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

Exploiting fine-grained semantic features on point cloud is still challengingdue to its irregular and sparse structure in a non-Euclidean space. Amongexisting studies, PointNet provides an efficient and promising approach tolearn shape features directly on unordered 3D point cloud and has achievedcompetitive performance. However, local feature that is helpful towards bettercontextual learning is not considered. Meanwhile, attention mechanism showsefficiency in capturing node representation on graph-based data by attendingover neighboring nodes. In this paper, we propose a novel neural network forpoint cloud, dubbed GAPNet, to learn local geometric representations byembedding graph attention mechanism within stacked Multi-Layer-Perceptron (MLP)layers. Firstly, we introduce a GAPLayer to learn attention features for eachpoint by highlighting different attention weights on neighborhood. Secondly, inorder to exploit sufficient features, a multi-head mechanism is employed toallow GAPLayer to aggregate different features from independent heads. Thirdly,we propose an attention pooling layer over neighbors to capture local signatureaimed at enhancing network robustness. Finally, GAPNet applies stacked MLPlayers to attention features and local signature to fully extract localgeometric structures. The proposed GAPNet architecture is tested on theModelNet40 and ShapeNet part datasets, and achieves state-of-the-artperformance in both shape classification and part segmentation tasks.

GAPNet: Graph Attention based Point Neural Network for Exploiting Local Feature of Point Cloud