Invariant representations in object recognition systems are generally obtained by pooling
feature vectors over spatially local neighborhoods. But pooling is not local in the feature …

We introduce a fast deformable spatial pyramid (DSP) matching algorithm for computing
dense pixel correspondences. Dense matching methods typically enforce both appearance …

This paper addresses the problem of category-level image classification. The underlying
image model is a graph whose nodes correspond to a dense set of regions, and edges …

In this paper, we propose a low-rank sparse coding (LRSC) method that exploits local
structure information among features in an image for the purpose of image-level …

Abstract Knowledge transfer from large teacher models to smaller student models has
recently been studied for metric learning, focusing on fine-grained classification. In this work …

Graph-based methods are known to be successful in many machine learning and pattern
classification tasks. These methods consider semistructured data as graphs where nodes …

We propose a dense local region detector to extract features suitable for image matching
and object recognition tasks. Whereas traditional local interest operators rely on repeatable …

The salient region is the most important part of an image. The salient portion in images also
attracts the most attention when people search for images in large-scale datasets. However …

Clinician‐friendly methods for cardiac image segmentation in clinical practice remain a
tough challenge. Larger standard deviation in segmentation accuracy may be expected for …

A fundamental step in biometric recognition is to identify discriminative features in order to
maximize user separation. Matching systems will often require manually choosing these …