In this paper we show a method for identifying ligament tears in MRI scans. We present a new algorithm that builds a spatial pyramid over the tendon invariant to scale and orientation changes of the tendon. We analyze the performance of both LLC encoded texton features and Intensity histograms for building extracting features from the pyramid regions. Figure 1. A cropped MRI of a damaged Patell...

This paper focuses on the problem of 3D shape categorization. For a given set of training 3D shapes, a 3D shape recognition system must be able to predict the class label for a test 3D shape. We introduce a novel discriminative approach for recognizing 3D shape categories which is based on a 3D Spatial Pyramid (3DSP) decomposition. 3D local descriptors computed on the 3D shapes have to be extra...

1. Oxford-IIIT combined: a spatial pyramid intersection kernel SVM image classifier, a sliding-window randomforest object detector, a sliding-window intersection kernel SVM object detector, and a discriminative constellation model facial feature extractor. For each of the twenty features, methods were ranked based on their performance on a validation set and associated to successive runs by dec...

The efficiency of all Zerotree coding algorithms relay on the "decaying spectrum" hypothesis: a wavelet coefficient within a certain frequency scale of a wavelet subband decomposition has a larger magnitude than all his descendants (coefficients situated in higher frequency scales having the same spatial orientation). The higher the percentage this hypothesis is satisfied, the better are the re...

In curve estimation using wavelet methods it is common to select the resolution level to be an integer, so as to exploit the computational advantages of the pyramid or cascade algorithm. This choice, however, can produce a noticeable amount of either oversmoothing or undersmoothing. Its analogue for estimation by kernel methods is to restrict the bandwidth to be an integer power of 1 2 , which ...

(x − x)A(x − x) Mahalanobis distance: Previous work on learning metrics has focused on learning a single distance metric for all instances. One of our primary contributions is to learn a distance function for every training image. Most visual categorization approaches make use of machine learning after computing distances between images (e.g. SVM with pyramid kernel). We want to learn how to co...

This paper discusses a new convolution tree kernel by introducing local alignments. The main idea of the new kernel is to allow some syntactic alternations during each match between subtrees. In this paper, we give an algorithm to calculate the composite kernel. The experiment results show promising improvements on two tasks: semantic role labeling and question classification.