Toumpa, A orcid.org/0000-0003-4438-6809 and Cohn, A (2019) Relational Graph Representation Learning for Predicting Object Affordances. In: NeurIPS 2019: 33rd Conference on Neural Information Processing Systems, 08-14 Dec 2019, Vancouver, Canada.
Abstract
We address the problem of affordance classification for class-agnostic objects considering an open set of actions, by unsupervised learning of object interactions,inducing object affordance classes. A novel qualitative spatial representation incorporating depth information is used to construct Activity Graphs which encode object interactions. These Activity Graphs are clustered to obtain interaction classes, and subsequently extract classes of object affordances. Our experiments demonstrate that our method learns object affordances without being scene- or object-specific.
Metadata
Item Type: | Conference or Workshop Item |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | This is a conference paper presented at NeurIPS 2019: 33rd Conference on Neural Information Processing Systems workshop Graph Representation Learning. |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) |
Depositing User: | Symplectic Publications |
Date Deposited: | 28 Oct 2019 10:00 |
Last Modified: | 14 Dec 2019 01:40 |
Published Version: | https://grlearning.github.io/papers/67.pdf |
Status: | Published |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:152669 |