CUED Publications database

Semantic transform: Weakly supervised semantic inference for relating visual attributes

Shankar, S and Lasenby, J and Cipolla, R (2013) Semantic transform: Weakly supervised semantic inference for relating visual attributes. Proceedings of the IEEE International Conference on Computer Vision. pp. 361-368.

Full text not available from this repository.

Abstract

Relative (comparative) attributes are promising for thematic ranking of visual entities, which also aids in recognition tasks. However, attribute rank learning often requires a substantial amount of relational supervision, which is highly tedious, and apparently impractical for real-world applications. In this paper, we introduce the Semantic Transform, which under minimal supervision, adaptively finds a semantic feature space along with a class ordering that is related in the best possible way. Such a semantic space is found for every attribute category. To relate the classes under weak supervision, the class ordering needs to be refined according to a cost function in an iterative procedure. This problem is ideally NP-hard, and we thus propose a constrained search tree formulation for the same. Driven by the adaptive semantic feature space representation, our model achieves the best results to date for all of the tasks of relative, absolute and zero-shot classification on two popular datasets. © 2013 IEEE.

Item Type: Article
Uncontrolled Keywords: Optimization Ranking Semantic Descriptions
Subjects: UNSPECIFIED
Divisions: Div F > Machine Intelligence
Div F > Signal Processing and Communications
Depositing User: Cron Job
Date Deposited: 14 May 2014 21:45
Last Modified: 08 Dec 2014 02:21
DOI: 10.1109/ICCV.2013.52