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

Difference from Background: Limit of Detection

Difference from Background: Limit of Detection

The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...

You might also read

Related Articles

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

Sort by

Same author

Pose Guided Unsupervised Domain Adaptation for Human Body Part Segmentation.

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

Same author

DEGAST3D: Learning Deformable 3D Graph Similarity to Track Plant Cells in Unregistered Time Lapse Images.

IEEE transactions on computational biology and bioinformatics·2025

Same author

Reconstruction Guided Meta-Learning for Few Shot Open Set Recognition.

IEEE transactions on pattern analysis and machine intelligence·2023

Same author

Text-Based Localization of Moments in a Video Corpus.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2021

Same author

Learning Person Re-Identification Models From Videos With Weak Supervision.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2021

Same author

Exploiting Typicality for Selecting Informative and Anomalous Samples in Videos.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2019

Search research articles

Related Experiment Video

Updated: May 6, 2026

Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues

Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues

Published on: June 3, 2013

A Two-Stage Noise-Tolerant Paradigm for Label Corrupted Person Re-Identification.

Min Liu, Fei Wang, Xueping Wang

IEEE Transactions on Pattern Analysis and Machine Intelligence

|February 2, 2024

Summary

This summary is machine-generated.

This study introduces a novel two-stage noise-tolerant paradigm (TSNT) to address corrupted labels in supervised person re-identification (Re-ID). TSNT significantly improves accuracy on noisy datasets by refining samples and using co-training for robust learning.

More Related Videos

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

Related Experiment Videos

Last Updated: May 6, 2026

Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues

Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues

Published on: June 3, 2013

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

Area of Science:

Computer Vision
Machine Learning

Background:

Supervised person re-identification (Re-ID) methods are vulnerable to inevitable label corruption.
Existing Re-ID approaches often overlook the impact of noisy labels on performance.

Purpose of the Study:

To develop a robust person Re-ID paradigm tolerant to labeling errors.
To enhance the accuracy and reliability of Re-ID systems in real-world, noisy scenarios.

Main Methods:

Proposed a two-stage noise-tolerant paradigm (TSNT) for person Re-ID.
Implemented a self-refining strategy to focus on pure, progressively refurbished samples.
Employed a co-training strategy with a rectified cross-entropy loss and a noise-robust triplet loss for collaborative learning.

Main Results:

Achieved 90.3% rank-1 accuracy on the Market1501 dataset with a 20% noise ratio.
Demonstrated a 6.2% improvement over state-of-the-art methods under noisy conditions.
Validated the superiority and robustness of the TSNT paradigm.

Conclusions:

The proposed TSNT paradigm effectively handles label-corrupted data in person Re-ID.
TSNT offers a significant advancement in building reliable Re-ID systems despite noisy labels.
The method shows strong potential for practical applications requiring accurate person identification.