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

HCP: A Flexible CNN Framework for Multi-label Image Classification.

Yunchao Wei, Wei Xia, Min Lin

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |October 30, 2015
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    Aggregates Classification01:29

    Aggregates Classification

    1.2K
    Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
    Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
    1.2K
    Force Classification01:22

    Force Classification

    2.6K
    Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
    Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
    2.6K

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Learning Gaze Synthesizer via 3D-eye Controlled Diffusion and Cross-domain Feature Alignment.

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

    Topo4D++: Realistic Physically Based 4D Head Capture With Topology-Preserving Gaussian Splatting and Expression Priors.

    IEEE transactions on pattern analysis and machine intelligence·2025
    Same author

    Longitudinal Study of Changes in Retinal Curvature and its Relationship With Myopia Shift in Chinese Children.

    Investigative ophthalmology & visual science·2025
    Same author

    Deep Rib Fracture Instance Segmentation and Classification From CT on the RibFrac Challenge.

    IEEE transactions on medical imaging·2025
    Same author

    Large Generative Model Impulsed Lightweight Gaze Estimator via Deformable Approximate Large Kernel Pursuit.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025
    Same author

    High <i>Frankia</i> abundance and low diversity of microbial community are associated with nodulation specificity and stability of sea buckthorn root nodule.

    Frontiers in plant science·2024

    This study introduces Hypotheses-CNN-Pooling (HCP), a novel deep learning framework for multi-label image classification. HCP effectively handles complex object layouts and achieves state-of-the-art performance without requiring bounding box data.

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Deep Learning

    Background:

    • Convolutional Neural Networks (CNNs) excel at single-label image classification.
    • Multi-label image classification presents challenges due to complex object arrangements and limited training data.
    • Existing methods struggle to effectively leverage CNNs for multi-label tasks.

    Purpose of the Study:

    • To propose a flexible deep CNN infrastructure, Hypotheses-CNN-Pooling (HCP), for improved multi-label image classification.
    • To address the limitations of current approaches in handling complex object layouts and data scarcity.
    • To develop a method that does not require ground-truth bounding box information for training.

    Main Methods:

    • HCP takes object segment hypotheses as input.

    Related Experiment Videos

  • A shared CNN processes each hypothesis, with outputs aggregated via max pooling.
  • The framework is robust to noisy hypotheses and can utilize pre-trained CNNs.

    • Main Results:

    • HCP achieves superior performance on Pascal VOC 2007 and VOC 2012 multi-label datasets.
    • The proposed method reached 90.5% mAP on the VOC 2012 dataset.
    • Fusion with complementary features improved performance to 93.2% mAP.

    Conclusions:

    • HCP offers a flexible and effective solution for multi-label image classification.
    • The approach overcomes key challenges in the field, including data requirements and object complexity.
    • Experimental results validate HCP's superiority over existing state-of-the-art methods.