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

Predicting crowded intents and trajectories is crucial in varouls real-worldapplications, including service robots and autonomous vehicles. Understandingenvironmental dynamics is challenging, not only due to the complexities ofmodeling pair-wise spatial and temporal interactions but also the diverseinfluence of group-wise interactions. To decode the comprehensive pair-wise andgroup-wise interactions in crowded scenarios, we introduce Hyper-STTN, aHypergraph-based Spatial-Temporal Transformer Network for crowd trajectoryprediction. In Hyper-STTN, crowded group-wise correlations are constructedusing a set of multi-scale hypergraphs with varying group sizes, capturedthrough random-walk robability-based hypergraph spectral convolution.Additionally, a spatial-temporal transformer is adapted to capture pedestrians'pair-wise latent interactions in spatial-temporal dimensions. Theseheterogeneous group-wise and pair-wise are then fused and aligned though amultimodal transformer network. Hyper-STTN outperformes other state-of-the-artbaselines and ablation models on 5 real-world pedestrian motion datasets.

Hyper-STTN: Social Group-aware Spatial-Temporal Transformer Network for Human Trajectory Prediction with Hypergraph Reasoning