Related papers: Surface Vision Mamba: Leveraging Bidirectional Sta…

Recent advancements in State Space Models, notably Mamba, have demonstrated superior performance over the dominant Transformer models, particularly in reducing the computational complexity from quadratic to linear. Yet, difficulties in…

Multi-modal semantic segmentation significantly enhances AI agents' perception and scene understanding, especially under adverse conditions like low-light or overexposed environments. Leveraging additional modalities (X-modality) like…

Convolutional Neural Networks (CNNs) and Transformer-based self-attention models have become the standard for medical image segmentation. This paper demonstrates that convolution and self-attention, while widely used, are not the only…

Mamba has recently gained widespread attention as a backbone model for point cloud modeling, leveraging a state-space architecture that enables efficient global sequence modeling with linear complexity. However, its lack of local inductive…

The rapid advances in deep learning have significantly enhanced the accuracy of multimodal 3D human pose estimation (HPE). However, the state-of-the-art (SOTA) HPE pipelines still rely on Transformers, whose quadratic complexity makes…

Pathological diagnosis is highly reliant on image analysis, where Regions of Interest (ROIs) serve as the primary basis for diagnostic evidence, while whole-slide image (WSI)-level tasks primarily capture aggregated patterns. To extract…

Recent efforts on image restoration have focused on developing "all-in-one" models that can handle different degradation types and levels within single model. However, most of mainstream Transformer-based ones confronted with dilemma…

Abnormality detection in medical imaging is a critical task requiring both high efficiency and accuracy to support effective diagnosis. While convolutional neural networks (CNNs) and Transformer-based models are widely used, both face…

State-Space Models (SSMs) have emerged as an efficient alternative to transformers, yet existing visual SSMs retain deeply ingrained biases from their origins in natural language processing. In this paper, we address these limitations by…

In the field of medical image segmentation, models based on both CNN and Transformer have been thoroughly investigated. However, CNNs have limited modeling capabilities for long-range dependencies, making it challenging to exploit the…

Prior efforts in light-weight model development mainly centered on CNN and Transformer-based designs yet faced persistent challenges. CNNs adept at local feature extraction compromise resolution while Transformers offer global reach but…

Point cloud segmentation is an important topic in 3D understanding that has traditionally has been tackled using either the CNN or Transformer. Recently, Mamba has emerged as a promising alternative, offering efficient long-range contextual…

Land cover analysis using hyperspectral images (HSI) remains an open problem due to their low spatial resolution and complex spectral information. Recent studies are primarily dedicated to designing Transformer-based architectures for…

With intelligent room-side sensing and service robots widely deployed, human motion prediction (HMP) is essential for safe, proactive assistance. However, many existing HMP methods either produce a single, deterministic forecast that…

RGB-D salient object detection (SOD) aims to identify the most conspicuous objects in a scene with the incorporation of depth cues. Existing methods mainly rely on CNNs, limited by the local receptive fields, or Vision Transformers that…

The problem of imputing multivariate time series spans a wide range of fields, from clinical healthcare to multi-sensor systems. Initially, Recurrent Neural Networks (RNNs) were employed for this task; however, their error accumulation…

Effectively modeling global context information in hyperspectral image (HSI) denoising is crucial, but prevailing methods using convolution or transformers still face localized or computational efficiency limitations. Inspired by the…

Reconstructing degraded images is a critical task in image processing. Although CNN and Transformer-based models are prevalent in this field, they exhibit inherent limitations, such as inadequate long-range dependency modeling and high…

Motion forecasting is a crucial component of autonomous driving systems, enabling the generation of accurate and smooth future trajectories to ensure safe navigation to the destination. In previous methods, potential future trajectories are…

In this work, we propose an accurate and real-time optical flow and disparity estimation model by fusing pairwise input images in the proposed non-causal selective state space for dense perception tasks. We propose a non-causal Mamba…