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

Cooperative sparse representation in two opposite directions for semi-supervised image annotation.

Zhong-Qiu Zhao1, Hervé Glotin, Zhao Xie

  • 1College of Computer Science and Information Engineering, Hefei University of Technology, Hefei 230009, China.

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|May 12, 2012
PubMed
Summary

Related Concept Videos

2D NMR: Overview of Homonuclear Correlation Techniques01:16

2D NMR: Overview of Homonuclear Correlation Techniques

Homonuclear correlation spectroscopy (COSY) is a powerful technique used in Nuclear Magnetic Resonance (NMR) spectroscopy to study the correlations between nuclei of the same type within a molecule. It provides information about scalar couplings between adjacent nuclei, which helps determine connectivity and structural information. There are several COSY variants, each with its unique strengths and experimental parameters.
COSY90 is the standard two-dimensional (2D) COSY experiment that...
2D NMR: Homonuclear Correlation Spectroscopy (COSY)01:06

2D NMR: Homonuclear Correlation Spectroscopy (COSY)

Homonuclear correlation spectroscopy, or COSY, is a 2-dimensional NMR technique that provides information about coupled protons. Typically, the geminal and vicinal coupling are observed. For example, consider the COSY spectrum of ethyl acetate, where its 1D proton NMR spectrum is plotted along the vertical and horizontal axes with their corresponding chemical shift scale. Three spots on the diagonal corresponding to the three peaks in the 1D proton spectrum are called diagonal peaks. The COSY...

You might also read

Related Articles

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

Sort by
Same author

Data-driven sampling strategies for fine-tuning bird detection modelsa).

The Journal of the Acoustical Society of America·2026
Same author

First Report on the Acoustic Signals of Lahille's Bottlenose Dolphins in Argentina.

Animals : an open access journal from MDPI·2026
Same author

Whistles characterisation using artificial intelligence reveals responses of short-beaked common dolphins to a bio-inspired acoustic mitigation device for fishing nets.

Scientific reports·2025
Same author

Acoustic and visual monitoring of Peale's dolphins (<i>Lagenorhynchus australis</i>) in the Magellan Strait.

PeerJ·2025
Same author

Age and interpulse interval relation from newborn to adult sperm whale (Physeter macrocephalus) off Mauritius.

Scientific reports·2024
Same author

Deep audio embeddings for vocalisation clustering.

PloS one·2023

This study introduces cooperative kernel sparse representation (Co-KSR) for semi-supervised image annotation. Co-KSR leverages complementary forward and backward sparse representations, significantly improving annotation performance over existing methods.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Artificial Intelligence

Background:

  • Sparse Representation (SR) is effective for computer vision tasks.
  • Kernel SR offers powerful classification capabilities.
  • Semi-supervised learning is crucial for leveraging limited labeled data.

Purpose of the Study:

  • To explore the application of cooperative SR in semi-supervised image annotation.
  • To introduce a novel backward SR method and investigate its complementarity with forward SR.
  • To develop and evaluate a Cooperative Kernel Sparse Representation (Co-KSR) method for enhanced image annotation.

Main Methods:

  • Utilizing forward SR to represent unlabeled images using labeled ones.
  • Introducing and applying backward SR to represent labeled images using unlabeled ones.

Related Experiment Videos

  • Employing co-training to combine forward and backward SR in kernel space, forming Co-KSR.

    • Main Results:

    • Experimental results demonstrate that forward and backward KSRs are complementary.
    • The proposed Co-KSR method significantly outperforms individual SR methods.
    • Co-KSR achieves superior image annotation performance compared to state-of-the-art semi-supervised classifiers.

    Conclusions:

    • The complementary nature of SR in opposite directions is validated.
    • Co-KSR offers a significant advancement in semi-supervised image annotation.
    • Sparsity plays a critical role in the cooperative image representation for improved annotation.