… However, it is impractical to use such kernels for … efficient match kernels (EMK) that map
local features to a low dimensional feature space and average the resulting vectors to form a set…

… match kernel—a new kernel function over unordered feature sets that allows them to be
used effectively and efficiently … match kernel may be used in conjunction with existing kernel-…

… applicable in the space of vector sets. In this work we propose a … match kernel – a new
kernel function over unordered feature sets that allows them to be used effectively and efficiently …

… of feature vectors, eg., image sets. A widely used match kernel between two sets of feature
… more efficiently by just matching images assigned to the same anchors. We first construct a …

… a class of temporal match kernels which are able to match and align videos efficiently. It can
… In our case, we employ it to define a class of temporal kernel between set of visual frames. …

… As a result, the proposed method is still efficient for retrieval although we consider both SIFT
… 5(c), we present the histogram of matches between image pairs with or without applying the …

… , can effectively operate on groups of similar features found across multiple images. This
method implicitly performs feature set … Finally, the proposed method is shown effective for place …

… test set. … features in conjunction with efficient match kernels work well on this dataset and
obtain 70.8% accuracy using a single patch size, which beat SPM with the same SIFT features …

… However, the use of multiple kernels faces the challenge of choosing the kernel weights, …
match kernel can be solved efficiently using projected gradient method. Weights on each kernel …

… To turn a generic kernel into a democratic one, we introduce a set of weights a to enforce …
Sminchisescu, “Efficient match kernels between sets of features for visual recognition,” in Proc. …