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

We present a novel task for cross-dataset visual grounding in 3D scenes(Cross3DVG), which overcomes limitations of existing 3D visual groundingmodels, specifically their restricted 3D resources and consequent tendencies ofoverfitting a specific 3D dataset. We created RIORefer, a large-scale 3D visualgrounding dataset, to facilitate Cross3DVG. It includes more than 63k diversedescriptions of 3D objects within 1,380 indoor RGB-D scans from 3RScan, withhuman annotations. After training the Cross3DVG model using the source 3Dvisual grounding dataset, we evaluate it without target labels using the targetdataset with, e.g., different sensors, 3D reconstruction methods, and languageannotators. Comprehensive experiments are conducted using established visualgrounding models and with CLIP-based multi-view 2D and 3D integration designedto bridge gaps among 3D datasets. For Cross3DVG tasks, (i) cross-dataset 3Dvisual grounding exhibits significantly worse performance than learning andevaluation with a single dataset because of the 3D data and language variantsacross datasets. Moreover, (ii) better object detector and localization modulesand fusing 3D data and multi-view CLIP-based image features can alleviate thislower performance. Our Cross3DVG task can provide a benchmark for developingrobust 3D visual grounding models to handle diverse 3D scenes while leveragingdeep language understanding.

Cross3DVG: Cross-Dataset 3D Visual Grounding on Different RGB-D Scans