Evaluating bag-of-visual-words representations in scene classification

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)

389 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationProceedings of the ACM International Multimedia Conference and Exhibition
Pages197-206
StatePublished - 2007

Conference

TitleInternational Multimedia Conference, MM'07 - 9th ACM SIG Multimedia International Workshop on Multimedia Information Retrieval, MIR'07
PlaceGermany
CityAugsburg, Bavaria
Period28-28 September 2007

Abstract

Based on keypoints extracted as salient image patches, an image can be described as a "bag of visual words" and this representation has been used in scene classification. The choice of dimension, selection, and weighting of visual words in this representation is crucial to the classification performance but has not been thoroughly studied in previous work. Given the analogy between this representation and the bag-of-words representation of text documents, we apply techniques used in text categorization, including term weighting, stop word removal, feature selection, to generate image representations that differ in the dimension, selection, and weighting of visual words. The impact of these representation choices to scene classification is studied through extensive experiments on the TRECVID and PASCAL collection. This study provides an empirical basis for designing visual-word representations that are likely to produce superior classification performance. Copyright 2007 ACM.

Research Area(s)

  • Bag-of-visual-words, Keypoint, Local interest point, Scene classification

Citation Format(s)

Evaluating bag-of-visual-words representations in scene classification. / Yang, Jun; Jiang, Yu-Gang; Hauptmann, Alexander G.; Ngo, Chong-Wah.

Proceedings of the ACM International Multimedia Conference and Exhibition. 2007. p. 197-206.

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)