Large-scale image retrieval with compressed Fisher vectors

@article{Perronnin2010LargescaleIR,
  title={Large-scale image retrieval with compressed Fisher vectors},
  author={Florent Perronnin and Yan Liu and Jorge S{\'a}nchez and Herv{\'e} Poirier},
  journal={2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition},
  year={2010},
  pages={3384-3391}
}
The problem of large-scale image search has been traditionally addressed with the bag-of-visual-words (BOV). In this article, we propose to use as an alternative the Fisher kernel framework. We first show why the Fisher representation is well-suited to the retrieval problem: it describes an image by what makes it different from other images. One drawback of the Fisher vector is that it is high-dimensional and, as opposed to the BOV, it is dense. The resulting memory and computational costs do… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 489 CITATIONS

Adding spatial distribution clue to aggregated vector in image retrieval

  • EURASIP J. Image and Video Processing
  • 2018
VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Towards Visual Feature Translation

  • CVPR 2018
  • 2018
VIEW 14 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Discriminatively Learned Hierarchical Rank Pooling Networks

  • International Journal of Computer Vision
  • 2017
VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Accurate Image Search with Multi-Scale Contextual Evidences

  • International Journal of Computer Vision
  • 2016
VIEW 11 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Dehashing: Server-Side Context-Aware Feature Reconstruction for Mobile Visual Search

  • IEEE Transactions on Circuits and Systems for Video Technology
  • 2016
VIEW 4 EXCERPTS
CITES METHODS & RESULTS
HIGHLY INFLUENCED

Robust aggregation of local image descriptors for visual search

VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Selective aggregated descriptors for robust mobile image retrieval

  • 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)
  • 2015
VIEW 19 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

$\mathcal {L}_p$ -Norm IDF for Scalable Image Retrieval

  • IEEE Transactions on Image Processing
  • 2014
VIEW 16 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Learning Important Spatial Pooling Regions for Scene Classification

  • 2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2014
VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Mobile Visual Search

  • IEEE Signal Processing Magazine
  • 2011
VIEW 20 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2010
2019

CITATION STATISTICS

  • 83 Highly Influenced Citations

  • Averaged 48 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 27 REFERENCES

Packing bag-of-features

  • 2009 IEEE 12th International Conference on Computer Vision
  • 2009
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Spectral Hashing

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Object retrieval with large vocabularies and fast spatial matching

  • 2007 IEEE Conference on Computer Vision and Pattern Recognition
  • 2007
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Scalable Recognition with a Vocabulary Tree

  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Video Google: a text retrieval approach to object matching in videos

  • Proceedings Ninth IEEE International Conference on Computer Vision
  • 2003
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Aggregating local descriptors into a compact image representation

  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
VIEW 2 EXCERPTS

Similar Papers

Loading similar papers…