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

Depth Perception and Spatial Vision01:15

Depth Perception and Spatial Vision

2.7K
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
2.7K

You might also read

Related Articles

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

Sort by
Same author

Cortical and white matter myelination proceed in concert during early infancy.

Nature communications·2026
Same author

Multiphasic myelination and dendritic growth modulate qMRI signals in human visual cortex.

bioRxiv : the preprint server for biology·2026
Same author

Correction: Hierarchical microstructural tissue growth of the gray and white matter of human visual cortex during the first year of life.

Brain structure & function·2026
Same author

Individual Brain Charting: fifth release of high-resolution fMRI data for cognitive mapping.

Scientific data·2026
Same author

From adolescence to adulthood: functional fingerprints of high-level visual cortex reveal differential development of visuospatial processing.

bioRxiv : the preprint server for biology·2026
Same author

Hierarchical microstructural tissue growth of the gray and white matter of human visual cortex during the first year of life.

Brain structure & function·2026

Related Experiment Video

Updated: Apr 11, 2026

Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues
08:04

Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues

Published on: December 4, 2013

4.9K

Spatiotemporal information during unsupervised learning enhances viewpoint invariant object recognition.

Moqian Tian, Kalanit Grill-Spector

    Journal of Vision
    |May 30, 2015
    PubMed
    Summary

    Unsupervised object recognition improves with more views. Spatiotemporal continuity aids learning with fewer views, enhancing 3-D object recognition across rotations.

    More Related Videos

    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

    1.2K
    Defining the Role Of Language in Infants' Object Categorization with Eye-tracking Paradigms
    07:31

    Defining the Role Of Language in Infants' Object Categorization with Eye-tracking Paradigms

    Published on: February 8, 2019

    7.4K

    Related Experiment Videos

    Last Updated: Apr 11, 2026

    Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues
    08:04

    Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues

    Published on: December 4, 2013

    4.9K
    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

    1.2K
    Defining the Role Of Language in Infants' Object Categorization with Eye-tracking Paradigms
    07:31

    Defining the Role Of Language in Infants' Object Categorization with Eye-tracking Paradigms

    Published on: February 8, 2019

    7.4K

    Area of Science:

    • Cognitive Science
    • Computer Vision
    • Machine Learning

    Background:

    • Object recognition is challenging due to variations in object views and appearance.
    • Humans can learn object recognition across views unsupervised, relying on natural viewing statistics.
    • Debate exists on whether temporal proximity, motion, or spatiotemporal continuity aids unsupervised learning.

    Purpose of the Study:

    • To investigate the role of temporal proximity, motion, and spatiotemporal continuity in unsupervised learning of novel 3-D objects.
    • To determine how different unsupervised learning factors affect 3-D object recognition across rotations.

    Main Methods:

    • Participants underwent unsupervised training with varying numbers of 3-D object views (24 or 8 views) across a 180° space.
    • Training conditions manipulated temporal proximity, motion, and spatiotemporal continuity.
    • Recognition performance on novel views was assessed after training.

    Main Results:

    • With 24 views, no significant difference in recognition was found between temporal proximity and spatiotemporal continuity/motion.
    • With only 8 views, spatiotemporal continuity significantly improved novel view recognition compared to temporal proximity.
    • Temporal proximity alone was sufficient for learning with abundant views, but spatiotemporal information enhanced learning with sparser data.

    Conclusions:

    • View-invariant object recognition can be achieved through temporal proximity with sufficient data.
    • Spatiotemporal information enhances unsupervised learning by creating broader view-tuned representations, especially with limited object views.
    • Findings inform theories of object recognition and computational algorithm development for learning from examples.