University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Weakly supervised learning of objects, attributes and their associations

Shi, Zhiyuan, Yang, Yongxin, Hospedales, Timothy M and Xiang, Tao (2014) Weakly supervised learning of objects, attributes and their associations In: European Conference on Computer vision (ECCV) 2014, 2014-09-06-2014-09-12, Zurich, Switzerlanad.

Full text not available from this repository.


When humans describe images they tend to use combinations of nouns and adjectives, corresponding to objects and their associated attributes respectively. To generate such a description automatically, one needs to model objects, attributes and their associations. Conventional methods require strong annotation of object and attribute locations, making them less scalable. In this paper, we model object-attribute associations from weakly labelled images, such as those widely available on media sharing sites (e.g. Flickr), where only image-level labels (either object or attributes) are given, without their locations and associations. This is achieved by introducing a novel weakly supervised non-parametric Bayesian model. Once learned, given a new image, our model can describe the image, including objects, attributes and their associations, as well as their locations and segmentation. Extensive experiments on benchmark datasets demonstrate that our weakly supervised model performs at par with strongly supervised models on tasks such as image description and retrieval based on object-attribute associations. © 2014 Springer International Publishing.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
Shi, Zhiyuan
Hospedales, Timothy M
Date : 2014
DOI : 10.1007/978-3-319-10605-2_31
Copyright Disclaimer : © Springer International Publishing Switzerland 2014
Uncontrolled Keywords : object attribute associations, Weakly supervised learning, Bayesian networks, Supervised learning, Benchmark datasets, Conventional methods, Image descriptions, Non-parametric Bayesian modeling, Object attributes, Weakly supervised learning, Image segmentation
Depositing User : Diane Maxfield
Date Deposited : 16 Apr 2019 13:31
Last Modified : 16 Apr 2019 13:31

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800