Related papers: V2M: Visual 2-Dimensional Mamba for Image Represen…

We introduce a novel state-space architecture for diffusion models, effectively harnessing spatial and frequency information to enhance the inductive bias towards local features in input images for image generation tasks. While state-space…

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…

State Space Models (SSMs) like Mamba2 are a promising alternative to Transformers, with faster theoretical training and inference times -- especially for long context lengths. Recent work on Matryoshka Representation Learning -- and its…

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…

A fundamental objective in robot manipulation is to enable models to comprehend visual scenes and execute actions. Although existing Vision-Language-Action (VLA) models for robots can handle a range of basic tasks, they still face…

Mamba is emerging as a novel approach to overcome the challenges faced by Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) in computer vision. While CNNs excel at extracting local features, they often struggle to capture…

Medical video segmentation gains increasing attention in clinical practice due to the redundant dynamic references in video frames. However, traditional convolutional neural networks have a limited receptive field and transformer-based…

We propose a novel hybrid Mamba-Transformer backbone, MambaVision, specifically tailored for vision applications. Our core contribution includes redesigning the Mamba formulation to enhance its capability for efficient modeling of visual…

Video anomaly detection (VAD) is an essential task in the image processing community with prospects in video surveillance, which faces fundamental challenges in balancing detection accuracy with computational efficiency. As video content…

Attention-based methods have demonstrated exceptional performance in modelling long-range dependencies on spherical cortical surfaces, surpassing traditional Geometric Deep Learning (GDL) models. However, their extensive inference time and…

Sequence modeling plays a vital role across various domains, with recurrent neural networks being historically the predominant method of performing these tasks. However, the emergence of transformers has altered this paradigm due to their…

Recent advances in LiDAR 3D detection have demonstrated the effectiveness of Transformer-based frameworks in capturing the global dependencies from point cloud spaces, which serialize the 3D voxels into the flattened 1D sequence for…

Vision Mambas (ViMs) achieve remarkable success with sub-quadratic complexity, but their efficiency remains constrained by quadratic token scaling with image resolution. While existing methods address token redundancy, they overlook ViMs'…

Existing Transformer-based models for point cloud analysis suffer from quadratic complexity, leading to compromised point cloud resolution and information loss. In contrast, the newly proposed Mamba model, based on state space models (SSM),…

Scene flow estimation aims to predict 3D motion from consecutive point cloud frames, which is of great interest in autonomous driving field. Existing methods face challenges such as insufficient spatio-temporal modeling and inherent loss of…

Mamba has demonstrated exceptional performance in visual tasks due to its powerful global modeling capabilities and linear computational complexity, offering considerable potential in hyperspectral image super-resolution (HSISR). However,…

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…

Vision state space models inherit the efficiency and long-range modeling ability of Mamba-style selective scans. However, their performance depends critically on the representation of two-dimensional visual features as one-dimensional token…

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…

Recurrent neural networks and Transformers have recently dominated most applications in hyperspectral (HS) imaging, owing to their capability to capture long-range dependencies from spectrum sequences. However, despite the success of these…