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 19, 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

Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks.

Deng-Ping Fan, Zheng Lin, Zhao Zhang

IEEE Transactions on Neural Networks and Learning Systems

|June 4, 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

Q-Bone system: an intelligent quantitative system for alveolar bone loss to assist the diagnosis of periodontitis - model development and validation.

Journal of translational medicine·2026

Same author

RPCANet$^{++}$: Deep Interpretable Robust PCA for Sparse Object Segmentation.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

MRCNet: Motion Reasoning Chain for Cross Modal Video Camouflaged Object Detection.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

SRFormerV2: Taking a Closer Look at Permuted Self-Attention for Image Super-Resolution.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

Efficient Third-Harmonic Generation and the Strain Engineering Control of Polarization Anisotropy in TiS<sub>3</sub>.

Nano letters·2026

Same author

Highly Efficient and Anisotropic Second Harmonic Generation in BiInSe Alloy Nanowire and ReS<sub>2</sub>/BiInSe Heterostructures.

The journal of physical chemistry letters·2026

Same journal

Granular Ball-Based Noise-Resistant Fuzzy Multineighborhood Feature Selection via Label Enhancement and Feature Graph.

IEEE transactions on neural networks and learning systems·2026

Same journal

Fighting Evolving Spam With ARTMAP Models: A Noise-Resilient Online Detection Framework.

IEEE transactions on neural networks and learning systems·2026

Same journal

HyperSAT: Unsupervised Hypergraph Neural Networks for Weighted MaxSAT Problems.

IEEE transactions on neural networks and learning systems·2026

Same journal

Negation of Basic Belief Assignment in Multisource Information Fusion on Dempster-Shafer Theory With Applications in Pattern Classification.

IEEE transactions on neural networks and learning systems·2026

Same journal

Intervention Feasible Region and Driver Risk Capacity Aware Human-Machine Collaborative Safe Trajectory Planning.

IEEE transactions on neural networks and learning systems·2026

Same journal

A Unified Differential Denoising Learning Framework With a Pre-Trained Model and Fuzzy Graph Networks for Drug-Drug Interaction Prediction.

IEEE transactions on neural networks and learning systems·2026

See all related articles

Researchers developed a new dataset and a deep learning model, D3Net, for salient object detection in real-world human activity scenes using RGB-D data. D3Net significantly improves performance and enables efficient salient object mask extraction.

Area of Science:

Computer Vision
Machine Learning
Robotics

Background:

Salient Object Detection (SOD) using RGB-D data is an active research area.
Limited research exists on RGB-D SOD specifically for real-world human activity scenes.
Existing benchmarks and models lack comprehensiveness for this specific domain.

Purpose of the Study:

To address the gap in RGB-D SOD for human activity scenes.
To introduce a new benchmark and dataset for evaluating RGB-D SOD methods.
To propose a novel deep learning architecture for improved RGB-D SOD.

Main Methods:

Collected and curated the Salient Person (SIP) dataset with diverse real-world scenes.
Conducted a large-scale benchmark comparing 32 contemporary SOD models across seven datasets.

More Related Videos

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

Related Experiment Videos

Last Updated: Dec 19, 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

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

Proposed the Deep Depth-Depurator Network (D3Net) with a depth depurator unit and feature learning module.

Main Results:

D3Net outperformed all prior methods across five key performance metrics.
The benchmark provides a comprehensive evaluation and baseline for future research.
D3Net achieved efficient salient object mask extraction at 65 frames/s.

Conclusions:

The proposed D3Net model represents a significant advancement in RGB-D SOD for human activity scenes.
The SIP dataset and comprehensive benchmark facilitate further research and development in the field.
D3Net's efficiency enables practical applications like background changing.