Related papers: Fore-Mamba3D: Mamba-based Foreground-Enhanced Enco…
Modeling high-resolution spatiotemporal representations, including both global dynamic contexts (e.g., holistic human motion tendencies) and local motion details (e.g., high-frequency changes of keypoints), is essential for video-based…
Point cloud videos can faithfully capture real-world spatial geometries and temporal dynamics, which are essential for enabling intelligent agents to understand the dynamically changing world. However, designing an effective 4D backbone…
Mamba-based architectures have shown to be a promising new direction for deep learning models owing to their competitive performance and sub-quadratic deployment speed. However, current Mamba multi-modal large language models (MLLM) are…
We present PlainMamba: a simple non-hierarchical state space model (SSM) designed for general visual recognition. The recent Mamba model has shown how SSMs can be highly competitive with other architectures on sequential data and initial…
Recently, the Mamba architecture based on state space models has demonstrated remarkable performance in a series of natural language processing tasks and has been rapidly applied to remote sensing change detection (CD) tasks. However, most…
Recent Mamba-based architectures for video understanding demonstrate promising computational efficiency and competitive performance, yet struggle with overfitting issues that hinder their scalability. To overcome this challenge, we…
Restoration and enhancement are essential for improving the quality of videos captured under atmospheric turbulence conditions, aiding visualization, object detection, classification, and tracking in surveillance systems. In this paper, we…
Transformer-based segmentation methods face the challenge of efficient inference when dealing with high-resolution images. Recently, several linear attention architectures, such as Mamba and RWKV, have attracted much attention as they can…
Single-modal object detection tasks often experience performance degradation when encountering diverse scenarios. In contrast, multimodal object detection tasks can offer more comprehensive information about object features by integrating…
Selective state space models (SSMs) represented by Mamba have demonstrated their computational efficiency and promising outcomes in various tasks, including automatic speech recognition (ASR). Mamba has been applied to ASR task with the…
Multi-source remote sensing enables complementary observation of ground objects, while cross-modal fine-grained object retrieval remains challenging, especially under unaligned optical and SAR conditions. Unlike conventional retrieval…
Mamba-based vision models have gained extensive attention as a result of being computationally more efficient than attention-based models. However, spatial redundancy still exists in these models, represented by token and block redundancy.…
The Detection of small objects, especially traffic signs, is a critical sub-task in object detection and autonomous driving. Despite signficant progress in previous research, two main challenges remain. First, the issue of feature…
Accurate building segmentation and height estimation from single-view RGB satellite imagery are fundamental for urban analytics, yet remain ill-posed due to structural variability and the high computational cost of global context modeling.…
The purpose of RGB-D Salient Object Detection (SOD) is to pinpoint the most visually conspicuous areas within images accurately. While conventional deep models heavily rely on CNN extractors and overlook the long-range contextual…
Deep Learning based Weather Prediction (DLWP) models have been improving rapidly over the last few years, surpassing state of the art numerical weather forecasts by significant margins. While much of the optimization effort is focused on…
Recently, Mamba-based methods, with its advantage in long-range information modeling and linear complexity, have shown great potential in optimizing both computational cost and performance of light field image super-resolution (LFSR).…
Video anomaly detection (VAD) has been extensively researched due to its potential for intelligent video systems. However, most existing methods based on CNNs and transformers still suffer from substantial computational burdens and have…
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…
Brain lesion segmentation remains challenging due to small, low-contrast lesions, anisotropic sampling, and cross-slice discontinuities. We propose CenterMamba-SAM, an end-to-end framework that freezes a pretrained backbone and trains only…