Conditions for viewpoint dependence and viewpoint invariance: What mechanisms 
are used to recognize an object?

Tarr, MJ; Bülthoff, HH

アイテム詳細

登録内容を編集ファイル形式で保存

一時保存へ追加

このアイテムの新しいバージョンが利用可能です:
https://pure.mpg.de/pubman/item/item_1794599_4

詳細要約

公開

報告書

Conditions for viewpoint dependence and viewpoint invariance: What mechanisms are used to recognize an object?

MPS-Authors

/persons/resource/persons84981

Tarr, MJ
Max Planck Institute for Biological Cybernetics, Max Planck Society;
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons83839

Bülthoff, HH
Max Planck Institute for Biological Cybernetics, Max Planck Society;
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;

External Resource

There are no locators available

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

フルテキスト (公開)

公開されているフルテキストはありません

付随資料 (公開)

There is no public supplementary material available

引用

Tarr, M., & Bülthoff, H.(1993). Conditions for viewpoint dependence and viewpoint invariance: What mechanisms are used to recognize an object? (3). Tübingen, Germany: Max Planck Institute for Biological Cybernetics.

引用: https://hdl.handle.net/11858/00-001M-0000-0013-ED82-C

要旨

Is object recognition viewpoint dependent or viewpoint invariant under "everyday" conditions? While Biederman and Gerhardstein (1993) argue that viewpoint-invariant mechanisms are used almost exclusively, an analysis indicates that: 1) their conditions for immediate viewpoint
invariance lack the generality to characterize everyday recognition; 2) viewpoint-dependent effects are it not the byproduct of systems other than recognition; 3) empirical evidence supports a prominent role for viewpoint-dependent mechanisms in subordindate-level discriminations; 4) geon structural descriptions provide an inadequate
account of how unfamiliar exemplars of familiar categories are recognized because they are at times too stable and too sensitive with regard to the entry-level. We conclude that exemplar-based multiple-views representations may support both viewpoint-dependent and viewpoint-invariant recognition, with relevant information being applied according to context and task.