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

3D visual grounding aims to localize the target object in a 3D point cloud bya free-form language description. Typically, the sentences describing thetarget object tend to provide information about its relative relation betweenother objects and its position within the whole scene. In this work, we proposea relation-aware one-stage framework, named 3D Relative Position-aware Network(3DRP-Net), which can effectively capture the relative spatial relationshipsbetween objects and enhance object attributes. Specifically, 1) we propose a 3DRelative Position Multi-head Attention (3DRP-MA) module to analyze relativerelations from different directions in the context of object pairs, which helpsthe model to focus on the specific object relations mentioned in the sentence.2) We designed a soft-labeling strategy to alleviate the spatial ambiguitycaused by redundant points, which further stabilizes and enhances the learningprocess through a constant and discriminative distribution. Extensiveexperiments conducted on three benchmarks (i.e., ScanRefer and Nr3D/Sr3D)demonstrate that our method outperforms all the state-of-the-art methods ingeneral. The source code will be released on GitHub.

3DRP-Net: 3D Relative Position-aware Network for 3D Visual Grounding