Geometric Latent Dirichlet Allocation on a Matching Graph for Large-scale Image Datasets

  title={Geometric Latent Dirichlet Allocation on a Matching Graph for Large-scale Image Datasets},
  author={James Philbin and Josef Sivic and Andrew Zisserman},
  journal={International Journal of Computer Vision},
Given a large-scale collection of images our aim is to efficiently associate images which contain the same entity, for example a building or object, and to discover the significant entities. To achieve this, we introduce the Geometric Latent Dirichlet Allocation (gLDA) model for unsupervised discovery of particular objects in unordered image collections. This explicitly represents images as mixtures of particular objects or facades, and builds rich latent topic models which incorporate the… CONTINUE READING
Highly Cited
This paper has 77 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 51 extracted citations

Mining near duplicate image groups

Multimedia Tools and Applications • 2014
View 6 Excerpts
Highly Influenced

Learning to Match Images in Large-Scale Collections

ECCV Workshops • 2012
View 4 Excerpts
Highly Influenced

Fine-tuning CNN Image Retrieval with No Human Annotation

IEEE transactions on pattern analysis and machine intelligence • 2018
View 1 Excerpt

SIFT Meets CNN: A Decade Survey of Instance Retrieval

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2018

Common visual pattern discovery and search

2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) • 2017
View 1 Excerpt

On Image Retrieval Techniques and its Scope

Shreya Bansod
View 1 Excerpt

77 Citations

Citations per Year
Semantic Scholar estimates that this publication has 77 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 45 references

Scene Summarization for Online Image Collections

2007 IEEE 11th International Conference on Computer Vision • 2007
View 4 Excerpts
Highly Influenced

Finding scientific topics.

Proceedings of the National Academy of Sciences of the United States of America • 2004
View 5 Excerpts
Highly Influenced

Better matching with fewer features: The selection of useful features in large database recognition problems

2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops • 2009

Decomposition, discovery and detection of visual categories using topic models

2008 IEEE Conference on Computer Vision and Pattern Recognition • 2008
View 2 Excerpts

Similar Papers

Loading similar papers…