Abstract | ||
---|---|---|
Our work is oriented towards the idea of developing cognitive capabilities in artificial systems through Object Action Complexes (OACs) [7]. The theory comes up with the claim that objects and actions are inseparably intertwined. Categories of objects are not built by visual appearance only, as very common in computer vision, but by the actions an agent can perform and by attributes perceivable. The core of the OAC concept is constituting objects from a set of attributes, which can be manifold in type (e.g. color, shape, mass, material), to actions. This twofold of attributes and actions provides the base for categories. The work presented here is embedded in the development of an extensible system for providing and evolving attributes, beginning with attributes extractable from visual data. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1007/978-3-540-79547-6_2 | ICVS |
Keywords | Field | DocType |
shape attribute,visual data,visual appearance,attributes perceivable,object action complex,computer vision,object action complexes,cognitive capability,attributes extractable,extensible system,artificial system,oac concept,computer and information science | Computer vision,Computer science,Artificial intelligence,Artificial systems,Cognition,Cognitive vision,Visual appearance | Conference |
Volume | ISSN | ISBN |
5008 | 0302-9743 | 3-540-79546-4 |
Citations | PageRank | References |
6 | 0.57 | 7 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kai Huebner | 1 | 90 | 6.29 |
Mårten Björkman | 2 | 202 | 13.90 |
Babak Rasolzadeh | 3 | 30 | 1.87 |
Martina Schmidt | 4 | 6 | 0.57 |
Danica Kragic | 5 | 2070 | 142.17 |