Compositional Model Based Fisher Vector Coding for Image Classification

@article{Liu2017CompositionalMB,
  title={Compositional Model Based Fisher Vector Coding for Image Classification},
  author={Lingqiao Liu and Peng Wang and Chunhua Shen and Lei Wang and Anton van den Hengel and Chao Ching Wang and Heng Tao Shen},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2017},
  volume={39},
  pages={2335-2348}
}
Deriving from the gradient vector of a generative model of local features, Fisher vector coding (FVC) has been identified as an effective coding method for image classification. Most, if not all, FVC implementations employ the Gaussian mixture model (GMM) as the generative model for local features. However, the representative power of a GMM can be limited because it essentially assumes that local features can be characterized by a fixed number of feature prototypes, and the number of prototypes… CONTINUE READING
Tweets
This paper has been referenced on Twitter 13 times. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-6 of 6 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 44 references