Related papers: A Structure-aware and Motion-adaptive Framework fo…

Existing monocular 3D pose estimation methods primarily rely on joint positional features, while overlooking intrinsic directional and angular correlations within the skeleton. As a result, they often produce implausible poses under joint…

Multi-modal data fusion has recently been shown promise in classification tasks in remote sensing. Optical data and radar data, two important yet intrinsically different data sources, are attracting more and more attention for potential…

State Space Models (SSMs) have emerged as a powerful and efficient alternative to Transformers, demonstrating linear-time complexity and exceptional sequence modeling capabilities. However, their application to vision tasks remains…

Driven by the rapid development of deep learning technology, the YOLO series has set a new benchmark for real-time object detectors. Additionally, transformer-based structures have emerged as the most powerful solution in the field, greatly…

Existing salient object detection (SOD) models are generally constrained by the limited receptive fields of convolutional neural networks (CNNs) and quadratic computational complexity of Transformers. Recently, the emerging state-space…

Regression based methods are not performing as well as detection based methods for human pose estimation. A central problem is that the structural information in the pose is not well exploited in the previous regression methods. In this…

State space models (SSMs) have emerged as a powerful paradigm for efficient single-image super-resolution (SR) due to their linear complexity and long-range modeling capabilities. However, existing Mamba-based methods typically rely on…

Despite the recent success of Multimodal Foundation Models (FMs), their reliance on massive paired datasets limits their applicability in low-data and rare-scenario settings where aligned data is scarce and expensive. A key bottleneck is…

State Space Models (SSMs) show significant potential for long-sequence modeling, but their reliance on input order conflicts with the irregular nature of point clouds. Existing approaches often rely on predefined serialization schemes whose…

Multimodal image fusion aims to integrate information from different imaging techniques to produce a comprehensive, detail-rich single image for downstream vision tasks. Existing methods based on local convolutional neural networks (CNNs)…

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…

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…

Human engagement estimation in conversational scenarios is essential for applications such as adaptive tutoring, remote healthcare assessment, and socially aware human--computer interaction. Engagement is a dynamic, multimodal signal…

Recent advancements in transformers, specifically self-attention mechanisms, have significantly improved hyperspectral image (HSI) classification. However, these models often suffer from inefficiencies, as their computational complexity…

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…

Human pose forecasting is a challenging problem involving complex human body motion and posture dynamics. In cases that there are multiple people in the environment, one's motion may also be influenced by the motion and dynamic movements of…

Motion planning is a challenging task to generate safe and feasible trajectories in highly dynamic and complex environments, forming a core capability for autonomous vehicles. In this paper, we propose DRAMA, the first Mamba-based…

Learned Image Compression (LIC) has explored various architectures, such as Convolutional Neural Networks (CNNs) and transformers, in modeling image content distributions in order to achieve compression effectiveness. However, achieving…

Action coordination in human structure is indispensable for the spatial constraints of 2D joints to recover 3D pose. Usually, action coordination is represented as a long-range dependence among body parts. However, there are two main…

In the era of large-scale pre-trained models, effectively adapting general knowledge to specific affective computing tasks remains a challenge, particularly regarding computational efficiency and multimodal heterogeneity. While…