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

This work studies the problem of predicting the sequence of future actionsfor surround vehicles in real-world driving scenarios. To this aim, we makethree main contributions. The first contribution is an automatic method toconvert the trajectories recorded in real-world driving scenarios to actionsequences with the help of HD maps. The method enables automatic datasetcreation for this task from large-scale driving data. Our second contributionlies in applying the method to the well-known traffic agent tracking andprediction dataset Argoverse, resulting in 228,000 action sequences.Additionally, 2,245 action sequences were manually annotated for testing. Thethird contribution is to propose a novel action sequence prediction method byintegrating past positions and velocities of the traffic agents, mapinformation and social context into a single end-to-end trainable neuralnetwork. Our experiments prove the merit of the data creation method and thevalue of the created dataset - prediction performance improves consistentlywith the size of the dataset and shows that our action prediction methodoutperforms comparing models.

Action Sequence Predictions of Vehicles in Urban Environments using Map and Social Context