Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

MsGCN: a multi-stream graph convolutional network for multiband PLV graph fusion in EEG-based biometric identification.

Frontiers in computational neuroscienceĀ·2026
Same author

Multifunctional vanadium-doped carbon dots nanozymes: preparation and applications in colorimetric sensing and tumor therapy.

Mikrochimica actaĀ·2026
Same author

Distinct multiplex immunofluorescence-based immune and stromal marker expression profile of subcutaneously metastatic SMARCA4-deficient undifferentiated thoracic tumor: a case report.

Translational lung cancer researchĀ·2026
Same author

Vdr-PparĪ±-Plin5-regulated lipid droplet dynamics mediates exercise protection against HFD-induced skeletal muscle ectopic lipid deposition and insulin resistance in mice.

Pharmacological researchĀ·2026
Same author

Online health information seeking, healthcare utilization, and exercise-related self-management among patients with long-term conditions in China during COVID-19.

Digital healthĀ·2026
Same author

Reinforcement learning in linear embedding space unlocks generalizable control across soft robot configurations.

Nature communicationsĀ·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 systemsĀ·2026
Same journal

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

IEEE transactions on neural networks and learning systemsĀ·2026
Same journal

HyperSAT: Unsupervised Hypergraph Neural Networks for Weighted MaxSAT Problems.

IEEE transactions on neural networks and learning systemsĀ·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 systemsĀ·2026
Same journal

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

IEEE transactions on neural networks and learning systemsĀ·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 systemsĀ·2026
See all related articles

Related Experiment Video

Updated: May 24, 2025

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories
07:52

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories

Published on: July 10, 2019

14.0K

A Forward and Backward Compatible Framework for Few-Shot Class-Incremental Pill Recognition.

Jinghua Zhang, Li Liu, Kai Gao

    IEEE Transactions on Neural Networks and Learning Systems
    |March 3, 2025
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a new framework for few-shot class-incremental pill recognition (FSCIPR) to handle new pill types with limited data. The discriminative and bidirectional compatible FSCIL (DBC-FSCIL) framework improves recognition accuracy and efficiency in healthcare settings.

    More Related Videos

    Design and Analysis for Fall Detection System Simplification
    08:05

    Design and Analysis for Fall Detection System Simplification

    Published on: April 6, 2020

    10.6K
    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
    04:23

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

    Published on: April 21, 2023

    1.7K

    Related Experiment Videos

    Last Updated: May 24, 2025

    Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories
    07:52

    Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories

    Published on: July 10, 2019

    14.0K
    Design and Analysis for Fall Detection System Simplification
    08:05

    Design and Analysis for Fall Detection System Simplification

    Published on: April 6, 2020

    10.6K
    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
    04:23

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

    Published on: April 21, 2023

    1.7K

    Area of Science:

    • Computer Science
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Automatic pill recognition (APR) is vital for hospital efficiency and patient safety.
    • Current deep learning models struggle with new pill classes due to data limitations.
    • Few-shot class-incremental learning is needed for evolving pill recognition systems.

    Purpose of the Study:

    • To develop the first framework for few-shot class-incremental pill recognition (FSCIPR).
    • To address the challenges of limited data for new pill classes and continuous learning.
    • To improve the adaptability and efficiency of automatic pill recognition systems.

    Main Methods:

    • Introduced the Discriminative and Bidirectional Compatible Few-Shot Class-Incremental Learning (DBC-FSCIL) framework.
    • Proposed virtual class generation and center-triplet (CT) loss for forward-compatible learning.
    • Developed uncertainty quantification for pseudo-feature synthesis in backward-compatible learning, incorporating data replay (DR) and knowledge distillation (KD).

    Main Results:

    • The DBC-FSCIL framework demonstrated superior performance compared to existing state-of-the-art methods.
    • The proposed methods effectively enhance discriminative feature learning and enable backward compatibility.
    • A new pill image dataset for FSCIL was created, establishing new benchmarks.

    Conclusions:

    • The DBC-FSCIL framework offers a robust solution for few-shot class-incremental pill recognition.
    • This approach enables efficient learning of new pill classes while retaining knowledge of old ones.
    • The framework has significant potential for improving healthcare applications reliant on accurate pill identification.