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 Experiment Videos

Semantic-gap-oriented active learning for multilabel image annotation.

Jinhui Tang, Zheng-Jun Zha, Dacheng Tao

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |December 24, 2011
    PubMed
    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

    Holistic Invariant Retracing for Distortion-Resilient Multi-Modal Learning in Spatial Transcriptomics.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same author

    Demonstration of efficient predictive surrogates for large-scale quantum processors.

    Nature communications·2026
    Same author

    A DeepSeek-powered AI system for automated chest radiograph interpretation in clinical practice.

    Nature communications·2026
    Same author

    NoisePO: Efficient Semantic Noise Generation and Ranking for Diffusion-Based Text-to-Image Synthesis.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same author

    Stability and Generalization for Distributed SGDA.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same author

    SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    Style-Aware Contrastive Test-Time Adaptation: A Dual-Cache Model for Robust Vision-Language Alignment.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    Semantic Frame Interpolation.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    Physics-Guided Cross-Modal Decoupling with Test-Time Adaptation for Hyperspectral Image Restoration.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    See all related articles

    This study introduces a novel active learning method for image annotation that prioritizes concepts with larger semantic gaps. This approach optimizes user feedback, improving efficiency in tackling the semantic gap problem.

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Artificial Intelligence

    Background:

    • Active learning methods aim to minimize user effort in image annotation by strategically selecting data points for labeling.
    • Existing methods often treat semantic concepts individually or correlatively, neglecting the core issue of the semantic gap.
    • The semantic gap, representing the difference between low-level image features and high-level semantic concepts, is a key challenge in image understanding.

    Discussion:

    • This paper proposes a semantic-gap-oriented active learning strategy that integrates semantic gap measurement into sample selection.
    • The method leverages an extended multilabel sparse-graph-based semisupervised learning model that accounts for semantic correlations.
    • By focusing user feedback on concepts with larger semantic gaps, the proposed method aims to more effectively bridge the semantic gap.

    Related Experiment Videos

    Key Insights:

    • The magnitude of the semantic gap for each concept significantly impacts the effectiveness of user feedback in image annotation.
    • Incorporating semantic gap measures into active learning strategies enhances the performance of user feedback.
    • Prioritizing user effort towards concepts with larger semantic gaps leads to more efficient and effective image annotation.

    Outlook:

    • Future research could explore adaptive weighting schemes for semantic gap measures in active learning.
    • Investigating the scalability of this approach to larger and more complex image datasets is warranted.
    • Further analysis of different semantic gap metrics and their impact on various machine learning models is recommended.