BROWSE

Related Researcher

Author's Photo

Hwang, Sung Ju
Machine Learning and Visual Recognition Group
Research Interests
  • Machine learning, deep learning, visual recognition, natural language processing

ITEM VIEW & DOWNLOAD

Learning the Relative Importance of Objects from Tagged Images for Retrieval and Cross-Modal Search

Cited 9 times inthomson ciCited 14 times inthomson ci
Title
Learning the Relative Importance of Objects from Tagged Images for Retrieval and Cross-Modal Search
Author
Hwang, Sung JuGrauman, Kristen
Keywords
Image retrieval; Image tags; Multi-modal retrieval; Cross-modal retrieval; Image search; Object recognition; Auto annotation; Kernelized canonical correlation analysis
Issue Date
2012-11
Publisher
SPRINGER
Citation
INTERNATIONAL JOURNAL OF COMPUTER VISION, v.100, no.2, pp.134 - 153
Abstract
We introduce an approach to image retrieval and auto-tagging that leverages the implicit information about object importance conveyed by the list of keyword tags a person supplies for an image. We propose an unsupervised learning procedure based on Kernel Canonical Correlation Analysis that discovers the relationship between how humans tag images (e.g., the order in which words are mentioned) and the relative importance of objects and their layout in the scene. Using this discovered connection, we show how to boost accuracy for novel queries, such that the search results better preserve the aspects a human may find most worth mentioning. We evaluate our approach on three datasets using either keyword tags or natural language descriptions, and quantify results with both ground truth parameters as well as direct tests with human subjects. Our results show clear improvements over approaches that either rely on image features alone, or that use words and image features but ignore the implied importance cues. Overall, our work provides a novel way to incorporate high-level human perception of scenes into visual representations for enhanced image search
URI
Go to Link
DOI
10.1007/s11263-011-0494-3
ISSN
0920-5691
Appears in Collections:
EE_Journal Papers
Files in This Item:
000308364500003.pdf Download

find_unist can give you direct access to the published full text of this article. (UNISTARs only)

Show full item record

qrcode

  • mendeley

    citeulike

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

MENU