A multiple instance learning approach to image annotation with saliency map

Tran Phuong Nhung, Cam Tu Nguyen, Jinhee Chun, Ha Vu Le, Takeshi Tokuyama

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents a novel approach to image annotation based on multi-instance learning (MIL) and saliency map. Image Annotation is an automatic process of assigning labels to images so as to obtain semantic retrieval of images. This problem is often ambiguous as a label is given to the whole image while it may only corresponds to a small region in the image. As a result, MIL methods are suitable solutions to resolve the ambiguities during learning. On the other hand, saliency detection aims at detecting foreground/background regions in images. Once we obtain this information, labels and image regions can be aligned better, i.e., foreground labels (background labels) are more sensitive to foreground areas (background areas). Our proposed method, which is based on an ensemble of MIL classifiers from two views (background/foreground), improves annotation performance in comparison to baseline methods that do not exploit saliency information.

Original languageEnglish
Title of host publicationIC3K 2013; KDIR 2013 - 5th International Conference on Knowledge Discovery and Information Retrieval and KMIS 2013 - 5th International Conference on Knowledge Management and Information Sharing, Proc.
PublisherSciTePress
Pages152-159
Number of pages8
ISBN (Print)9789898565754
DOIs
Publication statusPublished - 2013 Jan 1
Event5th International Conference on Knowledge Discovery and Information Retrieval, KDIR 2013 and the 5th International Conference on Knowledge Management and Information Sharing, KMIS 2013 - Vilamoura, Algarve, Portugal
Duration: 2013 Sep 192013 Sep 22

Publication series

NameIC3K 2013; KDIR 2013 - 5th International Conference on Knowledge Discovery and Information Retrieval and KMIS 2013 - 5th International Conference on Knowledge Management and Information Sharing, Proc.

Other

Other5th International Conference on Knowledge Discovery and Information Retrieval, KDIR 2013 and the 5th International Conference on Knowledge Management and Information Sharing, KMIS 2013
CountryPortugal
CityVilamoura, Algarve
Period13/9/1913/9/22

Keywords

  • Image annotation
  • Multiple instance learning
  • Visual saliency

ASJC Scopus subject areas

  • Information Systems
  • Software

Fingerprint Dive into the research topics of 'A multiple instance learning approach to image annotation with saliency map'. Together they form a unique fingerprint.

Cite this