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

Compared with the visual grounding on 2D images, the natural-language-guided3D object localization on point clouds is more challenging. In this paper, wepropose a new model, named InstanceRefer, to achieve a superior 3D visualgrounding through the grounding-by-matching strategy. In practice, our modelfirst predicts the target category from the language descriptions using asimple language classification model. Then, based on the category, our modelsifts out a small number of instance candidates (usually less than 20) from thepanoptic segmentation of point clouds. Thus, the non-trivial 3D visualgrounding task has been effectively re-formulated as a simplifiedinstance-matching problem, considering that instance-level candidates are morerational than the redundant 3D object proposals. Subsequently, for eachcandidate, we perform the multi-level contextual inference, i.e., referringfrom instance attribute perception, instance-to-instance relation perception,and instance-to-background global localization perception, respectively.Eventually, the most relevant candidate is selected and localized by rankingconfidence scores, which are obtained by the cooperative holisticvisual-language feature matching. Experiments confirm that our methodoutperforms previous state-of-the-arts on ScanRefer online benchmark andNr3D/Sr3D datasets.

InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring