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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Trajectory prediction with uncertainty is a critical and challenging task forautonomous driving. Nowadays, we can easily access sensor data represented inmultiple views. However, cross-view consistency has not been evaluated by theexisting models, which might lead to divergences between the multimodalpredictions from different views. It is not practical and effective when thenetwork does not comprehend the 3D scene, which could cause the downstreammodule in a dilemma. Instead, we predicts multimodal trajectories whilemaintaining cross-view consistency. We presented a cross-view trajectoryprediction method using shared 3D Queries (XVTP3D). We employ a set of 3Dqueries shared across views to generate multi-goals that are cross-viewconsistent. We also proposed a random mask method and coarse-to-finecross-attention to capture robust cross-view features. As far as we know, thisis the first work that introduces the outstanding top-down paradigm in BEVdetection field to a trajectory prediction problem. The results of experimentson two publicly available datasets show that XVTP3D achieved state-of-the-artperformance with consistent cross-view predictions.

XVTP3D: Cross-view Trajectory Prediction Using Shared 3D Queries for Autonomous Driving