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

You might also read

Related Articles

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

Sort by
Same author

Glycolysis-mediated H3K18la modifications drive aggressive bladder cancer through metabolic and epigenetic reprogramming.

Frontiers in immunology·2026
Same author

FP3O: Enabling Proximal Policy Optimization in Multiagent Cooperation With Parameter-Sharing Versatility.

IEEE transactions on neural networks and learning systems·2026
Same author

Stabilizing Topological States in ZrTe<sub>5</sub> from First-Principles Defect Physics.

Nano letters·2026
Same author

Povarov-type Reaction of Anilines, Aqueous Acetaldehyde, and <sup><i>t</i></sup>BuONO for Access to <i>N</i>-Nitroso-1,2,3,4-tetrahydroquinolines.

Organic letters·2026
Same author

Diagnostic association of ante-mortem biomarkers with cerebral amyloid angiopathy in a cohort with high Alzheimer's disease comorbidity.

Journal of Alzheimer's disease reports·2026
Same author

Gene regulatory landscape dissected by single-cell four-omics sequencing.

Nature·2026

Related Experiment Video

Updated: Dec 28, 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

941

Unsupervised AER Object Recognition Based on Multiscale Spatio-Temporal Features and Spiking Neurons.

Qianhui Liu, Gang Pan, Haibo Ruan

    IEEE Transactions on Neural Networks and Learning Systems
    |February 15, 2020
    PubMed
    Summary

    This study introduces an unsupervised approach for object recognition using address event representation (AER) events. It utilizes a novel multiscale spatio-temporal feature (MuST) representation and spiking neural networks (SNNs) for effective and flexible real-world applications.

    More Related Videos

    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
    12:27

    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

    Published on: February 15, 2017

    7.3K
    A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions
    07:34

    A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions

    Published on: March 25, 2014

    10.2K

    Related Experiment Videos

    Last Updated: Dec 28, 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

    941
    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
    12:27

    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

    Published on: February 15, 2017

    7.3K
    A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions
    07:34

    A Simple Stimulatory Device for Evoking Point-like Tactile Stimuli: A Searchlight for LFP to Spike Transitions

    Published on: March 25, 2014

    10.2K

    Area of Science:

    • Neuroscience
    • Computer Science
    • Artificial Intelligence

    Background:

    • Object recognition is a key challenge in machine perception.
    • Traditional methods often require large labeled datasets.
    • Event-based vision offers efficient data streams.

    Purpose of the Study:

    • To propose an unsupervised object recognition method for address event representation (AER) data.
    • To introduce a novel multiscale spatio-temporal feature (MuST) representation.
    • To leverage spiking neural networks (SNNs) with spike-timing-dependent plasticity (STDP) for enhanced recognition.

    Main Methods:

    • Developed a multiscale spatio-temporal feature (MuST) representation for AER events.
    • Implemented an unsupervised spiking neural network (SNN) using spike-timing-dependent plasticity (STDP).
    • Evaluated the approach on five AER datasets, including the new GESTURE-DVS dataset.

    Main Results:

    • MuST effectively extracts spatial and temporal information from AER events into a compact spike representation.
    • The SNN with MuST demonstrates effective unsupervised object recognition.
    • The proposed method shows advantages in flexibility and effectiveness across various datasets.

    Conclusions:

    • The unsupervised AER object recognition approach using MuST and SNNs is effective.
    • MuST enhances information conveyance through spikes, benefiting SNN recognition.
    • The method is suitable for real-world recognition tasks due to its unsupervised nature.