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

Nowadays, our mobility systems are evolving into the era of intelligentvehicles that aim to improve road safety. Due to their vulnerability,pedestrians are the users who will benefit the most from these developments.However, predicting their trajectory is one of the most challenging concerns.Indeed, accurate prediction requires a good understanding of multi-agentinteractions that can be complex. Learning the underlying spatial and temporalpatterns caused by these interactions is even more of a competitive and openproblem that many researchers are tackling. In this paper, we introduce a modelcalled PRediction Transformer (PReTR) that extracts features from themulti-agent scenes by employing a factorized spatio-temporal attention module.It shows less computational needs than previously studied models withempirically better results. Besides, previous works in motion prediction sufferfrom the exposure bias problem caused by generating future sequencesconditioned on model prediction samples rather than ground-truth samples. Inorder to go beyond the proposed solutions, we leverage encoder-decoderTransformer networks for parallel decoding a set of learned object queries.This non-autoregressive solution avoids the need for iterative conditioning andarguably decreases training and testing computational time. We evaluate ourmodel on the ETH/UCY datasets, a publicly available benchmark for pedestriantrajectory prediction. Finally, we justify our usage of the parallel decodingtechnique by showing that the trajectory prediction task can be better solvedas a non-autoregressive task.

PreTR: Spatio-Temporal Non-Autoregressive Trajectory Prediction Transformer