From Red Wine to Red Tomato: Composition with Context

@article{Misra2017FromRW,
  title={From Red Wine to Red Tomato: Composition with Context},
  author={Ishan Misra and Abhinav Gupta and Martial Hebert},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2017},
  pages={1160-1169}
}
Compositionality and contextuality are key building blocks of intelligence. They allow us to compose known concepts to generate new and complex ones. However, traditional learning methods do not model both these properties and require copious amounts of labeled data to learn new concepts. A large fraction of existing techniques, e.g., using late fusion, compose concepts but fail to model contextuality. For example, red in red wine is different from red in red tomatoes. In this paper, we present… CONTINUE READING
Highly Cited
This paper has 26 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.

References

Publications referenced by this paper.
Showing 1-10 of 70 references

Discovering states and transformations in image collections

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2015
View 13 Excerpts
Highly Influenced

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

2015 IEEE International Conference on Computer Vision (ICCV) • 2015
View 3 Excerpts
Highly Influenced

The Pascal Visual Object Classes Challenge: A Retrospective

International Journal of Computer Vision • 2014
View 3 Excerpts
Highly Influenced

Write a Classifier: Zero-Shot Learning Using Purely Textual Descriptions

2013 IEEE International Conference on Computer Vision • 2013
View 4 Excerpts
Highly Influenced

Recognition using visual phrases

View 5 Excerpts
Highly Influenced

Learning Deep Representations of Fine-Grained Visual Descriptions

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2016

Similar Papers

Loading similar papers…