相关论文: TrackingMiM: Efficient Mamba-in-Mamba Serializatio…

Perceptual image compression focuses on preserving high visual quality under low-bitrate constraints. Most existing approaches to perceptual compression leverage the strong generative capabilities of generative adversarial networks or…

Efficiency has been a critical problem in UAV tracking due to limitations in computation resources, battery capacity, and unmanned aerial vehicle maximum load. Although discriminative correlation filters (DCF)-based trackers prevail in this…

State space models (SSMs), such as Mamba, have emerged as an efficient alternative to transformers for long-context sequence modeling. However, despite their growing adoption, SSMs lack the interpretability tools that have been crucial for…

Video super-resolution remains a major challenge in low-level vision tasks. To date, CNN- and Transformer-based methods have delivered impressive results. However, CNNs are limited by local receptive fields, while Transformers struggle with…

Linear State Space Models (SSMs) offer remarkable performance gains in efficient sequence modeling, with constant inference-time computation and memory complexity. Recent advances, such as Mamba, further enhance SSMs with input-dependent…

The rapid growth of long-duration, high-definition videos has made efficient video quality assessment (VQA) a critical challenge. Existing research typically tackles this problem through two main strategies: reducing model parameters and…

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.…

Foundation models refer to deep learning models pretrained on large unlabeled datasets through self-supervised algorithms. In the Earth science and remote sensing communities, there is growing interest in transforming the use of Earth…

Training urban spatio-temporal foundation models that generalize well across diverse regions and cities is critical for deploying urban services in unseen or data-scarce regions. Recent studies have typically focused on fusing cross-domain…

Robot grasping, whether handling isolated objects, cluttered items, or stacked objects, plays a critical role in industrial and service applications. However, current visual grasp detection methods based on Convolutional Neural Networks…

Multi-modal learning that combines pathological images with genomic data has significantly enhanced the accuracy of survival prediction. Nevertheless, existing methods have not fully utilized the inherent hierarchical structure within both…

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…

Skeleton Action Recognition (SAR) involves identifying human actions using skeletal joint coordinates and their interconnections. While plain Transformers have been attempted for this task, they still fall short compared to the current…

State space models (SSMs) have emerged as an efficient alternative to transformer-based models, offering linear complexity that scales better than transformers. One of the latest advances in SSMs, Mamba, introduces a selective scan…

The Mamba-based image restoration backbones have recently demonstrated significant potential in balancing global reception and computational efficiency. However, the inherent causal modeling limitation of Mamba, where each token depends…

Dynamic graph embedding has emerged as an important technique for modeling complex time-evolving networks across diverse domains. While transformer-based models have shown promise in capturing long-range dependencies in temporal graph data,…

3D visual perception tasks, such as 3D detection from multi-camera images, are essential components of autonomous driving and assistance systems. However, designing computationally efficient methods remains a significant challenge. In this…

The advent of Transformer and Mamba-based architectures has significantly advanced 3D medical image segmentation by enabling global contextual modeling, a capability traditionally limited in Convolutional Neural Networks (CNNs). However,…

Image generation models have encountered challenges related to scalability and quadratic complexity, primarily due to the reliance on Transformer-based backbones. In this study, we introduce MaskMamba, a novel hybrid model that combines…

Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. Many subquadratic-time architectures such as linear attention,…