Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Force Classification

Force Classification

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,...

Classification of Systems-I

Classification of Systems-I

Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:

You might also read

Related Articles

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

Sort by

Same author

Elucidation of aniline adsorption-desorption mechanism on various organo-mineral complexes.

Environmental science and pollution research international·2023

Same author

Deep Ranking for Image Zero-Shot Multi-Label Classification.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2020

Same author

The Regional Network for Asian Schistosomiasis and Other Helminth Zoonoses (RNAS(+)) target diseases in face of climate change.

Advances in parasitology·2010

Same author

Monomeric type I and type III transforming growth factor-β receptors and their dimerization revealed by single-molecule imaging.

Cell research·2010

Same author

Quantitative prediction of the thermal motion and intrinsic disorder of protein cofactors in crystalline state: a case study on halide anions.

Journal of theoretical biology·2010

Same author

Structure determination of selaginellins G and H from Selaginella pulvinata by NMR spectroscopy.

Magnetic resonance in chemistry : MRC·2010

Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Nov 2, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

A semi-supervised zero-shot image classification method based on soft-target.

Zhong Ji¹, Qiang Wang¹, Biying Cui¹

¹School of Electrical and Information Engineering, Tianjin University, Tianjin, China.

Neural Networks : the Official Journal of the International Neural Network Society

|June 8, 2021

Summary

This summary is machine-generated.

This study introduces a novel Soft-Target Semi-supervised Classification (STSC) model to improve zero-shot learning (ZSL). The STSC model effectively addresses domain shift and enhances generalization for recognizing unseen categories.

Keywords:

Autoencoder Image classification Semi-supervised learning Soft-Target Zero-shot learning

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

Related Experiment Videos

Last Updated: Nov 2, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Zero-shot learning (ZSL) faces challenges with domain shift and generalization.
Existing ZSL models struggle to recognize data from unseen categories effectively.

Purpose of the Study:

To propose a novel Soft-Target Semi-supervised Classification (STSC) model.
To address the fundamental challenges of domain shift and generalization in ZSL.
To improve the recognition of unseen categories in ZSL tasks.

Main Methods:

Leveraged an autoencoder network with two branches: one for labeled seen data and another for unlabeled ancillary data.
Utilized side information as latent vectors for implicit alignment of visual and side information in the seen data branch.
Employed unlabeled ancillary data to strengthen network reconstruction and smooth domain distribution, alleviating domain shift.
Proposed a Softmax-T loss function utilizing soft targets to enhance generation ability.

Main Results:

The proposed STSC model demonstrated superior performance in extensive experiments.
The approach showed effectiveness in both traditional zero-shot learning and generalized zero-shot learning tasks.
Experiments were conducted on three benchmark datasets, validating the model's superiority.

Conclusions:

The STSC model effectively tackles domain shift and generalization issues in ZSL.
The implicit alignment and explicit reconstruction strategies contribute to improved ZSL performance.
The proposed method offers a robust solution for recognizing unseen categories in ZSL.