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

Non-equilibrium in the Cell01:16

Non-equilibrium in the Cell

4.4K
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
4.4K
Stereotype Content Model02:16

Stereotype Content Model

14.7K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
14.7K

You might also read

Related Articles

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

Sort by
Same author

Long non-coding RNA UCA1 promotes the tumorigenesis in pancreatic cancer.

Biomedicine & pharmacotherapy = Biomedecine & pharmacotherapie·2016
Same author

Facile Synthesis of Boron-Doped rGO as Cathode Material for High Energy Li-O2 Batteries.

ACS applied materials & interfaces·2016
Same author

Identification of functional farnesoid X receptors in brain neurons.

FEBS letters·2016
Same author

The hydrogen tunneling splitting in malonaldehyde: A full-dimensional time-independent quantum mechanical method.

The Journal of chemical physics·2016
Same author

Cycloaddition Reaction of Vinylphenylfurans and Dimethyl Acetylenedicarboxylate to [8 + 2] Isomers via Tandem [4 + 2]/Diradical Alkene-Alkene Coupling/[1,3]-H Shift Reactions: Experimental Exploration and DFT Understanding of Reaction Mechanisms.

The Journal of organic chemistry·2016
Same author

Surface Modification of Li-Rich Cathode Materials for Lithium-Ion Batteries with a PEDOT:PSS Conducting Polymer.

ACS applied materials & interfaces·2016

Related Experiment Video

Updated: Jul 5, 2025

Generating Strictly Controlled Stimuli for Figure Recognition Experiments
05:39

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Published on: March 18, 2019

5.2K

Prototype-Augmented Self-Supervised Generative Network for Generalized Zero-Shot Learning.

Jiamin Wu, Tianzhu Zhang, Zheng-Jun Zha

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |January 15, 2024
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a novel Prototype-augmented Self-supervised Generative Network to overcome bias in Generalized Zero-Shot Learning (GZSL). The method enhances recognition of unseen classes by integrating self-supervised and prototype learning for domain-aware features.

    More Related Videos

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
    03:14

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

    Published on: December 6, 2024

    587
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.2K

    Related Experiment Videos

    Last Updated: Jul 5, 2025

    Generating Strictly Controlled Stimuli for Figure Recognition Experiments
    05:39

    Generating Strictly Controlled Stimuli for Figure Recognition Experiments

    Published on: March 18, 2019

    5.2K
    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
    03:14

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

    Published on: December 6, 2024

    587
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.2K

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Artificial Intelligence

    Background:

    • Generalized Zero-Shot Learning (GZSL) aims to recognize both seen and unseen classes by linking visual data with semantic embeddings.
    • Existing GZSL methods often exhibit a significant bias, misclassifying unseen class images as belonging to seen classes from the source domain.

    Purpose of the Study:

    • To address the bias problem in GZSL by proposing a novel generative network.
    • To improve the recognition of unseen classes by integrating self-supervised and prototype learning techniques.

    Main Methods:

    • A Self-supervised Learning Module is introduced, using anchors to bridge seen and unseen categories and create domain-aware features by separating source and target domain distributions.
    • A Prototype Enhancing Module utilizes class prototypes for fine-grained target domain modeling, employing alignment and dispersion mechanisms to ensure intra-class compactness and inter-class separability.
    • This work pioneers the use of self-supervised learning as guidance within GZSL frameworks.

    Main Results:

    • The proposed Prototype-augmented Self-supervised Generative Network effectively mitigates the bias issue prevalent in existing GZSL approaches.
    • The integration of self-supervised and prototype learning leads to the generation of superior target class features.
    • Experiments on five standard benchmarks show superior performance compared to current state-of-the-art GZSL methods.

    Conclusions:

    • The developed model successfully enhances Generalized Zero-Shot Learning by reducing bias and improving the recognition of unseen classes.
    • The novel integration of self-supervised and prototype learning offers a promising direction for future GZSL research.