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

Selective state space models (SSMs), such as Mamba, highly excel at capturing long-range dependencies in 1D sequential data, while their applications to 2D vision tasks still face challenges. Current visual SSMs often convert images into 1D…

Diffusion models have demonstrated strong capabilities in generating high-fidelity 3D human poses, yet their iterative nature and multi-hypothesis requirements incur substantial computational cost. In this paper, we propose an Efficient…

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,…

Multi-view depth estimation has achieved impressive performance over various benchmarks. However, almost all current multi-view systems rely on given ideal camera poses, which are unavailable in many real-world scenarios, such as autonomous…

In recent years, robust matching methods using deep learning-based approaches have been actively studied and improved in computer vision tasks. However, there remains a persistent demand for both robust and fast matching techniques. To…

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)…

The accelerated MRI reconstruction poses a challenging ill-posed inverse problem due to the significant undersampling in k-space. Deep neural networks, such as CNNs and ViTs, have shown substantial performance improvements for this task…

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…

Point cloud completion aims to generate a complete and high-fidelity point cloud from an initially incomplete and low-quality input. A prevalent strategy involves leveraging Transformer-based models to encode global features and facilitate…

In this paper, we propose an efficient human pose estimation network -- SFM (slender fusion model) by fusing multi-level features and adding lightweight attention blocks -- HSA (High-Level Spatial Attention). Many existing methods on…

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),…

Human motion generation stands as a significant pursuit in generative computer vision, while achieving long-sequence and efficient motion generation remains challenging. Recent advancements in state space models (SSMs), notably Mamba, have…

Molecular representation learning, a cornerstone for downstream tasks like molecular captioning and molecular property prediction, heavily relies on Graph Neural Networks (GNN). However, GNN suffers from the over-smoothing problem, where…

In the field of 3D Human Pose Estimation (HPE), accurately estimating human pose, especially in scenarios with occlusions, is a significant challenge. This work identifies and addresses a gap in the current state of the art in 3D HPE…

The graph convolutional networks (GCNs) have been applied to model the physically connected and non-local relations among human joints for 3D human pose estimation (HPE). In addition, the purely Transformer-based models recently show…

Point cloud segmentation is an important topic in 3D understanding that has traditionally has been tackled using either the CNN or Transformer. Recently, Mamba has emerged as a promising alternative, offering efficient long-range contextual…

Joint compression of point cloud geometry and attributes is essential for efficient 3D data representation. Existing methods often rely on post-hoc recoloring procedures and manually tuned bitrate allocation between geometry and attribute…

2D-to-3D human pose lifting is a fundamental challenge for 3D human pose estimation in monocular video, where graph convolutional networks (GCNs) and attention mechanisms have proven to be inherently suitable for encoding the…

Real-time 2D keypoint detection plays an essential role in computer vision. Although CNN-based and Transformer-based methods have achieved breakthrough progress, they often fail to deliver superior performance and real-time speed. This…

Hyperspectral image (HSI) classification constitutes the fundamental research in remote sensing fields. Convolutional Neural Networks (CNNs) and Transformers have demonstrated impressive capability in capturing spectral-spatial contextual…