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

Representation learning of pedestrian trajectories transforms variable-lengthtimestamp-coordinate tuples of a trajectory into a fixed-length vectorrepresentation that summarizes spatiotemporal characteristics. It is a crucialtechnique to connect feature-based data mining with trajectory data. Trajectoryrepresentation is a challenging problem, because both environmental constraints(e.g., wall partitions) and temporal user dynamics should be meticulouslyconsidered and accounted for. Furthermore, traditional sequence-to-sequenceautoencoders using maximum log-likelihood often require dataset covering allthe possible spatiotemporal characteristics to perform well. This is infeasibleor impractical in reality. We propose TREP, a practical pedestrian trajectoryrepresentation learning algorithm which captures the environmental constraintsand the pedestrian dynamics without the need of any training dataset. Byformulating a sequence-to-sequence autoencoder with a spatial-aware objectivefunction under the paradigm of actor-critic reinforcement learning, TREPintelligently encodes spatiotemporal characteristics of trajectories with thecapability of handling diverse trajectory patterns. Extensive experiments onboth synthetic and real datasets validate the high fidelity of TREP torepresent trajectories.

Representation Learning of Pedestrian Trajectories Using Actor-Critic Sequence-to-Sequence Autoencoder