Spatial pooling for transformation invariant image representation

  title={Spatial pooling for transformation invariant image representation},
  author={Xia Li and Yan Song and Yijuan Lu and Qi Tian},
  booktitle={ACM Multimedia},
Spatial Pyramid Matching (SPM) [2] has been proposed to extend the Bag-of-Word (BoW) model for object classification. By re-serving the finer level information, it makes image matching more accurate. However, for not well-aligned images, where the object is rotated, flipped or translated, SPM may lose its discrimination power. To tackle this problem, we propose novel spatial pooling layouts to address various transformations, and generate a more general image representation. To evaluate the… CONTINUE READING