# Point Clouds Learning with Attention-based Graph Convolution Networks

arXiv: https://arxiv.org/abs/1905.13445 · HTML: https://mlsanity.com/paper/1905.13445/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 May 2019.

## Built on by (most cited first, 8 of 8)

- [MAAS: Multi-modal Assignation for Active Speaker Detection](https://mlsanity.com/paper/2101.03682/) (2021)
- [Deep Learning Based 3D Segmentation: A Survey](https://mlsanity.com/paper/2103.05423/) (2021)
- [End-to-End Active Speaker Detection](https://mlsanity.com/paper/2203.14250/) (2022)
- [Two-Stream Graph Convolutional Network for Intra-oral Scanner Image Segmentation](https://mlsanity.com/paper/2204.08797/) (2022)
- [Spatiotemporal Deformable Scene Graphs for Complex Activity Detection](https://mlsanity.com/paper/2104.08194/) (2021)
- [Graph Neural Networks: a bibliometrics overview](https://mlsanity.com/paper/2201.01188/) (2022)
- [DANet: Density Adaptive Convolutional Network with Interactive Attention for 3D Point Clouds](https://mlsanity.com/paper/2303.04473/) (2023)
- [Learning 3D Semantics from Pose-Noisy 2D Images with Hierarchical Full Attention Network](https://mlsanity.com/paper/2204.08084/) (2022)

## Abstract (arXiv)

Point clouds data, as one kind of representation of 3D objects, are the most primitive output obtained by 3D sensors. Unlike 2D images, point clouds are disordered and unstructured. Hence it is not straightforward to apply classification techniques such as the convolution neural network to point clouds analysis directly. To solve this problem, we propose a novel network structure, named Attention-based Graph Convolution Networks (AGCN), to extract point clouds features. Taking the learning process as a message propagation between adjacent points, we introduce an attention mechanism to AGCN for analyzing the relationships between local features of the points. In addition, we introduce an additional global graph structure network to compensate for the relative information of the individual points in the graph structure network. The proposed network is also extended to an encoder-decoder structure for segmentation tasks. Experimental results show that the proposed network can achieve state-of-the-art performance in both classification and segmentation tasks.