Learning From Human Attention for Attribute-Assisted Visual Recognition.

With prior knowledge of seen objects, humans have a remarkable ability to recognize novel objects using shared and distinct local attributes. This is significant for the challenging tasks of zero-shot learning (ZSL) and fine-grained visual classification (FGVC), where the discriminative attributes of objects have played an important role. Inspired by human visual attention, neural networks have widely exploited the attention mechanism to learn the locally discriminative attributes for challenging tasks.

The Ihara zeta function as a partition function for network structure characterisation.

Statistical characterizations of complex network structures can be obtained from both the Ihara Zeta function (in terms of prime cycle frequencies) and the partition function from statistical mechanics. However, these two representations are usually regarded as separate tools for network analysis, without exploiting the potential synergies between them. In this paper, we establish a link between the Ihara Zeta function from algebraic graph theory and the partition function from statistical mechanics, and exploit this relationship to obtain a deeper structural characterisation of network structure.

Regionwise Generative Adversarial Image Inpainting for Large Missing Areas.

Recently, deep neural networks have achieved promising performance for in-filling large missing regions in image inpainting tasks. They have usually adopted the standard convolutional architecture over the corrupted image, leading to meaningless contents, such as color discrepancy, blur, and other artifacts. Moreover, most inpainting approaches cannot handle well the case of a large contiguous missing area.

Two-Level Graph Neural Network.

Graph neural networks (GNNs) are recently proposed neural network structures for the processing of graph-structured data. Due to their employed neighbor aggregation strategy, existing GNNs focus on capturing node-level information and neglect high-level information. Existing GNNs, therefore, suffer from representational limitations caused by the local permutation invariance (LPI) problem.

Learning Aligned Vertex Convolutional Networks for Graph Classification.

Graph convolutional networks (GCNs) are powerful tools for graph structure data analysis. One main drawback arising in most existing GCN models is that of the oversmoothing problem, i.e.

Uncalibrated, Two Source Photo-Polarimetric Stereo.

In this paper we present methods for estimating shape from polarisation and shading information, i.e. photo-polarimetric shape estimation, under varying, but unknown, illumination, i.

Erratum: Wang, J., et al. Microcanonical and Canonical Ensembles for fMRI Brain Networks in Alzheimer's Disease. 2021, , 216.

We sincerely apologize for the inconvenience of updating the authorship [...

Early Detection of Alzheimer's Disease: Detecting Asymmetries with a Return Random Walk Link Predictor.

Alzheimer's disease has been extensively studied using undirected graphs to represent the correlations of BOLD signals in different anatomical regions through functional magnetic resonance imaging (fMRI). However, there has been relatively little analysis of this kind of data using directed graphs, which potentially offer the potential to capture asymmetries in the interactions between different anatomical brain regions. The detection of these asymmetries is relevant to detect the disease in an early stage.

Graph Motif Entropy for Understanding Time-Evolving Networks.

The structure of networks can be efficiently represented using motifs, which are those subgraphs that recur most frequently. One route to understanding the motif structure of a network is to study the distribution of subgraphs using statistical mechanics. In this article, we address the use of motifs as network primitives using the cluster expansion from statistical physics.

Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification.

In this paper, we develop a novel backtrackless aligned-spatial graph convolutional network (BASGCN) model to learn effective features for graph classification. Our idea is to transform arbitrary-sized graphs into fixed-sized backtrackless aligned grid structures and define a new spatial graph convolution operation associated with the grid structures. We show that the proposed BASGCN model not only reduces the problems of information loss and imprecise information representation arising in existing spatially-based graph convolutional network (GCN) models, but also bridges the theoretical gap between traditional convolutional neural network (CNN) models and spatially-based GCN models.

Entropic Dynamic Time Warping Kernels for Co-Evolving Financial Time Series Analysis.

Network representations are powerful tools to modeling the dynamic time-varying financial complex systems consisting of multiple co-evolving financial time series, e.g., stock prices.

A Quantum-Inspired Similarity Measure for the Analysis of Complete Weighted Graphs.

We develop a novel method for measuring the similarity between complete weighted graphs, which are probed by means of the discrete-time quantum walks. Directly probing complete graphs using discrete-time quantum walks is intractable due to the cost of simulating the quantum walk. We overcome this problem by extracting a commute time minimum spanning tree from the complete weighted graph.

