Similarity-based viewspace interpolation and the categorization of 3D objects
In Proc. Edinburgh Workshop on Similarity and Categorization (1997)
Visual objects can be represented by their similarities to a small number of reference shapes or prototypes. This method yields low-dimensional (and therefore computationally tractable) representations, which support both the recognition of familiar shapes and the categorization of novel ones. In this note, we show how such representations can be used in a variety of tasks involving novel objects: viewpoint-invariant recognition, recovery of a canonical view, estimation of pose, and prediction of an arbitrary view. The unifying principle in all these cases is the representation of the view space of the novel object as an interpolation of the view spaces of the reference shapes.
|Keywords||No keywords specified (fix it)|
|Categories||categorize this paper)|
References found in this work BETA
No references found.
Citations of this work BETA
No citations found.
Similar books and articles
Representation is Representation of Similarities.Shimon Edelman - 1998 - Behavioral and Brain Sciences 21 (4):449-467.
How to Combine Interpolation with Feedback?Guenther Palm - 1998 - Behavioral and Brain Sciences 21 (4):478-478.
Empirical Dissociations Between Rule-Based and Similarity-Based Categorization.Gregory Ashby & Michael B. Casale - 2005 - Behavioral and Brain Sciences 28 (1):15-16.
Representation of Similarities – a Psychometric but Not an Explanatory Concept for Categorization.Martin Jüttner - 1998 - Behavioral and Brain Sciences 21 (4):475-476.
Computational Theories of Object Recognition.Shimon Edelman - 1997 - Trends in Cognitive Sciences 1 (8):296-304.
Proc. Edinburgh Workshop on Similarity and Categorization.Shimon Edelman & Sharon Duvdevani-Bar - 1997
Perceptual-Cognitive Universals as Reflections of the World.Roger N. Shepard - 2001 - Behavioral and Brain Sciences 24 (4):581-601.
Parts of Visual Shape as Primitives for Categorization.Manish Singh & Barbara Landau - 1998 - Behavioral and Brain Sciences 21 (1):36-37.
Learning Low-Dimensional Representations Via the Usage of Multiple-Class Labels.S. Edelman - unknown
The Rules Versus Similarity Distinction.Emmanuel M. Pothos - 2005 - Behavioral and Brain Sciences 28 (1):1-14.
Young Children's Representations of Spatial and Functional Relations Between Objects.Rachel Keen & Elizabeth S. Spelke - unknown
Added to index2010-12-22
Total downloads36 ( #139,642 of 2,153,834 )
Recent downloads (6 months)3 ( #225,089 of 2,153,834 )
How can I increase my downloads?