Related papers: Pose Magic: Efficient and Temporally Consistent Hu…

The Transformer architecture has shown a remarkable ability in modeling global relationships. However, it poses a significant computational challenge when processing high-dimensional medical images. This hinders its development and…

State Space Models (SSM), such as Mamba, have shown strong representation ability in modeling long-range dependency with linear complexity, achieving successful applications from high-level to low-level vision tasks. However, SSM's…

Achieving both high accuracy and topological continuity in road segmentation from satellite imagery is a critical goal for applications ranging from urban planning to disaster response. State-of-the-art methods often rely on Vision…

In recent years, 2D-to-3D pose uplifting in monocular 3D Human Pose Estimation (HPE) has attracted widespread research interest. GNN-based methods and Transformer-based methods have become mainstream architectures due to their advanced…

Multimodal medical image fusion integrates complementary information from different imaging modalities to enhance diagnostic accuracy and treatment planning. While deep learning methods have advanced performance, existing approaches face…

Convolutional neural networks and Transformer have made significant progresses in multi-modality medical image super-resolution. However, these methods either have a fixed receptive field for local learning or significant computational…

Many few-shot segmentation (FSS) methods use cross attention to fuse support foreground (FG) into query features, regardless of the quadratic complexity. A recent advance Mamba can also well capture intra-sequence dependencies, yet the…

Accurate 3D human pose estimation from monocular videos requires effective modelling of complex spatial and temporal dependencies. However, existing methods often face challenges in efficiency and adaptability when modelling spatial and…

Remote sensing image fusion aims to generate a high-resolution multi/hyper-spectral image by combining a high-resolution image with limited spectral data and a low-resolution image rich in spectral information. Current deep learning (DL)…

The goal of 2D human pose estimation (HPE) is to localize anatomical landmarks, given an image of a person in a pose. SOTA techniques make use of thousands of labeled figures (finetuning transformers or training deep CNNs), acquired using…

Estimating human dance motion is a challenging task with various industrial applications. Recently, many efforts have focused on predicting human dance motion using either egocentric video or music as input. However, the task of jointly…

Transformers have demonstrated impressive results for 3D point cloud semantic segmentation. However, the quadratic complexity of transformer makes computation costs high, limiting the number of points that can be processed simultaneously…

Next Point-of-Interest (POI) recommendation is a critical task in location-based services, yet it faces the fundamental challenge of coupled spatiotemporal asymmetry inherent in urban mobility. Specifically, transition intents between…

Hybrid Mamba-Transformer networks have recently garnered broad attention. These networks can leverage the scalability of Transformers while capitalizing on Mamba's strengths in long-context modeling and computational efficiency. However,…

We explore 3D human pose estimation from a single RGB image. While many approaches try to directly predict 3D pose from image measurements, we explore a simple architecture that reasons through intermediate 2D pose predictions. Our approach…

Partial differential equations (PDEs) are widely used to model complex physical systems, but solving them efficiently remains a significant challenge. Recently, Transformers have emerged as the preferred architecture for PDEs due to their…

The basic body shape (i.e., the body shape in T-pose) of a person does not change within a single video. However, most SOTA human mesh estimation (HME) models output a slightly different, thus inconsistent basic body shape for each video…

Task failures in prior fine-grained robotic manipulation methods often stem from suboptimal initial grasping, which is critical for subsequent manipulation and reducing the requirement for complex pose adjustments. To address this, we…

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.…

Applying pre-trained models to assist point cloud understanding has recently become a mainstream paradigm in 3D perception. However, existing application strategies are straightforward, utilizing only the final output of the pre-trained…