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

Frequency and associated factors of segmental root developmental arrest in endodontically treated immature permanent teeth with apical periodontitis: a retrospective cohort study.

BMC oral health·2026
Same author

Forkhead Box O1 Promotes Osteogenesis of Periodontal Ligament Stem Cells Via Glycolysis-Related Metabolic Reprogramming.

International dental journal·2026
Same author

Topical tapinarof (benvitimod) for papulopustular rosacea: two cases.

Anais brasileiros de dermatologia·2026
Same author

Early detection of Alzheimer's disease based on leveraging multimodal features of the clock drawing test.

Journal of Alzheimer's disease : JAD·2026
Same author

[Early Alzheimer's disease recognition via multimodal hand movement quality assessment].

Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi·2026
Same author

From signal to strategy: a disproportionality analysis of dupilumab-associated rosacea in FAERS with a summary of reported clinical cases.

The Journal of dermatological treatment·2026

Related Experiment Video

Updated: Jun 7, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

369

PVPUFormer: Probabilistic Visual Prompt Unified Transformer for Interactive Image Segmentation.

Xu Zhang, Kailun Yang, Jiacheng Lin

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |November 12, 2024
    PubMed
    Summary

    This study introduces the Probabilistic Visual Prompt Unified Transformer (PVPUFormer) for interactive image segmentation. It enhances performance by considering prompt context and aligning features for more accurate mask predictions.

    More Related Videos

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    2.7K
    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: Jun 7, 2025

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    369
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    2.7K
    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 Vision
    • Machine Learning
    • Artificial Intelligence

    Background:

    • Interactive image segmentation relies on user input like clicks and scribbles.
    • Existing methods often neglect contextual information around prompts, limiting feedback.
    • This leads to suboptimal performance and slower interaction efficiency.

    Purpose of the Study:

    • To propose a novel interactive image segmentation method, the Probabilistic Visual Prompt Unified Transformer (PVPUFormer).
    • To improve prompt feature extraction by incorporating contextual information.
    • To enhance segmentation accuracy and efficiency through better feature alignment.

    Main Methods:

    • Developed a Probabilistic Prompt-unified Encoder (PPuE) to generate unified prompt vectors using contextual information.
    • Introduced a Prompt-to-Pixel Contrastive (P2C) loss for aligning prompt and pixel-level features.
    • Designed a Dual-cross Merging Attention (DMA) module for bidirectional feature interaction.

    Main Results:

    • The proposed PVPUFormer significantly improves interactive image segmentation performance.
    • Experiments demonstrate consistent gains across various challenging datasets.
    • Achieved state-of-the-art results in interactive segmentation tasks.

    Conclusions:

    • The PVPUFormer effectively leverages diverse visual prompts and their context.
    • The P2C loss and DMA module contribute to robust feature representation and alignment.
    • The method offers a powerful and efficient solution for interactive image segmentation.