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

The demand for the retrieval of complex scene data in autonomous driving isincreasing, especially as passenger vehicles have been equipped with theability to navigate urban settings, with the imperative to address long-tailscenarios. Meanwhile, under the pre-existing two dimensional image retrievalmethod, some problems may arise with scene retrieval, such as lack of globalfeature representation and subpar text retrieval ability. To address theseissues, we have proposed \textbf{BEV-CLIP}, the first multimodal Bird's-EyeView(BEV) retrieval methodology that utilizes descriptive text as an input toretrieve corresponding scenes. This methodology applies the semantic featureextraction abilities of a large language model (LLM) to facilitate zero-shotretrieval of extensive text descriptions, and incorporates semi-structuredinformation from a knowledge graph to improve the semantic richness and varietyof the language embedding. Our experiments result in 87.66% accuracy onNuScenes dataset in text-to-BEV feature retrieval. The demonstrated cases inour paper support that our retrieval method is also indicated to be effectivein identifying certain long-tail corner scenes.

BEV-CLIP: Multi-modal BEV Retrieval Methodology for Complex Scene in Autonomous Driving