IS HUMAN OBJECT RECOGNITION BETTER DESCRIBED BY GEON STRUCTURAL DESCRIPTIONS OR BY MULTIPLE VIEWS - COMMENT ON BIEDERMAN AND GERHARDSTEIN (1993)
IS HUMAN OBJECT RECOGNITION BETTER DESCRIBED BY GEON STRUCTURAL DESCRIPTIONS OR BY MULTIPLE VIEWS - COMMENT ON BIEDERMAN AND GERHARDSTEIN (1993)
复制标题
DOI：
10.1037/0096-1523.21.6.1494
复制
发表时间：
1995-12-01
影响因子：
2.1
通讯作者：
BULTHOFF, HH
中科院分区：
文献类型：
--
作者：
TARR, MJ;BULTHOFF, HH
在“日常”条件下，人类物体识别是视点依赖还是视点不变？I. Biederman和P. C. Gerhardstein（1993）认为，观点不变机制几乎完全被使用。然而，我们的分析表明：(a)他们的即时视点不变性条件缺乏表征a：广泛范围的识别现象的通用性，(b)视点相关结果的广泛体不能被视为处理“副产品”或“实验工件”，以及(c) geon结构描述不能连贯地解释类别识别，这是他们想要解释的领域。当前证据的权重支持基于范例的多观点机制，作为范例特定和类别识别的重要组成部分。
Is human object recognition viewpoint dependent or viewpoint invariant under ''everyday'' conditions? I. Biederman and P. C. Gerhardstein (1993) argued that viewpoint-invariant mechanisms are used almost exclusively. However, our analysis indicates that (a) their conditions for immediate viewpoint invariance lack the generality to characterize a :vide range of recognition phenomena, (b) the extensive body of viewpoint-dependent results cannot be dismissed as processing ''by-products'' or ''experimental artifacts,'' and (c) geon structural descriptions cannot coherently account for category recognition, the domain they are intended to explain. The weight of current evidence supports an exemplar-based multiple-views mechanism as an important component of both exemplar-specific and categorical recognition.