Learning Shared, Discriminative, and Compact Representations for Visual Recognition

@article{Lobel2015LearningSD,
  title={Learning Shared, Discriminative, and Compact Representations for Visual Recognition},
  author={Hans Lobel and Ren{\'e} Vidal and Alvaro Soto},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2015},
  volume={37},
  pages={2218-2231}
}
Dictionary-based and part-based methods are among the most popular approaches to visual recognition. In both methods, a mid-level representation is built on top of low-level image descriptors and high-level classifiers are trained on top of the mid-level representation. While earlier methods built the mid-level representation without supervision, there is currently great interest in learning both representations jointly to make the mid-level representation more discriminative. In this work we… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 59 references

Similar Papers

Loading similar papers…