Related papers: Hybrid State-Space and GRU-based Graph Tokenizatio…
Weakly supervised semantic segmentation offers a label-efficient solution to train segmentation models for volumetric medical imaging. However, existing approaches often rely on 2D encoders that neglect the inherent volumetric nature of the…
Non-coding RNAs (ncRNAs) play pivotal roles in gene expression regulation and the pathogenesis of various diseases. Accurate classification of ncRNAs is essential for functional annotation and disease diagnosis. To address existing…
Unsupervised graph-level anomaly detection (UGLAD) is a critical and challenging task across various domains, such as social network analysis, anti-cancer drug discovery, and toxic molecule identification. However, existing methods often…
Molecular representation learning, a cornerstone for downstream tasks like molecular captioning and molecular property prediction, heavily relies on Graph Neural Networks (GNN). However, GNN suffers from the over-smoothing problem, where…
State Space Models (SSM), such as Mamba, have shown strong representation ability in modeling long-range dependency with linear complexity, achieving successful applications from high-level to low-level vision tasks. However, SSM's…
Efficiently modeling large 2D contexts is essential for various fields including Giga-Pixel Whole Slide Imaging (WSI) and remote sensing. Transformer-based models offer high parallelism but face challenges due to their quadratic complexity…
Single hyperspectral image super-resolution (SHSR) aims to restore high-resolution images from low-resolution hyperspectral images. Recently, the Visual Mamba model has achieved an impressive balance between performance and computational…
Haze contamination in hyperspectral remote sensing images (HSI) can lead to spatial visibility degradation and spectral distortion. Haze in HSI exhibits spatial irregularity and inhomogeneous spectral distribution, with few dehazing…
Graph Mamba, a powerful graph embedding technique, has emerged as a cornerstone in various domains, including bioinformatics, social networks, and recommendation systems. This survey represents the first comprehensive study devoted to Graph…
Medical image super-resolution (SR) is essential for enhancing diagnostic accuracy while reducing acquisition cost and scanning time. However, modeling both long-range anatomical structures and fine-grained frequency details with low…
Transformers have demonstrated impressive results for 3D point cloud semantic segmentation. However, the quadratic complexity of transformer makes computation costs high, limiting the number of points that can be processed simultaneously…
In the field of multimodal medical data analysis, leveraging diverse types of data and understanding their hidden relationships continues to be a research focus. The main challenges lie in effectively modeling the complex interactions…
Translating NIR to the visible spectrum is challenging due to cross-domain complexities. Current models struggle to balance a broad receptive field with computational efficiency, limiting practical use. Although the Selective Structured…
Deep unfolding methods have made impressive progress in restoring 3D hyperspectral images (HSIs) from 2D measurements through convolution neural networks or Transformers in spectral compressive imaging. However, they cannot efficiently…
Semantic segmentation of multi-source remote sensing images is a fundamental task for Earth observation applications. Existing methods often struggle with insufficient multi-scale context modeling and suboptimal cross-modal feature fusion,…
Mainstream approaches to spectral reconstruction (SR) primarily focus on designing Convolution- and Transformer-based architectures. However, CNN methods often face challenges in handling long-range dependencies, whereas Transformers are…
Medical Hyperspectral Imaging (MHSI) offers potential for computational pathology and precision medicine. However, existing CNN and Transformer struggle to balance segmentation accuracy and speed due to high spatial-spectral dimensionality.…
Selective state space models (SSMs), such as Mamba, highly excel at capturing long-range dependencies in 1D sequential data, while their applications to 2D vision tasks still face challenges. Current visual SSMs often convert images into 1D…
Snapshot Compressive Imaging (SCI) enables fast spectral imaging but requires effective decoding algorithms for hyperspectral image (HSI) reconstruction from compressed measurements. Current CNN-based methods are limited in modeling…
Transformers have become increasingly popular for image super-resolution (SR) tasks due to their strong global context modeling capabilities. However, their quadratic computational complexity necessitates the use of window-based attention…