Related papers: Beyond Attention: Learning Spatio-Temporal Dynamic…
Detecting driver fatigue is critical for road safety, as drowsy driving remains a leading cause of traffic accidents. Many existing solutions rely on computationally demanding deep learning models, which result in high latency and are…
Graph representation learning methods have been widely adopted in financial applications to enhance company representations by leveraging inter-firm relationships. However, current approaches face three key challenges: (1) The advantages of…
Spatio-temporal graphs such as traffic networks or gene regulatory systems present challenges for the existing deep learning methods due to the complexity of structural changes over time. To address these issues, we introduce…
Dynamic demand prediction is crucial for the efficient operation and management of urban transportation systems. Extensive research has been conducted on single-mode demand prediction, ignoring the fact that the demands for different…
Effective interaction modeling and behavior prediction of dynamic agents play a significant role in interactive motion planning for autonomous robots. Although existing methods have improved prediction accuracy, few research efforts have…
Accurate real-time traffic forecasting is a core technological problem against the implementation of the intelligent transportation system. However, it remains challenging considering the complex spatial and temporal dependencies among…
Attention Deficit Hyperactivity Disorder (ADHD) is a prevalent neurodevelopmental disorder whose neuroimaging-based diagnosis remains challenging due to complex time-varying disruptions in brain connectivity. Functional MRI (fMRI) provides…
Graph Attention Networks (GATs) are one of the most popular GNN architectures and are considered as the state-of-the-art architecture for representation learning with graphs. In GAT, every node attends to its neighbors given its own…
Predicting the motion of surrounding vehicles is essential for autonomous vehicles, as it governs their own motion plan. Current state-of-the-art vehicle prediction models heavily rely on map information. In reality, however, this…
Accurately identifying the underlying graph structures of multi-agent systems remains a difficult challenge. Our work introduces a novel machine learning-based solution that leverages the attention mechanism to predict future states of…
Graph Attention Network (GAT) and GraphSAGE are neural network architectures that operate on graph-structured data and have been widely studied for link prediction and node classification. One challenge raised by GraphSAGE is how to smartly…
Traffic forecasting is an indispensable part of Intelligent transportation systems (ITS), and long-term network-wide accurate traffic speed forecasting is one of the most challenging tasks. Recently, deep learning methods have become…
We present an attention mechanism inspired from definition of screened Coulomb potential. This attention mechanism was used to interpret the Graph Attention (GAT) model layers and training dataset by using a flexible and scalable framework…
The analysis of spatiotemporal data is increasingly utilized across diverse domains, including transportation, healthcare, and meteorology. In real-world settings, such data often contain missing elements due to issues like sensor…
Accurately modelling human attention is essential for numerous computer vision applications, particularly in the domain of automotive safety. Existing methods typically collapse gaze into saliency maps or scanpaths, treating gaze dynamics…
The paradigm of Transformers using the self-attention mechanism has manifested its advantage in learning graph-structured data. Yet, Graph Transformers are capable of modeling full range dependencies but are often deficient in extracting…
Managing microservice architectures in distributed systems is complex and resource intensive due to the high frequency and dynamic nature of inter service interactions. Accurate prediction of these future interactions can enhance adaptive…
Auto-encoders have emerged as a successful framework for unsupervised learning. However, conventional auto-encoders are incapable of utilizing explicit relations in structured data. To take advantage of relations in graph-structured data,…
Graph Neural Networks (GNNs) are deep learning methods which provide the current state of the art performance in node classification tasks. GNNs often assume homophily -- neighboring nodes having similar features and labels--, and therefore…
The cues needed to detect spoofing attacks against automatic speaker verification are often located in specific spectral sub-bands or temporal segments. Previous works show the potential to learn these using either spectral or temporal…