• DOI:10.1109/ICCV.2017.234
Corpus ID: 2292730

Joint Discovery of Object States and Manipulation Actions

@article{Alayrac2017JointDO,
  title={Joint Discovery of Object States and Manipulation Actions},
  author={Jean-Baptiste Alayrac and Josef Sivic and I. Laptev and S. Lacoste-Julien},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={2146-2155}
}

Jean-Baptiste Alayrac, Josef Sivic, +1 author S. Lacoste-Julien

Published 2017

Computer Science

2017 IEEE International Conference on Computer Vision (ICCV)

Many human activities involve object manipulations aiming to modify the object state. Examples of common state changes include full/empty bottle, open/closed door, and attached/detached car wheel. In this work, we seek to automatically discover the states of objects and the associated manipulation actions. Given a set of videos for a particular task, we propose a joint model that learns to identify object states and to localize state-modifying actions. Our model is formulated as a… CONTINUE READING

View on IEEE

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed