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 Experiment Video

Updated: Jun 8, 2026

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis
05:48

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis

Published on: August 9, 2024

Weakly supervised training of a sign language recognition system using multiple instance learning density matrices.

Daniel Kelly1, John Mc Donald, Charles Markham

  • 1Computer Science Department, National University of Ireland Maynooth, Maynooth, Ireland. dankelly@cs.nuim.ie

IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics : a Publication of the IEEE Systems, Man, and Cybernetics Society
|September 30, 2010
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

NMES-Facilitated Mandibular Rehabilitation for Spasticity-Related Trismus in ALS.

Muscle & nerve·2026
Same author

Frailty and postoperative outcomes following craniopharyngioma resection: a multicenter Registry for Adenomas of the Pituitary and Related Disorders analysis.

Neurosurgical focus·2026
Same author

Educators' knowledge of and perceptions towards students with autism in Nigeria.

International journal of developmental disabilities·2026
Same author

Developmentally Inspired Bioprinting of Nascent Multicellular Human Heart Tissue Through in Situ Differentiation and Morphogenesis of iPSCs.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Phenotypic and Genomic Profiling of <i>Escherichia coli</i> from Irish Raw Milk and Raw Milk Products: A Baseline Study.

Antibiotics (Basel, Switzerland)·2026
Same author

Prevention and Diagnosis of Cervical Cancers in the UK and Europe: What Have We Learned in the Last 10 Years and What Is Next?

British journal of hospital medicine (London, England : 2005)·2026
Same journal

Strategic Ability Updating in Concurrent Games by Coalitional Commitment.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2015
Same journal

Meta-Analysis of the First Facial Expression Recognition Challenge.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

Adjustable model-based fusion method for multispectral and panchromatic images.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

Face Feature Weighted Fusion Based on Fuzzy Membership Degree for Video Face Recognition.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

A New Adaptive Fast Cellular Automaton Neighborhood Detection and Rule Identification Algorithm.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

Human-arm-and-hand-dynamic model with variability analyses for a stylus-based haptic interface.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
See all related articles

This study introduces an automated system for sign language recognition, using a novel algorithm to extract individual signs from sentences for training classifiers. This enables automatic training and spotting of signs in continuous sign language, improving accessibility.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Linguistics

Background:

  • Automated sign language recognition is crucial for communication accessibility.
  • Training sign language models typically requires precisely segmented data, which is labor-intensive.
  • Existing methods struggle with the continuous and nuanced nature of natural sign language.

Purpose of the Study:

  • To develop an automated system for training and spotting signs within continuous sign language sentences.
  • To overcome the limitations of supervised learning by utilizing weak and noisy supervision from text translations.
  • To enable robust sign language recognition without manual segmentation of training data.

Main Methods:

  • A novel multiple instance learning density matrix algorithm was developed for automatic sign extraction.

Related Experiment Videos

Last Updated: Jun 8, 2026

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis
05:48

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis

Published on: August 9, 2024

  • Isolated sign samples were automatically extracted from continuous sentences using text translations as supervision.
  • Spatiotemporal gesture and hand posture classifiers were trained using the automatically extracted sign samples.

    • Main Results:

    • The system demonstrated effective automatic extraction of isolated signs from continuous sign language.
    • Performance evaluations confirmed the efficacy of hand posture classification and spatiotemporal gesture spotting.
    • The overall sign spotting system, trained automatically on 30 signs, achieved successful recognition.

    Conclusions:

    • The proposed system offers an effective solution for automated sign language training and recognition.
    • The multiple instance learning approach significantly reduces the need for manual data annotation.
    • This work advances the field of sign language processing, paving the way for more accessible communication tools.