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

Deconvolution

Deconvolution

Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...

You might also read

Related Articles

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

Sort by

Same author

Frequency-Aware Degradation Modeling for Real-World Thermal Image Super-Resolution.

Entropy (Basel, Switzerland)·2024

Same author

Infrared-Visible Image Fusion Based on Semantic Guidance and Visual Perception.

Entropy (Basel, Switzerland)·2023

Same author

Road-Scene Parsing Based on Attentional Prototype-Matching.

Sensors (Basel, Switzerland)·2022

Same author

Comparative genomic analysis and characterization of incompatibility group FIB plasmid encoded virulence factors of Salmonella enterica isolated from food sources.

BMC genomics·2017

Same author

Electric field exposure promotes epithelial‑mesenchymal transition in human lens epithelial cells via integrin β1‑FAK signaling.

Molecular medicine reports·2017

Same author

Systematic Analysis of Lysine Acetylation in the Halophilic Archaeon Haloferax mediterranei.

Journal of proteome research·2017

Same journal

Research on a Regional Availability Evaluation Model for Road-Area High-Entropy Energy Based on Synergy Factors.

Entropy (Basel, Switzerland)·2026

Same journal

Atmospheric Turbulence Channel Modeling and Performance Analysis of a CO-ZP-OFDM Coherent Optical Communication System for UAV Air-to-Ground Scenarios.

Entropy (Basel, Switzerland)·2026

Same journal

Information Geometry and Asymptotic Theory for SMML Estimators.

Entropy (Basel, Switzerland)·2026

Same journal

Correlation Entropy and Power-Law Kinetics.

Entropy (Basel, Switzerland)·2026

Same journal

Research on the Contagion of Systemic Financial Risk Under the Impact of Climate Risks-From the Perspective of Complex Networks and Machine Learning.

Entropy (Basel, Switzerland)·2026

Same journal

The Statistical-Mechanical Meaning of the Wave Function of Quantum Mechanics.

Entropy (Basel, Switzerland)·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 18, 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

Task-Decoupled Knowledge Transfer for Cross-Modality Object Detection.

Chiheng Wei¹, Lianfa Bai¹, Xiaoyu Chen¹

¹The School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China.

Entropy (Basel, Switzerland)

|August 26, 2023

Summary

This summary is machine-generated.

This study introduces a novel method for infrared object detection, crucial for harsh weather conditions. It enhances cross-modality object detection performance by decoupling tasks and improving feature representation, achieving state-of-the-art results.

Keywords:

cross-modality knowledge transfer task-decoupled pre-training task-relevant hyperparameter evolution

More Related Videos

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

Related Experiment Videos

Last Updated: Jul 18, 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

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

Area of Science:

Computer Vision
Machine Learning
Remote Sensing

Background:

Infrared (IR) imaging is vital for object detection in adverse weather, complementing visible light data.
Existing IR object detection methods often rely on visible-light pre-training, which limits performance due to modality discrepancies.
A scarcity of large-scale IR datasets impedes the development of robust pre-training models.

Purpose of the Study:

To investigate the influence of task-relevant features on cross-modality object detection.
To propose a knowledge transfer algorithm for improved feature representation in IR object detection.
To enhance the performance of object detection across different modalities.

Main Methods:

A knowledge transfer algorithm based on classification and localization decoupling analysis was developed.
A task-decoupled pre-training method was introduced to adjust task-specific attributes learned by the model.
A task-relevant hyperparameter evolution method was proposed to enhance network adaptability during training.

Main Results:

The proposed method demonstrated improved accuracy for multi-modal object detection across various datasets.
State-of-the-art performance was achieved on the FLIR ADAS dataset.
The approach surpassed the performance of most existing multi-spectral object detection methods.

Conclusions:

The developed task-decoupled pre-training and knowledge transfer methods effectively improve cross-modality object detection.
The findings highlight the importance of tailored feature representation for robust performance in challenging environmental conditions.
This research offers a significant advancement for reliable object detection using infrared imaging.