Discovering Latent Topics with Saliency-weighted LDA for Image Scene Understanding

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 22
  • Download : 0
In the Latent Dirichlet Allocation (LDA) model, each image is represented by word distributions with their latent topics. Since the previous LDA-based models are not capable of dealing with the spatial information of visual words in images, this paper focuses on discovering the latent topics of images with visual saliency. To accomplish this, a saliency-weighted LDA (swLDA) model is proposed which incorporates visual saliency into the topic distribution of visual words, in a manner similar to human perception. The topic distributions of the visual words were learned with saliency weights reflecting whether the visual words were in the salient or non-salient regions. The experimental results demonstrate that the swLDA model effectively incorporates visual saliency as a focus of attention, mimicking human perception behavior, remarkably outperforming previous LDA models in terms of image categorization.
Publisher
IEEE COMPUTER SOC
Issue Date
2019-07
Language
English
Article Type
Article
Citation

IEEE MULTIMEDIA, v.26, no.3, pp.56 - 68

ISSN
1070-986X
DOI
10.1109/MMUL.2018.2883127
URI
http://hdl.handle.net/10203/267664
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0