Related papers: Graph and Skipped Transformer: Exploiting Spatial …

Pedestrian trajectory prediction aims to forecast future movements based on historical paths. Spatial-temporal (ST) methods often separately model spatial interactions among pedestrians and temporal dependencies of individuals. They…

We present EgoPoseFormer, a simple yet effective transformer-based model for stereo egocentric human pose estimation. The main challenge in egocentric pose estimation is overcoming joint invisibility, which is caused by self-occlusion or a…

3D human pose estimation is a difficult task, due to challenges such as occluded body parts and ambiguous poses. Graph convolutional networks encode the structural information of the human skeleton in the form of an adjacency matrix, which…

Human pose estimation (HPE) has attracted a significant amount of attention from the computer vision community in the past decades. Moreover, HPE has been applied to various domains, such as human-computer interaction, sports analysis, and…

Radar-based indoor 3D human pose estimation typically relied on fine-grained 3D keypoint labels, which are costly to obtain especially in complex indoor settings involving clutter, occlusions, or multiple people. In this paper, we propose…

Dynamic graph embedding has emerged as a very effective technique for addressing diverse temporal graph analytic tasks (i.e., link prediction, node classification, recommender systems, anomaly detection, and graph generation) in various…

Recent years have witnessed the emerging success of graph neural networks (GNNs) for modeling structured data. However, most GNNs are designed for homogeneous graphs, in which all nodes and edges belong to the same types, making them…

We present a deployment friendly, fast bottom-up framework for multi-person 3D human pose estimation. We adopt a novel neural representation of multi-person 3D pose which unifies the position of person instances with their corresponding 3D…

This paper presents a novel Kinematics and Trajectory Prior Knowledge-Enhanced Transformer (KTPFormer), which overcomes the weakness in existing transformer-based methods for 3D human pose estimation that the derivation of Q, K, V vectors…

In the field of 3D Human Pose Estimation from monocular videos, the presence of diverse occlusion types presents a formidable challenge. Prior research has made progress by harnessing spatial and temporal cues to infer 3D poses from 2D…

Estimating 3D poses from a monocular video is still a challenging task, despite the significant progress that has been made in recent years. Generally, the performance of existing methods drops when the target person is too small/large, or…

Polygonal meshes have become the standard for discretely approximating 3D shapes, thanks to their efficiency and high flexibility in capturing non-uniform shapes. This non-uniformity, however, leads to irregularity in the mesh structure,…

Graph-based next-step prediction models have recently been very successful in modeling complex high-dimensional physical systems on irregular meshes. However, due to their short temporal attention span, these models suffer from error…

The most commonly used method for addressing 3D geometric registration is the iterative closet-point algorithm, this approach is incremental and prone to drift over multiple consecutive frames. The Common strategy to address the drift is…

3D human pose estimation is fundamental to understanding human behavior. Recently, promising results have been achieved by graph convolutional networks (GCNs), which achieve state-of-the-art performance and provide rather light-weight…

Transformer-based 3D human pose estimation methods suffer from high computational costs due to the quadratic complexity of self-attention with respect to sequence length. Additionally, pose sequences often contain significant redundancy…

Graph convolutional networks (GCNs) are widely used for 3D hand pose estimation, where the hand skeleton is encoded as a fixed adjacency graph. We revisit whether this is the most effective way to incorporate hand topology in 2D-to-3D…

Existing lifting networks for regressing 3D human poses from 2D single-view poses are typically constructed with linear layers based on graph-structured representation learning. In sharp contrast to them, this paper presents Grid…

Multi-person pose estimation generally follows top-down and bottom-up paradigms. Both of them use an extra stage ($\boldsymbol{e.g.,}$ human detection in top-down paradigm or grouping process in bottom-up paradigm) to build the relationship…

Discrete-Time Dynamic Graphs (DTDGs), which are prevalent in real-world implementations and notable for their ease of data acquisition, have garnered considerable attention from both academic researchers and industry practitioners. The…