Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Dec 7, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

AttPNet: Attention-Based Deep Neural Network for 3D Point Set Analysis.

Yufeng Yang¹, Yixiao Ma¹, Jing Zhang²

¹Computational Biology Department, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA.

Sensors (Basel, Switzerland)

|September 26, 2020

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Multimodal Information-Driven Heterogeneous Graph Neural Networks for Protein-Ligand Binding Affinity Prediction.

Journal of chemical information and modeling·2026

Same author

SCMBench: benchmarking domain-specific and foundation models for single-cell multi-omics data integration.

Nature communications·2026

Same author

MVGFormer: Multi-view perspective with graph-guided transformer for cryo-ET segmentation.

Knowledge-based systems·2026

Same author

HorusEye: a self-supervised foundation model for generalizable X-ray tomography restoration.

Nature computational science·2026

Same author

Microsecond Dynamics of the Pyrophosphate Ion Release in SARS-CoV‑2 RNA Polymerase.

JACS Au·2026

Same author

Incorporating valuable prior knowledge to improve deep learning prediction of genetic perturbation responses.

Genome research·2026

Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026

Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026

Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026

Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026

Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026

Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026

See all related articles

Attention-based Point Network (AttPNet) enhances 3D object recognition by focusing on critical regions and channels. This novel deep learning model improves point set classification accuracy and robustness to data variations.

Area of Science:

Computer Vision
Machine Learning
3D Data Analysis

Background:

Point sets are a compact 3D representation format.
Existing deep learning models often treat all point set regions and channels equally, limiting focus on crucial details.
This can hinder accurate object characterization, especially for fine-grained structures.

Purpose of the Study:

Introduce a novel deep learning model, Attention-based Point Network (AttPNet), for improved point set analysis.
Enhance the ability of models to focus on characteristic regions and channels within point sets.
Improve the robustness and accuracy of 3D object classification using point set data.

Main Methods:

Developed AttPNet utilizing an attention mechanism for global feature masking and channel weighting.

Keywords:

attention mechanism deep neural network point cloud

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Dec 7, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Implemented a two-branch architecture: one for point-wise attention masks, another for abstracting global features with channel attention.

Evaluated performance on the ModelNet40 benchmark and a newly designed Electron Cryo-Tomography (ECT) dataset.

Main Results:

AttPNet achieved a 0.7% higher classification accuracy on ModelNet40 compared to the previous best model, without using voting.
Demonstrated robustness to rotational perturbations and missing points through experiments on augmented data.
Successfully handled fine-grained structures on the ECT dataset, showcasing its practical applicability.

Conclusions:

AttPNet offers a significant advancement in point set-based 3D object recognition.
The attention mechanism effectively directs focus to salient features, improving classification and robustness.
AttPNet shows promise for applications involving complex 3D structures, such as in cryo-electron tomography.