Related papers: Exploring Spatial Significance via Hybrid Pyramida…

Convolutional neural networks (CNNs) have achieved remarkable performance in hyperspectral image (HSI) classification over the last few years. Despite the progress that has been made, rich and informative spectral information of HSI has…

Convolution-based and Transformer-based vision backbone networks process images into the grid or sequence structures, respectively, which are inflexible for capturing irregular objects. Though Vision GNN (ViG) adopts graph-level features…

Extracting effective and discriminative features is very important for addressing the challenging person re-identification (re-ID) task. Prevailing deep convolutional neural networks (CNNs) usually use high-level features for identifying…

Traffic flow prediction plays a critical role in the intelligent transportation system, and it is also a challenging task because of the underlying complex Spatio-temporal patterns and heterogeneities evolving across time. However, most…

Traffic flow prediction plays a crucial role in alleviating traffic congestion and enhancing transport efficiency. While combining graph convolution networks with recurrent neural networks for spatial-temporal modeling is a common strategy…

Graph similarity computation aims to predict a similarity score between one pair of graphs to facilitate downstream applications, such as finding the most similar chemical compounds similar to a query compound or Fewshot 3D Action…

Under circumstances of heterophily, where nodes with different labels tend to be connected based on semantic meanings, Graph Neural Networks (GNNs) often exhibit suboptimal performance. Current studies on graph heterophily mainly focus on…

Heterogeneous Graph Neural Networks (HGNNs) have gained significant popularity in various heterogeneous graph learning tasks. However, most existing HGNNs rely on spatial domain-based methods to aggregate information, i.e., manually…

Most existing re-identification methods focus on learning robust and discriminative features with deep convolution networks. However, many of them consider content similarity separately and fail to utilize the context information of the…

Recognition of human actions and associated interactions with objects and the environment is an important problem in computer vision due to its potential applications in a variety of domains. The most versatile methods can generalize to…

Aero-engine is the core component of aircraft and other spacecraft. The high-speed rotating blades provide power by sucking in air and fully combusting, and various defects will inevitably occur, threatening the operation safety of…

Graph similarity learning (GSL), also referred to as graph matching in many scenarios, is a fundamental problem in computer vision, pattern recognition, and graph learning. However, previous GSL methods assume that graphs are homogeneous…

This work presents a novel graph neural network (GNN) architecture, the Feature-specific Interpretable Graph Neural Network (FIGNN), designed to enhance the interpretability of deep learning surrogate models defined on unstructured grids in…

This paper proposes a new Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes. Unlike state-of-the-art Graph Convolutional Neural Network (GCNN)…

Spatially embedded networks (SENs) represent a special type of complex graph, whose topologies are constrained by the networks' embedded spatial environments. The graph representation of such networks is thereby influenced by the embedded…

Scene graph generation (SGG) aims to detect objects in an image along with their pairwise relationships. There are three key properties of scene graph that have been underexplored in recent works: namely, the edge direction information, the…

Recognizing precise geometrical configurations of groups of objects is a key capability of human spatial cognition, yet little studied in the deep learning literature so far. In particular, a fundamental problem is how a machine can learn…

Predicting the future trajectory of surrounding vehicles is essential for the navigation of autonomous vehicles in complex real-world driving scenarios. It is challenging as a vehicle's motion is affected by many factors, including its…

Modeling spatial heterogeneity in the data generation process is essential for understanding and predicting geographical phenomena. Despite their prevalence in geospatial tasks, neural network models usually assume spatial stationarity,…

Recent salient object detection (SOD) methods based on deep neural network have achieved remarkable performance. However, most of existing SOD models designed for low-resolution input perform poorly on high-resolution images due to the…