Related papers: GRAM-MAMBA: Holistic Feature Alignment for Wireles…
Convolutional neural networks and Transformer have made significant progresses in multi-modality medical image super-resolution. However, these methods either have a fixed receptive field for local learning or significant computational…
Time series classification (TSC) is crucial in numerous real-world applications, such as environmental monitoring, medical diagnosis, and posture recognition. TSC tasks require models to effectively capture discriminative information for…
To address complex pathological feature extraction in automated cardiac MRI segmentation, we propose SAMba-UNet, a novel dual-encoder architecture that synergistically combines the vision foundation model SAM2, the linear-complexity…
Efficient extraction of spectral sequences and geospatial information has always been a hot topic in hyperspectral image classification. In terms of spectral sequence feature capture, RNN and Transformer have become mainstream…
With the breakthrough of Transformer-based pre-trained models, the demand for fine-tuning (FT) to adapt the base pre-trained models to downstream applications continues to grow, so it is essential for service providers to reduce the cost of…
Whole slide image (WSI) analysis heavily relies on multiple instance learning (MIL). While recent methods benefit from large-scale foundation models and advanced sequence modeling to capture long-range dependencies, they still struggle with…
State-space modeling has emerged as a powerful paradigm for sequence analysis in various tasks such as natural language processing, time-series forecasting, and signal processing. In this work, we propose an \emph{Adaptive State-Space…
Effectively integrating molecular graph structures with Large Language Models (LLMs) is a key challenge in drug discovery. Most existing multi-modal alignment methods typically process these structures by fine-tuning the LLM or adding a…
Multimodal Image Fusion (MMIF) integrates complementary information from various modalities to produce clearer and more informative fused images. MMIF under adverse weather is particularly crucial in autonomous driving and UAV monitoring…
Medical time series are central to healthcare, enabling continuous monitoring and supporting timely clinical decisions. Despite recent progress, existing methods struggle to jointly model local-global dynamics and handle nonstationarities…
Remote sensing change detection is vital for monitoring environmental and urban transformations but faces challenges like manual feature extraction and sensitivity to noise. Traditional methods and early deep learning models, such as…
Deep learning techniques have revolutionized the infrared and visible image fusion (IVIF), showing remarkable efficacy on complex scenarios. However, current methods do not fully combine frequency domain features with global semantic…
Deep visual odometry has demonstrated great advancements by learning-to-optimize technology. This approach heavily relies on the visual matching across frames. However, ambiguous matching in challenging scenarios leads to significant errors…
Most pattern recognition models are developed on pre-proce\-ssed data. In computer vision, for instance, RGB images processed through image signal processing (ISP) pipelines designed to cater to human perception are the most frequent input…
Multicategory remote object counting is a fundamental task in computer vision, aimed at accurately estimating the number of objects of various categories in remote images. Existing methods rely on CNNs and Transformers, but CNNs struggle to…
Recent Mamba-based methods for the pose-lifting task tend to model joint dependencies by 2D-to-1D mapping with diverse scanning strategies. Though effective, they struggle to model intricate joint connections and uniformly process all joint…
Incomplete multi-modal emotion recognition (IMER) aims at understanding human intentions and sentiments by comprehensively exploring the partially observed multi-source data. Although the multi-modal data is expected to provide more…
Recently, the state space model (SSM) represented by Mamba has shown remarkable performance in long-term sequence modeling tasks, including speech enhancement. However, due to substantial differences in sub-band features, applying the same…
The advent of single-cell multi-omics technologies has enabled the simultaneous profiling of diverse omics layers within individual cells. Integrating such multimodal data provides unprecedented insights into cellular identity, regulatory…
Recent advances in deep learning have made it possible to predict phenotypic measures directly from functional magnetic resonance imaging (fMRI) brain volumes, sparking significant interest in the neuroimaging community. However, existing…