Structural and view-specific representations for the categorization of three-dimensional objects

Date

2008

Authors

Rentschler, I.
Gschwind, M.
Brettel, H.
Osman, E.
Caelli, T.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Journal article

Citation

Vision Research, 2008; 48(25):2501-2508

Statement of Responsibility

Conference Name

Abstract

It has been debated whether object recognition depends on structural or view-specific representations. This issue is revisited here using a paradigm of priming, supervised category learning, and generalization to novel viewpoints. Results show that structural representations can be learned for three-dimensional (3D) objects lacking generalized-cone components (geons). Metric relations between object parts are distinctive features under such conditions. Representations preserving 3D structure are learned provided prior knowledge of object shape and sufficient image input information is available; otherwise view-specific representations are generated. These findings indicate that structural and view-specific representations are related through shifts of representation induced by learning.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

Copyright 2008 Elsevier

License

Grant ID

Call number

Persistent link to this record