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

Crowd image is arguably one of the most laborious data to annotate. In thispaper, we devote to reduce the massive demand of densely labeled crowd data,and propose a novel weakly-supervised setting, in which we leverage the binaryranking of two images with high-contrast crowd counts as training guidance. Toenable training under this new setting, we convert the crowd count regressionproblem to a ranking potential prediction problem. In particular, we tailor aSiamese Ranking Network that predicts the potential scores of two imagesindicating the ordering of the counts. Hence, the ultimate goal is to assignappropriate potentials for all the crowd images to ensure their orderings obeythe ranking labels. On the other hand, potentials reveal the relative crowdsizes but cannot yield an exact crowd count. We resolve this problem byintroducing "anchors" during the inference stage. Concretely, anchors are a fewimages with count labels used for referencing the corresponding counts frompotential scores by a simple linear mapping function. We conduct extensiveexperiments to study various combinations of supervision, and we show that theproposed method outperforms existing weakly-supervised methods withoutadditional labeling effort by a large margin.

Glance to Count: Learning to Rank with Anchors for Weakly-supervised Crowd Counting