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

Constructing and Visualizing Models using Mime-based Machine-learning Framework06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

2.3K
Mime is a flexible computational framework to construct a machine learning-based integration model with elegant performance. Here, we provide a detailed step-by-step procedure for developing predictive models with high accuracy, leveraging complex datasets to identify critical genes associated with disease progression, patient outcomes, and therapeutic response.
2.3K
A Gaze-Contingent Display Framework for Perceptual Learning Research with Simulated Central Vision Loss07:12

A Gaze-Contingent Display Framework for Perceptual Learning Research with Simulated Central Vision Loss

884
We present development of a gaze-contingent display framework designed for perceptual and oculomotor research simulating central vision loss. This framework is particularly adaptable for studying compensatory behavioral and oculomotor strategies in individuals experiencing both simulated and pathological central vision...
884
Magnetometric Characterization of Intermediates in the Solid-State Electrochemistry of Redox-Active Metal-Organic Frameworks06:53

Magnetometric Characterization of Intermediates in the Solid-State Electrochemistry of Redox-Active Metal-Organic Frameworks

2.6K
Ex situ magnetic surveys can directly provide bulk and local information on a magnetic electrode to reveal its charge storage mechanism step by step. Herein, electron spin resonance (ESR) and magnetic susceptibility are demonstrated to monitor the evaluation of paramagnetic species and their concentration in a redox-active metal-organic framework...
2.6K
Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning08:58

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

13.0K
We describe a protocol for the label-free identification of lymphocyte subtypes using quantitative phase imaging and a machine learning algorithm. Measurements of 3D refractive index tomograms of lymphocytes present 3D morphological and biochemical information for individual cells, which is then analyzed with a machine-learning algorithm for identification of cell...
13.0K
The Active Place Avoidance (APA) Test, an Effective, Versatile and Repeatable Spatial Learning Task for Mice06:03

The Active Place Avoidance (APA) Test, an Effective, Versatile and Repeatable Spatial Learning Task for Mice

2.9K
Here, we present a protocol for the active place avoidance test, a hippocampus-dependent spatial learning paradigm designed for rodents. Altering key parameters allows for re-testing of animals before and after treatments or over...
2.9K
Synthesis and Characterization of Functionalized Metal-organic Frameworks11:27

Synthesis and Characterization of Functionalized Metal-organic Frameworks

49.1K
Synthesis, activation, and characterization of intentionally designed metal-organic framework materials is challenging, especially when building blocks are incompatible or unwanted polymorphs are thermodynamically favored over desired forms. We describe how applications of solvent-assisted linker exchange, powder X-ray diffraction in capillaries and activation via supercritical CO2 drying, can address some of these...
49.1K

You might also read

Related Articles

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

Sort by
Same author

Underlying Semantic Diffusion for Effective and Efficient In-Context Learning.

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

Exploring the Stochastic Regularisation in Normalisation Layers for Semi-Supervised Learning.

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

Embodied Spatial Affordance: Spatial-Aware Affordance Learning for Embodied Navigation and Manipulation.

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

Impact of adjuvant breast radiotherapy on the risk and the survival of second primary lung cancer: a large population-based study.

Japanese journal of clinical oncology·2026
Same author

Paving the Way for Point Cloud Video Representation Learning Using a PDE Model.

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

ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generation.

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

Related Experiment Video

Updated: Jan 19, 2026

Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

2.3K

Label-activating framework for zero-shot learning.

Yang Liu1, Xinbo Gao2, Quanxue Gao1

  • 1State Key Laboratory of Integrated Services Networks, Xidian University, Shaanxi 710071, China.

Neural Networks : the Official Journal of the International Neural Network Society
|September 16, 2019
PubMed
Summary
This summary is machine-generated.

This study introduces a Label-Activating Framework (LAF) to improve zero-shot learning (ZSL) by unifying seen and unseen class labels in a shared space, enhancing generalized ZSL (GZSL) performance.

Keywords:
DiscriminativeLabel spaceSemantic spaceZero-shot learning

More Related Videos

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

884
Author Spotlight: Magnetometric Characterization of Intermediates in the Solid-State Electrochemistry of Redox-Active Metal-Organic Frameworks
06:53

Author Spotlight: Magnetometric Characterization of Intermediates in the Solid-State Electrochemistry of Redox-Active Metal-Organic Frameworks

Published on: June 9, 2023

2.6K

Related Experiment Videos

Last Updated: Jan 19, 2026

Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

2.3K
Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
07:12

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

884
Author Spotlight: Magnetometric Characterization of Intermediates in the Solid-State Electrochemistry of Redox-Active Metal-Organic Frameworks
06:53

Author Spotlight: Magnetometric Characterization of Intermediates in the Solid-State Electrochemistry of Redox-Active Metal-Organic Frameworks

Published on: June 9, 2023

2.6K

Area of Science:

  • Computer Vision
  • Machine Learning
  • Artificial Intelligence

Background:

  • Existing zero-shot learning (ZSL) models often fail to adequately consider label information, learning direct mappings between visual and semantic spaces.
  • Indirect Attribute Prediction (IAP) methods struggle with Generalized ZSL (GZSL) due to differing label spaces for seen and unseen classes.
  • A unified and discriminative label space is crucial for effective semantic-based classification in ZSL and GZSL.

Purpose of the Study:

  • To propose a novel Label-Activating Framework (LAF) that unifies label spaces for both seen and unseen classes in ZSL.
  • To enable the activation of the label space by learning embeddings from visual and semantic information.
  • To enhance the discriminative power of the label space, particularly for the challenging Generalized ZSL (GZSL) task.

Main Methods:

  • The proposed Label-Activating Framework (LAF) embeds visual features and semantic information into a common label space, initially represented by one-hot vectors.
  • The framework learns mappings from vision and semantics to activate the label space, allowing unseen class labels to be represented as linear combinations of seen class labels.
  • A specific model is developed within the framework to mitigate the projection domain shift problem.

Main Results:

  • The activated label space becomes highly discriminative, enabling a unified representation for seen and unseen classes.
  • The proposed LAF demonstrates superior performance compared to state-of-the-art methods in extensive experiments.
  • The framework proves particularly effective and suitable for the Generalized ZSL (GZSL) setting.

Conclusions:

  • The Label-Activating Framework (LAF) offers a more effective and reasonable approach to semantic-based classification, especially for GZSL.
  • By unifying label spaces and enhancing discriminability, LAF addresses key limitations of existing ZSL methods.
  • The developed model effectively tackles projection domain shift, leading to improved ZSL and GZSL performance.