Title | ||
---|---|---|
Recognizing object affordances in terms of spatio-temporal object-object relationships |
Abstract | ||
---|---|---|
In this paper we describe a probabilistic framework that models the interaction between multiple objects in a scene. We present a spatio-temporal feature encoding pairwise interactions between each object in the scene. By the use of a kernel representation we embed object interactions in a vector space which allows us to define a metric comparing interactions of different temporal extent. Using this metric we define a probabilistic model which allows us to represent and extract the affordances of individual objects based on the structure of their interaction. In this paper we focus on the presented pairwise relationships but the model can naturally be extended to incorporate additional cues related to a single object or multiple objects. We compare our approach with traditional kernel approaches and show a significant improvement. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/HUMANOIDS.2014.7041337 | Humanoid Robots |
Keywords | Field | DocType |
human-robot interaction,probability,kernel representation,object affordances,object interactions,pairwise interactions,pairwise relationships,probabilistic framework,probabilistic model,spatio-temporal object-object relationships,vector space | Kernel (linear algebra),Computer vision,Pairwise comparison,Pattern recognition,Computer science,Support vector machine,Object model,Feature extraction,Statistical model,Artificial intelligence,Affordance,Encoding (memory) | Conference |
ISSN | Citations | PageRank |
2164-0572 | 7 | 0.51 |
References | Authors | |
27 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Alessandro Pieropan | 1 | 53 | 4.39 |
carl henrik ek | 2 | 327 | 30.76 |
hedvig kjellstrom | 3 | 491 | 42.24 |