Approximate Fisher Kernels of Non-iid Image Models for Image Categorization

@article{Cinbis2016ApproximateFK,
  title={Approximate Fisher Kernels of Non-iid Image Models for Image Categorization},
  author={Ramazan Gokberk Cinbis and Jakob J. Verbeek and Cordelia Schmid},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2016},
  volume={38},
  pages={1084-1098}
}
The bag-of-words (BoW) model treats images as sets of local descriptors and represents them by visual word histograms. The Fisher vector (FV) representation extends BoW, by considering the first and second order statistics of local descriptors. In both representations local descriptors are assumed to be identically and independently distributed (iid), which is a poor assumption from a modeling perspective. It has been experimentally observed that the performance of BoW and FV representations… CONTINUE READING
Related Discussions
This paper has been referenced on Twitter 4 times. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-9 of 9 extracted citations

Correlated Topic Vector for Scene Classification

IEEE Transactions on Image Processing • 2017
View 6 Excerpts
Highly Influenced

From BoW to CNN: Two Decades of Texture Representation for Texture Classification

International Journal of Computer Vision • 2018
View 2 Excerpts

SIFT Meets CNN: A Decade Survey of Instance Retrieval

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2018
View 1 Excerpt

Compositional Model Based Fisher Vector Coding for Image Classification

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2017
View 1 Excerpt

Locally-Transferred Fisher Vectors for Texture Classification

2017 IEEE International Conference on Computer Vision (ICCV) • 2017
View 1 Excerpt

Sparse Coding Based Fisher Vector Using a Bayesian Approach

IEEE Signal Processing Letters • 2017
View 1 Excerpt

Learning Gaussian mixture model with a maximization-maximization algorithm for image classification

2016 12th IEEE International Conference on Control and Automation (ICCA) • 2016
View 2 Excerpts

References

Publications referenced by this paper.
Showing 1-10 of 56 references

The Pascal Visual Object Classes Challenge: A Retrospective

International Journal of Computer Vision • 2014
View 8 Excerpts
Highly Influenced

Recognizing indoor scenes

2009 IEEE Conference on Computer Vision and Pattern Recognition • 2009
View 10 Excerpts
Highly Influenced

Using Fisher kernels from topic models for dimensionality reduction

G. Chandalia, M. Beal
Proc. NIPS Workshop Novel Appl. Dimensionality Reduction, 2006, http://citeseerx.ist.psu.edu/ viewdoc/summary?doi=10.1.1.85.3720. • 2006
View 4 Excerpts
Highly Influenced

Fisher Kernels on Visual Vocabularies for Image Categorization

2007 IEEE Conference on Computer Vision and Pattern Recognition • 2007
View 5 Excerpts
Highly Influenced

Latent Dirichlet Allocation

View 4 Excerpts
Highly Influenced

Efficient Additive Kernels via Explicit Feature Maps

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2010
View 4 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…