Related papers: Self-Clustering Graph Transformer Approach to Mode…

Graph Transformers (GTs) have demonstrated superior performance compared to traditional message-passing graph neural networks in many studies, especially in processing graph data with long-range dependencies. However, GTs tend to suffer…

In recent years, functional magnetic resonance imaging has emerged as a powerful tool for investigating the human brain's functional connectivity networks. Related studies demonstrate that functional connectivity networks in the human brain…

We propose the Soft Graph Transformer (SGT), a soft-input-soft-output neural architecture designed for MIMO detection. While Maximum Likelihood (ML) detection achieves optimal accuracy, its exponential complexity makes it infeasible in…

This paper tackles the challenge of automatically assessing physical rehabilitation exercises for patients who perform the exercises without clinician supervision. The objective is to provide a quality score to ensure correct performance…

Functional connectivity (FC) studies have demonstrated the overarching value of studying the brain and its disorders through the undirected weighted graph of fMRI correlation matrix. Most of the work with the FC, however, depends on the way…

Functional magnetic resonance imaging (fMRI) is widely used for studying and diagnosing brain disorders, with functional connectivity (FC) matrices providing powerful representations of large-scale neural interactions. However, existing…

Diverse cognitive processes set different demands on locally segregated and globally integrated brain activity. However, it remains unclear how resting brains configure their functional organization to balance the demands on network…

Semi-supervised learning (SSL) has made notable advancements in medical image segmentation (MIS), particularly in scenarios with limited labeled data and significantly enhancing data utilization efficiency. Previous methods primarily focus…

Deep learning, especially convolutional neural networks (CNNs) and Transformer architectures, have become the focus of extensive research in medical image segmentation, achieving impressive results. However, CNNs come with inductive biases…

Nearly one in five adolescents currently live with a diagnosed mental or behavioral health condition, such as anxiety, depression, or conduct disorder, underscoring the urgency of developing accurate and interpretable diagnostic tools.…

In this paper, we analyze electroencephalograms (EEG) which are recordings of brain electrical activity. We develop new clustering methods for identifying synchronized brain regions, where the EEGs show similar oscillations or waveforms…

Transformers have increasingly outperformed gated RNNs in obtaining new state-of-the-art results on supervised tasks involving text sequences. Inspired by this trend, we study the question of how Transformer-based models can improve the…

Recurrent neural networks (RNNs) trained on compositional tasks can exhibit functional modularity, in which neurons can be clustered by activity similarity and participation in shared computational subtasks. Unlike brains, these RNNs do not…

Functional MRI measuring BOLD signal is an increasingly important imaging modality in studying brain functions and neurological disorders. It can be acquired in either a resting-state or a task-based paradigm. Compared to resting-state…

Graph Convolutional Networks (GCNs) demonstrate strong capability in modeling skeletal topology for action recognition, yet their dense floating-point computations incur high energy costs. Spiking Neural Networks (SNNs), characterized by…

Many real-world relational systems, such as social networks and biological systems, contain dynamic interactions. When learning dynamic graph representation, it is essential to employ sequential temporal information and geometric structure.…

Despite the success of Transformer models in vision and language tasks, they often learn knowledge from enormous data implicitly and cannot utilize structured input data directly. On the other hand, structured learning approaches such as…

For multimodal skeleton-based action recognition, Graph Convolutional Networks (GCNs) are effective models. Still, their reliance on floating-point computations leads to high energy consumption, limiting their applicability in…

Since context modeling is critical for estimating depth from a single image, researchers put tremendous effort into obtaining global context. Many global manipulations are designed for traditional CNN-based architectures to overcome the…

Magnetic resonance imaging (MRI) has played a crucial role in fetal neurodevelopmental research. Structural annotations of MR images are an important step for quantitative analysis of the developing human brain, with Deep Learning providing…