Most state-of-the-art feature selection methods tend to overlook the structural relationship between a pair of samples associated with each dimension, which may encapsulate useful information for refining performance selection. Moreover, they usually consider candidate relevancy equivalent selected relevancy, and therefore, some less relevant features be misinterpreted as salient features. To o...

We propose the novel audio feature structural change for the analysis and visualisation of recorded music, and argue that it is related to a particular notion of musical complexity. Structural change is a meta feature that can be calculated from an arbitrary frame-wise basis feature, with each element in the structural change feature vector representing the change of the basis feature at a diff...

Learning discriminative representations for unseen person images is critical for person Re-Identification (ReID). Most of current approaches learn deep representations in classification tasks, which essentially minimize the empirical classification risk on the training set. As shown in our experiments, such representations commonly focus on several body parts discriminative to the training set,...

Feature detection on MR images has largely relied on intensity classification and gradient-based magnitudes. In this paper, we propose the use of phase congruency as a more robust detection method, as it is based on a multiscale intensity-invariant measure. We show the application of phase congruency for the detection of cortical sulci from T2 weighted MRI. Sulci represent important landmarks i...

This paper proposes a novel local feature descriptor, Local Directional Number Pattern (LDN), for face analysis: face and expression recognition. LDN encodes the directional information of the face’s textures (i.e., the texture’s structure) in a compact way, producing a more discriminative code than current methods. We compute the structure of each micro-pattern with the aid of a compass mask, ...

Real-world networks exhibit prominent hierarchical and modular structures, with various subgraphs as building blocks. Most existing studies simply consider distinct motifs use only their numbers to characterize the underlying network. Although such statistics can be used describe a network model, or even design some algorithms, role of in applications further explored so improve results. In thi...