Spatial boundary effect can significantly reduce the performance of a learned discriminative
correlation filter (DCF) model. A commonly used method to relieve this effect is to extract …

Graph classification aims to predict the label associated with a graph and is an important
graph analytic task with widespread applications. Recently, graph neural networks (GNNs) …

Recent findings have shown multiple graph learning models, such as graph classification
and graph matching, are highly vulnerable to adversarial attacks, ie small input …

Despite the recent breakthrough of high accuracy deep graph matching (GM) over visual
images, the robustness of deep GM models is rarely studied which yet has been revealed an …

A recent study has shown that graph matching models are vulnerable to adversarial
manipulation of their input which is intended to cause a mismatching. Nevertheless, there is …

Generalized canonical correlation analysis (GCCA) has been widely used for classification
and regression problems. The key idea of GCCA is to map the data from different views into …

The proximal support vector machine via generalized eigenvalues (GEPSVM) is a well-
known pattern classification method. GEPSVM, however, is prone to outliers due to its use of …

Determination of correspondences between vertexes of two graphs is one of essential tasks
in the computer vision fields. Despite the graph matching problem is NP-hard, hypergraph …

Unbalanced geometric structure caused by variations with deformations, rotations and
outliers is a critical issue that hinders correspondence establishment between image pairs in …

Featured Application Our method can be used for 3D reconstruction, metaverse, virtual
reality and augmented reality. Abstract Image matching is a basic task in three-dimensional …