… Exploiting the dominant orientation in our covariant match kernel provides a complementary
way to further handle the same problem. We mention that using the dominant orientation is …

… image translation via conditional covariance matching. The translated images are used
to train the segmentation network. This framework allows both tasks to improve each other. …

… [19] exploits a simple assumption (time translation) on the temporal model to evaluate ef…
Orientation covariant aggregation of local descriptors with embeddings. In ECCV, Sep. 2014…

… (with translations of a kernel) by SE(2) group convolutions (with roto-translations of a kernel).
The … Our results on the public datasets match or improve upon the state of the art with the …

… Figure 1 demonstrates the illustration of the kernel-based covariance matching framework
… which combines shearing, scaling, rotation and translation sequentially. In our method, the …

… a translated learning method, which exploits a translation … of covariance operators in
Reproducing Kernel Hilbert Spaces. … an unsupervised kernel sorting method to match object pairs …

… The third convolutional layer has a kernel size of 3×3 and … For detectors that are covariant
to more than translation, to avoid … To show the matching performance, we evaluate matching …

… focus on kernel methods on covariance … covariance operator representation and the geometry
of positive definite operators. Computationally, we focus on kernel methods on covariance …

… Such “soft invariances” match intuitive notions of similarity, … of this kind correspond to
translations, rotations and warpings. … instead of ˆΣ, we take Σ to be the regularized covariance form …

… the theory of job matching and the theory of human capital by examining the covariance
structure of … Job matching theory predicts that we should observe an eventual decrease in the …