the crowd densitymap into final sitting and standing density maps using attention mechanism.Extensive experiments show the efficacy of our approach in solving thecategorized crowd counting problem.

CCCNet: An Attention Based Deep Learning Framework for Categorized Crowd Counting