Name
Abstract | ||
|---|---|---|
We propose to shift the goal of recognition from naming to describing. Doing so allows us not only to name familiar objects, but also: to report unusual aspects of a familiar object (“spotty dog”, not just “dog”); to say something about unfamiliar objects (“hairy and four-legged”, not just “unknown”); and to learn how to recognize new objects with few or no visual examples. Rather than focusing on identity assignment, we make inferring attributes the core problem of recognition. These attributes can be semantic (“spotty”) or discriminative (“dogs have it but sheep do not”). Learning attributes presents a major new challenge: generalization across object categories, not just across instances within a category. In this paper, we also introduce a novel feature selection method for learning attributes that generalize well across categories. We support our claims by thorough evaluation that provides insights into the limitations of the standard recognition paradigm of naming and demonstrates the new abilities provided by our attribute-based framework. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/CVPR.2009.5206772 | Miami, FL |
Keywords | Field | DocType |
feature extraction,learning (artificial intelligence),object recognition,attribute-based framework,feature selection,identity assignment,learning attributes,object attributes,object category,object naming,object recognition | Computer vision,3D single-object recognition,Method,Pattern recognition,Feature selection,Computer science,Object model,Feature extraction,Artificial intelligence,Discriminative model,Machine learning,Cognitive neuroscience of visual object recognition | Conference |
Volume | Issue | ISSN |
2009 | 1 | 1063-6919 |
ISBN | Citations | PageRank |
978-1-4244-3992-8 | 720 | 32.62 |
References | Authors | |
14 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ali Farhadi | 1 | 4492 | 190.40 |
| Endres, I. | 2 | 727 | 33.54 |
| Derek Hoiem | 3 | 4998 | 302.66 |
| D. A. Forsyth | 4 | 9227 | 1138.80 |