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 Videos

Viewpoint dependency in object representation and recognition

Z Liu1

  • 1NEC Research Institute, Princeton, NJ 08540, USA.

Spatial Vision
|January 1, 1996
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

Synaptic reorganization following kainic acid-induced seizures during development.

Brain research. Developmental brain research·1998
Same author

Simultaneous learning of motion discrimination in two directions.

Brain research. Cognitive brain research·1998
Same author

Effect of procaine hydrochloride on cyanide intoxication and its effect on neuronal calcium in mice.

Toxicology and applied pharmacology·1998
Same author

Seizures in rats treated with kainic acid induce Fos-like immunoreactivity in locus coeruleus.

Neuroreport·1998
Same author

Rapid analysis of steroidal saponin mixture using electrospray ionization mass spectrometry combined with sequential tandem mass spectrometry.

Rapid communications in mass spectrometry : RCM·1998
Same author

The spacing between binding sites controls the mode of cooperative DNA-protein interactions: implications for evolution of regulatory circuitry.

Journal of molecular biology·1998
Same journal

Comment on 'angle illusion on a picture's surface' by Hammad et al. (2008).

Spatial vision·2009
Same journal

Feature-based attentional modulation increases with stimulus separation in divided-attention tasks.

Spatial vision·2009
Same journal

Spatial distance between target and irrelevant patch modulates detection in a texture segmentation task.

Spatial vision·2009
Same journal

Inhibition related impairments of coherent motion perception in the attention-induced motion blindness paradigm.

Spatial vision·2009
Same journal

Recognition units in reading: backward masking experiments.

Spatial vision·2009
Same journal

Spatial-temporal modeling of interactive image interpretation.

Spatial vision·2009
See all related articles

Object recognition performance can depend on viewpoint, even with viewpoint-independent internal representations. This study shows recognition varies with object parts, challenging existing theories of object representation.

Area of Science:

  • Cognitive Psychology
  • Computer Vision
  • Neuroscience

Background:

  • Object recognition is crucial for interaction with the environment.
  • Current research debates whether internal object representations are viewpoint-dependent or independent.
  • Existing models often conflate viewpoint-dependent performance with viewpoint-dependent representations.

Purpose of the Study:

  • To investigate whether viewpoint-independent internal representations can explain viewpoint-dependent recognition performance.
  • To examine the role of specific object features and learned views in recognition.
  • To test predictions of the Recognition-By-Components theory.

Main Methods:

  • Utilized three-dimensional (3D) natural objects for recognition tasks.

Related Experiment Videos

  • Manipulated object viewpoints and analyzed recognition performance.
  • Compared performance across views sharing similar visible major object parts.

    • Main Results:

    • Recognition performance varied systematically based on the views from which representations were learned.
    • Performance differences were observed even for views sharing the same major object parts.
    • Results suggest that performance can be viewpoint-dependent even if representations are not.

    Conclusions:

    • A viewpoint-independent internal representation does not preclude viewpoint-dependent recognition performance.
    • The findings challenge theories like Recognition-By-Components that may not fully account for view-specific performance.
    • Object recognition is influenced by the interplay between image information and learned representations across different views.