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

Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

7.0K
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...
7.0K
Force Classification01:22

Force Classification

1.6K
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,...
1.6K
Deconvolution01:20

Deconvolution

246
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...
246
Classification of Signals01:30

Classification of Signals

862
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
862
Detection of Gross Error: The Q Test01:00

Detection of Gross Error: The Q Test

6.4K
When one or more data points appear far from the rest of the data, there is a need to determine whether they are outliers and whether they should be eliminated from the data set to ensure an accurate representation of the measured value. In many cases, outliers arise from gross errors (or human errors) and do not accurately reflect the underlying phenomenon. In some cases, however, these apparent outliers reflect true phenomenological differences. In these cases, we can use statistical methods...
6.4K
Masking and Demasking Agents01:19

Masking and Demasking Agents

2.6K
EDTA titrations may necessitate masking and demasking agents to temporarily protect a particular metal ion in a mixture from the EDTA reaction. These agents facilitate the sequential analysis of the metal ions by forming stable complexes with some—but not all—metal ions during certain steps.
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...
2.6K

You might also read

Related Articles

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

Sort by
Same author

The Explosion of Life: Lessons from Live Imaging of Ovulation.

Reproduction (Cambridge, England)·2026
Same author

Characterizing individual differences in SCR responsivity: A hybrid mixture and single-trial modeling framework.

Biological psychology·2026
Same author

Outcomes of Lung Transplantation for Pulmonary Sarcoidosis Across Multiple Eras: A 25-Year Experience from a US Center.

Sarcoidosis, vasculitis, and diffuse lung diseases : official journal of WASOG·2026
Same author

How Gun Violence Exposure Influences Racial Health Disparities among Adults in the United States.

Journal of racial and ethnic health disparities·2026
Same author

Update of the EORTC Health-related Quality of Life Modules for Bladder Cancer: Phase 1-2 of the Development Process.

European urology oncology·2026
Same author

Combination Therapy with Ceftazidime-Avibactam, Aztreonam, and Topical Polymyxin B for NDM-Producing <i>Klebsiella pneumoniae</i> CNS Infection: A Case Report.

Infection and drug resistance·2026

Related Experiment Video

Updated: Sep 6, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

629

Learning to Overcome Noise in Weak Caption Supervision for Object Detection.

Mesut Erhan Unal, Keren Ye, Mingda Zhang

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |June 30, 2022
    PubMed
    Summary

    This study introduces a novel method for training object detection models using image captions as weak supervision. The approach effectively handles noisy captions, improving detection accuracy and generalizing across datasets.

    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
    08:25

    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

    9.1K
    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
    04:23

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

    Published on: April 21, 2023

    1.9K

    Related Experiment Videos

    Last Updated: Sep 6, 2025

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

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

    Published on: December 15, 2023

    629
    Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
    08:25

    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

    9.1K
    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
    04:23

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

    Published on: April 21, 2023

    1.9K

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Natural Language Processing

    Background:

    • Object detection models typically require detailed bounding box annotations, which are expensive and time-consuming to create.
    • Leveraging naturally occurring image captions offers a potentially cheaper and more scalable source of supervision.
    • Existing methods struggle with the inherent noise and incompleteness of image-level captions for object localization.

    Purpose of the Study:

    • To develop the first mechanism for training object detection models using only image-level captions as weak supervision.
    • To address the challenges posed by noisy and incomplete caption data in weakly-supervised object detection.
    • To create a robust and generalizable framework for extracting object localization information from descriptive text.

    Main Methods:

    • Proposed a technique to filter image-caption pairs, identifying those with sufficient signal for supervision.
    • Developed complementary mechanisms to extract image-level pseudo-labels from captions for training.
    • Implemented an iterative weakly-supervised object detection model trained on these pseudo-labels.
    • Utilized diverse datasets (COCO, Flickr30K, MIRFlickr1M, Conceptual Captions) with varying noise levels.

    Main Results:

    • A method for selecting suitable image-caption pairs significantly improved training signal.
    • The primary pseudo-label inference technique outperformed alternative methods across various settings.
    • Weighting labels from different captions yielded better results than uniform treatment.
    • The developed techniques demonstrated generalization capabilities to unseen datasets.

    Conclusions:

    • Weakly-supervised object detection from image captions is feasible and effective, even with noisy data.
    • The proposed filtering and pseudo-labeling mechanisms are crucial for success.
    • The approach offers a cost-effective alternative to traditional supervised methods for object detection.