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

Compared with single image based crowd counting, video provides thespatial-temporal information of the crowd that would help improve therobustness of crowd counting. But translation, rotation and scaling of peoplelead to the change of density map of heads between neighbouring frames.Meanwhile, people walking in/out or being occluded in dynamic scenes leads tothe change of head counts. To alleviate these issues in video crowd counting, aLocality-constrained Spatial Transformer Network (LSTN) is proposed.Specifically, we first leverage a Convolutional Neural Networks to estimate thedensity map for each frame. Then to relate the density maps betweenneighbouring frames, a Locality-constrained Spatial Transformer (LST) module isintroduced to estimate the density map of next frame with that of currentframe. To facilitate the performance evaluation, a large-scale video crowdcounting dataset is collected, which contains 15K frames with about 394Kannotated heads captured from 13 different scenes. As far as we know, it is thelargest video crowd counting dataset. Extensive experiments on our dataset andother crowd counting datasets validate the effectiveness of our LSTN for crowdcounting.

Locality-constrained Spatial Transformer Network for Video Crowd Counting