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 segmentation is a fundamental task serving as the basis of crowdedscene analysis, and it is highly desirable to obtain refined pixel-levelsegmentation maps. However, it remains a challenging problem, as existingapproaches either require dense pixel-level annotations to train deep learningmodels or merely produce rough segmentation maps from optical or particle flowswith physical models. In this paper, we propose the Motion Prior-Aware SiameseNetwork (MPASNET) for unsupervised crowd semantic segmentation. This model notonly eliminates the need for annotation but also yields high-qualitysegmentation maps. Specially, we first analyze the coherent motion patternsacross the frames and then apply a circular region merging strategy on thecollective particles to generate pseudo-labels. Moreover, we equip MPASNET withsiamese branches for augmentation-invariant regularization and siamese featureaggregation. Experiments over benchmark datasets indicate that our modeloutperforms the state-of-the-arts by more than 12% in terms of mIoU.

MPASNET: Motion Prior-Aware Siamese Network for Unsupervised Deep Crowd Segmentation in Video Scenes