Face Frontalization Using an Appearance-Flow-Based Convolutional Neural Network.

Facial pose variation is one of the major factors making face recognition (FR) a challenging task. One popular solution is to convert non-frontal faces to frontal ones on which FR is performed. Rotating faces causes facial pixel value changes.

Thermodynamic Analysis of Time Evolving Networks.

The problem of how to represent networks, and from this representation, derive succinct characterizations of network structure and in particular how this structure evolves with time, is of central importance in complex network analysis. This paper tackles the problem by proposing a thermodynamic framework to represent the structure of time-varying complex networks. More importantly, such a framework provides a powerful tool for better understanding the network time evolution.

Thermodynamic characterization of networks using graph polynomials.

In this paper, we present a method for characterizing the evolution of time-varying complex networks by adopting a thermodynamic representation of network structure computed from a polynomial (or algebraic) characterization of graph structure. Commencing from a representation of graph structure based on a characteristic polynomial computed from the normalized Laplacian matrix, we show how the polynomial is linked to the Boltzmann partition function of a network. This allows us to compute a number of thermodynamic quantities for the network, including the average energy and entropy.

Spherical and Hyperbolic Embeddings of Data.

Many computer vision and pattern recognition problems may be posed as the analysis of a set of dissimilarities between objects. For many types of data, these dissimilarities are not euclidean (i.e.

Generative Graph Prototypes from Information Theory.

In this paper we present a method for constructing a generative prototype for a set of graphs by adopting a minimum description length approach. The method is posed in terms of learning a generative supergraph model from which the new samples can be obtained by an appropriate sampling mechanism. We commence by constructing a probability distribution for the occurrence of nodes and edges over the supergraph.

Measuring graph similarity through continuous-time quantum walks and the quantum Jensen-Shannon divergence.

In this paper we propose a quantum algorithm to measure the similarity between a pair of unattributed graphs. We design an experiment where the two graphs are merged by establishing a complete set of connections between their nodes and the resulting structure is probed through the evolution of continuous-time quantum walks. In order to analyze the behavior of the walks without causing wave function collapse, we base our analysis on the recently introduced quantum Jensen-Shannon divergence.

Approximate von Neumann entropy for directed graphs.

In this paper, we develop an entropy measure for assessing the structural complexity of directed graphs. Although there are many existing alternative measures for quantifying the structural properties of undirected graphs, there are relatively few corresponding measures for directed graphs. To fill this gap in the literature, we explore an alternative technique that is applicable to directed graphs.

Backtrackless walks on a graph.

The aim of this paper is to explore the use of backtrackless walks and prime cycles for characterizing both labeled and unlabeled graphs. The reason for using backtrackless walks and prime cycles is that they avoid tottering, and can increase the discriminative power of the resulting graph representation. However, the use of such methods is limited in practice because of their computational cost.

Characterizing graph symmetries through quantum Jensen-Shannon divergence.

In this paper we investigate the connection between quantum walks and graph symmetries. We begin by designing an experiment that allows us to analyze the behavior of the quantum walks on the graph without causing the wave function collapse. To achieve this, we base our analysis on the recently introduced quantum Jensen-Shannon divergence.

Heat diffusion: thermodynamic depth complexity of networks.

In this paper we use the Birkhoff-von Neumann decomposition of the diffusion kernel to compute a polytopal measure of graph complexity. We decompose the diffusion kernel into a series of weighted Birkhoff combinations and compute the entropy associated with the weighting proportions (polytopal complexity). The maximum entropy Birkhoff combination can be expressed in terms of matrix permanents.

Graph characterization via Ihara coefficients.

The novel contributions of this paper are twofold. First, we demonstrate how to characterize unweighted graphs in a permutation-invariant manner using the polynomial coefficients from the Ihara zeta function, i.e.

Coupled prediction classification for robust visual tracking.

This paper addresses the problem of robust template tracking in image sequences. Our work falls within the discriminative framework in which the observations at each frame yield direct probabilistic predictions of the state of the target. Our primary contribution is that we explicitly address the problem that the prediction accuracy for different observations varies, and in some cases, can be very low.

Probabilistic white matter fiber tracking using particle filtering and von Mises-Fisher sampling.

Standard particle filtering technique have previously been applied to the problem of fiber tracking by Brun et al. [Brun, A., Bjornemo, M.