Learning Ordinal Relationships for Mid-Level Vision

We propose a framework that infers mid-level visual properties of an image by learning about ordinal relationships. Instead of estimating metric quantities directly, the system proposes pairwise relationship estimates for points in the input image. These sparse probabilistic ordinal measurements are...

Full description

Bibliographic Details
Main Authors: Krishnan, Dilip (Author), Freeman, William T. (Author), Zoran, Daniel (Contributor), Isola, Phillip John (Contributor)
Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor)
Format: Article
Language:English
Published: Institute of Electrical and Electronics Engineers (IEEE), 2018-06-06T15:24:09Z.
Subjects:
Online Access:Get fulltext