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 10, 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

Multi-path x-D Recurrent Neural Networks for Collaborative Image Classification.

Riqiang Gao¹, Yuankai Huo¹, Shunxing Bao¹

¹Electrical Engineering and Computer Science, Vanderbilt University, Nashville, TN, USA 37235, Vanderbilt University Medical Center, Nashville, TN, USA 37235.

|September 1, 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

Harmonization of White and Gray Matter Features in Diffusion Microarchitecture for Cross-Sectional Studies.

Computer aided intervention and diagnostics in clinical and medical images·2025

Same author

All-in-SAM: from Weak Annotation to Pixel-wise Nuclei Segmentation with Prompt-based Finetuning.

Journal of physics. Conference series·2025

Same author

Considerations and recommendations from the ISMRM diffusion study group for preclinical diffusion MRI: Part 2-Ex vivo imaging: Added value and acquisition.

Magnetic resonance in medicine·2025

Same author

Characterization of neurite and soma organization in the brain and spinal cord with diffusion MRI.

bioRxiv : the preprint server for biology·2025

Same author

Considerations and recommendations from the ISMRM Diffusion Study Group for preclinical diffusion MRI: Part 3-Ex vivo imaging: Data processing, comparisons with microscopy, and tractography.

Magnetic resonance in medicine·2025

Same author

Considerations and recommendations from the ISMRM diffusion study group for preclinical diffusion MRI: Part 1: In vivo small-animal imaging.

Magnetic resonance in medicine·2025

Same journal

Automated Behavior Analysis in the Novel Object Recognition Test.

Neurocomputing·2026

Same journal

CrunchLLM: Multitask LLMs for Structured Business Reasoning and Outcome Prediction.

Neurocomputing·2026

Same journal

Deep Learning for analyzing chaotic dynamics in biological time series: Insights from frog heart signals.

Neurocomputing·2026

Same journal

SymRefine: A symbolic regression approach for refining and compressing neural networks.

Neurocomputing·2026

Same journal

Artificial intelligence without restriction surpassing human intelligence with probability one: Theoretical insight into secrets of the brain with AI twins of the brain.

Neurocomputing·2025

Same journal

ShaderNN: A Lightweight and Efficient Inference Engine for Real-time Applications on Mobile GPUs.

Neurocomputing·2025

See all related articles

This study introduces the Multi-path x-D Recurrent Neural Network (MxDRNN), a novel deep learning model for image classification. The MxDRNN effectively handles unordered images, significantly improving accuracy across diverse datasets like VGGFace2 and lung screening CT scans.

Area of Science:

Computer Vision
Deep Learning
Artificial Intelligence

Background:

Multiple images per class are common in computer vision tasks.
Recurrent Neural Networks (RNNs) combined with Convolutional Neural Networks (CNNs) are used for ordered image data.
Existing methods struggle with unordered intra-class images.

Purpose of the Study:

To generalize the ordered RNN+CNN design to unordered image classification.
To introduce a novel Multi-path x-D Recurrent Neural Network (MxDRNN).
To improve classification performance on unordered intra-class images.

Main Methods:

Permuting multiple images into dummy orders to create learning paths.
Developing the Multi-path x-D Recurrent Neural Network (MxDRNN) architecture.

Keywords:

RNN category-irrelevant attributes longitudinal unordered image

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Related Experiment Videos

Last Updated: Dec 10, 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

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Evaluating the MxDRNN on eight diverse datasets (MNIST, 3D-MNIST, CIFAR, VGGFace2, lung CT).

Main Results:

Significant performance improvements across various fields, e.g., accuracy from 46.40% to 76.54% in VGGFace2.
Enhanced AUC from 0.7418 to 0.8162 in the NLST lung dataset.
Demonstrated robustness to category-irrelevant attributes like pose and expression.

Conclusions:

The MxDRNN effectively classifies unordered intra-class images.
The proposed method offers superior performance and generalizability compared to baselines.
MxDRNN represents a significant advancement in applying RNNs to unordered image classification.