English
Related papers

Related papers: Dual-stream Spatio-Temporal GCN-Transformer Networ…

200 papers

Modern multi-layer perceptron (MLP) models have shown competitive results in learning visual representations without self-attention. However, existing MLP models are not good at capturing local details and lack prior knowledge of human body…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Wenhao Li , Mengyuan Liu , Hong Liu , Tianyu Guo , Ti Wang , Hao Tang , Nicu Sebe

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…

Computer Vision and Pattern Recognition · Computer Science 2022-12-14 Soubarna Banik , Alejandro Mendoza Gracia , Alois Knoll

Various deep learning techniques have been proposed to solve the single-view 2D-to-3D pose estimation problem. While the average prediction accuracy has been improved significantly over the years, the performance on hard poses with depth…

Computer Vision and Pattern Recognition · Computer Science 2021-08-18 Ailing Zeng , Xiao Sun , Lei Yang , Nanxuan Zhao , Minhao Liu , Qiang Xu

Several methods have been proposed to estimate 3D human pose from multi-view images, achieving satisfactory performance on public datasets collected under relatively simple conditions. However, there are limited approaches studying…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Zhiyu Pan , Zhicheng Zhong , Wenxuan Guo , Yifan Chen , Jianjiang Feng , Jie Zhou

Recently, vision transformers have shown great success in a set of human reconstruction tasks such as 2D human pose estimation (2D HPE), 3D human pose estimation (3D HPE), and human mesh reconstruction (HMR) tasks. In these tasks, feature…

Computer Vision and Pattern Recognition · Computer Science 2023-03-24 Ce Zheng , Matias Mendieta , Taojiannan Yang , Guo-Jun Qi , Chen Chen

To achieve more accurate 2D human pose estimation, we extend the successful encoder-decoder network, simple baseline network (SBN), in three ways. To reduce the quantization errors caused by the large output stride size, two more decoder…

Computer Vision and Pattern Recognition · Computer Science 2021-06-02 Jie Ou , Mingjian Chen , Hong Wu

Realistic reconstruction of two hands interacting with objects is a new and challenging problem that is essential for building personalized Virtual and Augmented Reality environments. Graph Convolutional networks (GCNs) allow for the…

Computer Vision and Pattern Recognition · Computer Science 2022-10-26 Ahmed Tawfik Aboukhadra , Jameel Malik , Ahmed Elhayek , Nadia Robertini , Didier Stricker

We propose a novel attention-based 2D-to-3D pose estimation network for graph-structured data, named KOG-Transformer, and a 3D pose-to-shape estimation network for hand data, named GASE-Net. Previous 3D pose estimation methods have focused…

Computer Vision and Pattern Recognition · Computer Science 2022-09-27 Weixi Zhao , Weiqiang Wang

Multi-person pose understanding from RGB videos involves three complex tasks: pose estimation, tracking and motion forecasting. Intuitively, accurate multi-person pose estimation facilitates robust tracking, and robust tracking builds…

Computer Vision and Pattern Recognition · Computer Science 2023-09-14 Shihao Zou , Yuanlu Xu , Chao Li , Lingni Ma , Li Cheng , Minh Vo

Human pose estimation aims at localizing human anatomical keypoints or body parts in the input data (e.g., images, videos, or signals). It forms a crucial component in enabling machines to have an insightful understanding of the behaviors…

Computer Vision and Pattern Recognition · Computer Science 2022-04-18 Haoming Chen , Runyang Feng , Sifan Wu , Hao Xu , Fengcheng Zhou , Zhenguang Liu

Reconstructing multi-human body mesh from a single monocular image is an important but challenging computer vision problem. In addition to the individual body mesh models, we need to estimate relative 3D positions among subjects to generate…

Computer Vision and Pattern Recognition · Computer Science 2023-07-25 Chenyan Wu , Yandong Li , Xianfeng Tang , James Wang

We propose a transformer-based neural network architecture for multi-object 3D reconstruction from RGB videos. It relies on two alternative ways to represent its knowledge: as a global 3D grid of features and an array of view-specific 2D…

Computer Vision and Pattern Recognition · Computer Science 2022-08-29 Michał J. Tyszkiewicz , Kevis-Kokitsi Maninis , Stefan Popov , Vittorio Ferrari

Graph convolutional networks (GCNs) have emerged as dominant methods for skeleton-based action recognition. However, they still suffer from two problems, namely, neighborhood constraints and entangled spatiotemporal feature representations.…

Computer Vision and Pattern Recognition · Computer Science 2022-01-11 Ruwen Bai , Min Li , Bo Meng , Fengfa Li , Miao Jiang , Junxing Ren , Degang Sun

Convolution neural networks (CNNs) have succeeded in compressive image sensing. However, due to the inductive bias of locality and weight sharing, the convolution operations demonstrate the intrinsic limitations in modeling the long-range…

Image and Video Processing · Electrical Eng. & Systems 2022-01-03 Dongjie Ye , Zhangkai Ni , Hanli Wang , Jian Zhang , Shiqi Wang , Sam Kwong

Graph convolutional networks (GCNs) achieved promising performance in skeleton-based human action recognition by modeling a sequence of skeletons as a spatio-temporal graph. Most of the recently proposed GCN-based methods improve the…

Computer Vision and Pattern Recognition · Computer Science 2021-04-23 Negar Heidari , Alexandros Iosifidis

We propose a new learning-based method for estimating 2D human pose from a single image, using Dual-Source Deep Convolutional Neural Networks (DS-CNN). Recently, many methods have been developed to estimate human pose by using pose priors…

Computer Vision and Pattern Recognition · Computer Science 2015-04-28 Xiaochuan Fan , Kang Zheng , Yuewei Lin , Song Wang

Graph Convolutional Networks (GCNs) have been widely used in skeleton-based human action recognition. In GCN-based methods, the spatio-temporal graph is fundamental for capturing motion patterns. However, existing approaches ignore the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-25 Chang Li , Qian Huang , Yingchi Mao

Monocular 3D human pose estimation (HPE) often encounters challenges such as depth ambiguity and occlusion during the 2D-to-3D lifting process. Additionally, traditional methods may overlook multi-scale skeleton features when utilizing…

Computer Vision and Pattern Recognition · Computer Science 2025-08-21 Bing Han , Yuhua Huang , Pan Gao

Previous video-based human pose estimation methods have shown promising results by leveraging aggregated features of consecutive frames. However, most approaches compromise accuracy to mitigate jitter or do not sufficiently comprehend the…

Computer Vision and Pattern Recognition · Computer Science 2022-11-30 Kyung-Min Jin , Byoung-Sung Lim , Gun-Hee Lee , Tae-Kyung Kang , Seong-Whan Lee

Human pose assessment and correction play a crucial role in applications across various fields, including computer vision, robotics, sports analysis, healthcare, and entertainment. In this paper, we propose a Spatial-Temporal Transformer…

Computer Vision and Pattern Recognition · Computer Science 2023-11-02 Wenyang Hu , Kai Liu , Libin Liu , Huiliang Shang