Rethinking network design and local geometry in point cloud: A simple residual MLP framework

X Ma, C Qin, H You, H Ran, Y Fu - arxiv preprint arxiv:2202.07123, 2022 - arxiv.org
Point cloud analysis is challenging due to irregularity and unordered data structure. To
capture the 3D geometries, prior works mainly rely on exploring sophisticated local …

Dual-graph attention convolution network for 3-D point cloud classification

CQ Huang, F Jiang, QH Huang… - … on Neural Networks …, 2022 - ieeexplore.ieee.org
Three-dimensional point cloud classification is fundamental but still challenging in 3-D
vision. Existing graph-based deep learning methods fail to learn both low-level extrinsic and …

Improving graph representation for point cloud segmentation via attentive filtering

N Zhang, Z Pan, TH Li, W Gao… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Recently, self-attention networks achieve impressive performance in point cloud
segmentation due to their superiority in modeling long-range dependencies. However …

[HTML][HTML] Graph Neural Networks in Point Clouds: A Survey

D Li, C Lu, Z Chen, J Guan, J Zhao, J Du - Remote Sensing, 2024 - mdpi.com
With the advancement of 3D sensing technologies, point clouds are gradually becoming the
main type of data representation in applications such as autonomous driving, robotics, and …

Interpretable chirality-aware graph neural network for quantitative structure activity relationship modeling in drug discovery

YL Liu, Y Wang, O Vu, R Moretti… - Proceedings of the …, 2023 - ojs.aaai.org
In computer-aided drug discovery, quantitative structure activity relation models are trained
to predict biological activity from chemical structure. Despite the recent success of applying …

Uncertainty-guided contrastive learning for weakly supervised point cloud segmentation

B Yao, L Dong, X Qiu, K Song, D Yan… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Three-dimensional point cloud data are widely used in many fields, as they can be easily
obtained and contain rich semantic information. Recently, weakly supervised segmentation …

Classification of urban interchange patterns using a model combining shape context descriptor and graph convolutional neural network

M Yang, M Cao, L Cheng, H Jiang, T Ai… - Geo-Spatial Information …, 2024 - Taylor & Francis
Pattern recognition is critical to map data handling and their applications. This study
presents a model that combines the Shape Context (SC) descriptor and Graph …

RailSeg: Learning Local-Global Feature Aggregation with Contextual Information for Railway Point Cloud Semantic Segmentation

T Jiang, B Yang, Y Wang, L Dai, B Qiu… - … on Geoscience and …, 2023 - ieeexplore.ieee.org
Incomplete or outdated inventories of railway infrastructures may disrupt the railway sector's
administration and maintenance of transportation infrastructure, thus posing potential threats …

Kernel-based feature aggregation framework in point cloud networks

J Zhang, Z Zhang, L Wang, L Zhou, X Zhang, M Liu… - Pattern Recognition, 2023 - Elsevier
Various effective deep networks have been developed for analysis of 3D point clouds. One
key step in these networks is to aggregate the features of orderless points into a compact …

Vote2cap-detr++: Decoupling localization and describing for end-to-end 3d dense captioning

S Chen, H Zhu, M Li, X Chen, P Guo… - … on Pattern Analysis …, 2024 - ieeexplore.ieee.org
3D dense captioning requires a model to translate its understanding of an input 3D scene
into several captions associated with different object regions. Existing methods adopt a …