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

Recent works attempt to extend Graph Convolution Networks (GCNs) to pointclouds for classification and segmentation tasks. These works tend to sampleand group points to create smaller point sets locally and mainly focus onextracting local features through GCNs, while ignoring the relationship betweenpoint sets. In this paper, we propose the Dynamic Hop Graph Convolution Network(DHGCN) for explicitly learning the contextual relationships between thevoxelized point parts, which are treated as graph nodes. Motivated by theintuition that the contextual information between point parts lies in thepairwise adjacent relationship, which can be depicted by the hop distance ofthe graph quantitatively, we devise a novel self-supervised part-level hopdistance reconstruction task and design a novel loss function accordingly tofacilitate training. In addition, we propose the Hop Graph Attention (HGA),which takes the learned hop distance as input for producing attention weightsto allow edge features to contribute distinctively in aggregation. Eventually,the proposed DHGCN is a plug-and-play module that is compatible withpoint-based backbone networks. Comprehensive experiments on different backbonesand tasks demonstrate that our self-supervised method achieves state-of-the-artperformance. Our source code is available at: https://github.com/Jinec98/DHGCN.

DHGCN: Dynamic Hop Graph Convolution Network for Self-Supervised Point Cloud Learning