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

In this work, we explore the correlation between people trajectories andtheir head orientations. We argue that people trajectory and head poseforecasting can be modelled as a joint problem. Recent approaches on trajectoryforecasting leverage short-term trajectories (aka tracklets) of pedestrians topredict their future paths. In addition, sociological cues, such as expecteddestination or pedestrian interaction, are often combined with tracklets. Inthis paper, we propose MiXing-LSTM (MX-LSTM) to capture the interplay betweenpositions and head orientations (vislets) thanks to a joint unconstrainedoptimization of full covariance matrices during the LSTM backpropagation. Weadditionally exploit the head orientations as a proxy for the visual attention,when modeling social interactions. MX-LSTM predicts future pedestrians locationand head pose, increasing the standard capabilities of the current approacheson long-term trajectory forecasting. Compared to the state-of-the-art, ourapproach shows better performances on an extensive set of public benchmarks.MX-LSTM is particularly effective when people move slowly, i.e. the mostchallenging scenario for all other models. The proposed approach also allowsfor accurate predictions on a longer time horizon.

Forecasting People Trajectories and Head Poses by Jointly Reasoning on Tracklets and Vislets