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

Pedestrian trajectory prediction is a prominent research track that hasadvanced towards modelling of crowd social and contextual interactions, withextensive usage of Long Short-Term Memory (LSTM) for temporal representation ofwalking trajectories.  Existing approaches use virtual neighborhoods as a fixed grid for poolingsocial states of pedestrians with tuning process that controls how socialinteractions are being captured. This entails performance customization tospecific scenes but lowers the generalization capability of the approaches. Inour work, we deploy \textit{Grid-LSTM}, a recent extension of LSTM, whichoperates over multidimensional feature inputs. We present a new perspective tointeraction modeling by proposing that pedestrian neighborhoods can becomeadaptive in design. We use \textit{Grid-LSTM} as an encoder to learn aboutpotential future neighborhoods and their influence on pedestrian motion giventhe visual and the spatial boundaries. Our model outperforms state-of-the-artapproaches that collate resembling features over several publicly-testedsurveillance videos. The experiment results clearly illustrate thegeneralization of our approach across datasets that varies in scene featuresand crowd dynamics.

Graph2Kernel Grid-LSTM: A Multi-Cued Model for Pedestrian Trajectory Prediction by Learning Adaptive Neighborhoods