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

This paper addresses the problem of 3D referring expression comprehension(REC) in autonomous driving scenario, which aims to ground a natural languageto the targeted region in LiDAR point clouds. Previous approaches for RECusually focus on the 2D or 3D-indoor domain, which is not suitable foraccurately predicting the location of the queried 3D region in an autonomousdriving scene. In addition, the upper-bound limitation and the heavycomputation cost motivate us to explore a better solution. In this work, wepropose a new multi-modal visual grounding task, termed LiDAR Grounding. Thenwe devise a Multi-modal Single Shot Grounding (MSSG) approach with an effectivetoken fusion strategy. It jointly learns the LiDAR-based object detector withthe language features and predicts the targeted region directly from thedetector without any post-processing. Moreover, the image feature can beflexibly integrated into our approach to provide rich texture and colorinformation. The cross-modal learning enforces the detector to concentrate onimportant regions in the point cloud by considering the informative languageexpressions, thus leading to much better accuracy and efficiency. Extensiveexperiments on the Talk2Car dataset demonstrate the effectiveness of theproposed methods. Our work offers a deeper insight into the LiDAR-basedgrounding task and we expect it presents a promising direction for theautonomous driving community.

Language-Guided 3D Object Detection in Point Cloud for Autonomous Driving