View in EDS

Semantic Concept Co-Occurrence Patterns for Image Annotation and Retrieval.

Saved in:
Bibliographic Details
Title: Semantic Concept Co-Occurrence Patterns for Image Annotation and Retrieval.
Authors: Feng, Linan1, Bhanu, Bir2
Source: IEEE Transactions on Pattern Analysis & Machine Intelligence. Apr2016, Vol. 38 Issue 4, p785-799. 15p.
Subjects: Image retrieval, Image converters, Digital image processing, Pattern recognition systems, Imaging systems, Information retrieval research
Abstract: Describing visual image contents by semantic concepts is an effective and straightforward way to facilitate various high level applications. Inferring semantic concepts from low-level pictorial feature analysis is challenging due to the semantic gap problem, while manually labeling concepts is unwise because of a large number of images in both online and offline collections. In this paper, we present a novel approach to automatically generate intermediate image descriptors by exploiting concept co-occurrence patterns in the pre-labeled training set that renders it possible to depict complex scene images semantically. Our work is motivated by the fact that multiple concepts that frequently co-occur across images form patterns which could provide contextual cues for individual concept inference. We discover the co-occurrence patterns as hierarchical communities by graph modularity maximization in a network with nodes and edges representing concepts and co-occurrence relationships separately. A random walk process working on the inferred concept probabilities with the discovered co-occurrence patterns is applied to acquire the refined concept signature representation. Through experiments in automatic image annotation and semantic image retrieval on several challenging datasets, we demonstrate the effectiveness of the proposed concept co-occurrence patterns as well as the concept signature representation in comparison with state-of-the-art approaches. [ABSTRACT FROM PUBLISHER]
Copyright of IEEE Transactions on Pattern Analysis & Machine Intelligence is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 113814125
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Semantic Concept Co-Occurrence Patterns for Image Annotation and Retrieval.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Feng%2C+Linan%22">Feng, Linan</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Bhanu%2C+Bir%22">Bhanu, Bir</searchLink><relatesTo>2</relatesTo>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22IEEE+Transactions+on+Pattern+Analysis+%26+Machine+Intelligence%22">IEEE Transactions on Pattern Analysis & Machine Intelligence</searchLink>. Apr2016, Vol. 38 Issue 4, p785-799. 15p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Image+retrieval%22">Image retrieval</searchLink><br /><searchLink fieldCode="DE" term="%22Image+converters%22">Image converters</searchLink><br /><searchLink fieldCode="DE" term="%22Digital+image+processing%22">Digital image processing</searchLink><br /><searchLink fieldCode="DE" term="%22Pattern+recognition+systems%22">Pattern recognition systems</searchLink><br /><searchLink fieldCode="DE" term="%22Imaging+systems%22">Imaging systems</searchLink><br /><searchLink fieldCode="DE" term="%22Information+retrieval+research%22">Information retrieval research</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Describing visual image contents by semantic concepts is an effective and straightforward way to facilitate various high level applications. Inferring semantic concepts from low-level pictorial feature analysis is challenging due to the semantic gap problem, while manually labeling concepts is unwise because of a large number of images in both online and offline collections. In this paper, we present a novel approach to automatically generate intermediate image descriptors by exploiting concept co-occurrence patterns in the pre-labeled training set that renders it possible to depict complex scene images semantically. Our work is motivated by the fact that multiple concepts that frequently co-occur across images form patterns which could provide contextual cues for individual concept inference. We discover the co-occurrence patterns as hierarchical communities by graph modularity maximization in a network with nodes and edges representing concepts and co-occurrence relationships separately. A random walk process working on the inferred concept probabilities with the discovered co-occurrence patterns is applied to acquire the refined concept signature representation. Through experiments in automatic image annotation and semantic image retrieval on several challenging datasets, we demonstrate the effectiveness of the proposed concept co-occurrence patterns as well as the concept signature representation in comparison with state-of-the-art approaches. [ABSTRACT FROM PUBLISHER]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of IEEE Transactions on Pattern Analysis & Machine Intelligence is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=113814125
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1109/TPAMI.2015.2469281
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 15
        StartPage: 785
    Subjects:
      – SubjectFull: Image retrieval
        Type: general
      – SubjectFull: Image converters
        Type: general
      – SubjectFull: Digital image processing
        Type: general
      – SubjectFull: Pattern recognition systems
        Type: general
      – SubjectFull: Imaging systems
        Type: general
      – SubjectFull: Information retrieval research
        Type: general
    Titles:
      – TitleFull: Semantic Concept Co-Occurrence Patterns for Image Annotation and Retrieval.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Feng, Linan
      – PersonEntity:
          Name:
            NameFull: Bhanu, Bir
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 04
              Text: Apr2016
              Type: published
              Y: 2016
          Identifiers:
            – Type: issn-print
              Value: 01628828
          Numbering:
            – Type: volume
              Value: 38
            – Type: issue
              Value: 4
          Titles:
            – TitleFull: IEEE Transactions on Pattern Analysis & Machine Intelligence
              Type: main
ResultId 1