English
Related papers

Related papers: A Graph Attention Spatio-temporal Convolutional Ne…

200 papers

Recovering 3D human pose from 2D joints is a highly unconstrained problem. We propose a novel neural network framework, PoseNet3D, that takes 2D joints as input and outputs 3D skeletons and SMPL body model parameters. By casting our…

Computer Vision and Pattern Recognition · Computer Science 2020-11-13 Shashank Tripathi , Siddhant Ranade , Ambrish Tyagi , Amit Agrawal

Graph convolutional networks (GCNs) have been widely used and achieved remarkable results in skeleton-based action recognition. We think the key to skeleton-based action recognition is a skeleton hanging in frames, so we focus on how the…

Computer Vision and Pattern Recognition · Computer Science 2023-12-07 Nguyen Huu Bao Long

3D Convolutional Neural Network (3D CNN) captures spatial and temporal information on 3D data such as video sequences. However, due to the convolution and pooling mechanism, the information loss seems unavoidable. To improve the visual…

Computer Vision and Pattern Recognition · Computer Science 2022-08-17 Novanto Yudistira , Muthu Subash Kavitha , Takio Kurita

Graph convolutional networks (GCNs) have been very successful in modeling non-Euclidean data structures, like sequences of body skeletons forming actions modeled as spatio-temporal graphs. Most GCN-based action recognition methods use deep…

Computer Vision and Pattern Recognition · Computer Science 2021-04-26 Negar Heidari , Alexandros Iosifidis

Accurate and real-time traffic state prediction is of great practical importance for urban traffic control and web mapping services. With the support of massive data, deep learning methods have shown their powerful capability in capturing…

Machine Learning · Computer Science 2023-09-07 Xunlian Luo , Chunjiang Zhu , Detian Zhang , Qing Li

In this paper, we present a method to estimate a sequence of human poses in unconstrained videos. We aim to demonstrate that by using temporal information, the human pose estimation results can be improved over image based pose estimation…

Computer Vision and Pattern Recognition · Computer Science 2016-04-27 Dong Zhang , Mubarak Shah

This paper presents a self-supervised temporal video alignment framework which is useful for several fine-grained human activity understanding applications. In contrast with the state-of-the-art method of CASA, where sequences of 3D…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Quoc-Huy Tran , Muhammad Ahmed , Murad Popattia , M. Hassan Ahmed , Andrey Konin , M. Zeeshan Zia

Recently, spatiotemporal graphs have emerged as a concise and elegant manner of representing video clips in an object-centric fashion, and have shown to be useful for downstream tasks such as action recognition. In this work, we investigate…

Computer Vision and Pattern Recognition · Computer Science 2023-12-13 Aditya Murali , Deepak Alapatt , Pietro Mascagni , Armine Vardazaryan , Alain Garcia , Nariaki Okamoto , Didier Mutter , Nicolas Padoy

Human motion prediction (HMP) involves forecasting future human motion based on historical data. Graph Convolutional Networks (GCNs) have garnered widespread attention in this field for their proficiency in capturing relationships among…

Computer Vision and Pattern Recognition · Computer Science 2025-01-03 Jiexin Wang , Yiju Guo , Bing Su

Monocular 3D human pose estimation remains a fundamentally ill-posed inverse problem due to the inherent depth ambiguity in 2D-to-3D lifting. While contemporary video-based methods leverage temporal context to enhance spatial reasoning,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-23 Zhuoyang Xie , Yibo Zhao , Hui Huang , Riwei Wang , Zan Gao

Skeleton-based action recognition relies on the extraction of spatial-temporal topological information. Hypergraphs can establish prior unnatural dependencies for the skeleton. However, the existing methods only focus on the construction of…

Computer Vision and Pattern Recognition · Computer Science 2023-02-20 Shengqin Wang , Yongji Zhang , Hong Qi , Minghao Zhao , Yu Jiang

Video-based person re-identification aims to match pedestrians from video sequences across non-overlapping camera views. The key factor for video person re-identification is to effectively exploit both spatial and temporal clues from video…

Computer Vision and Pattern Recognition · Computer Science 2021-04-19 Jiawei Liu , Zheng-Jun Zha , Wei Wu , Kecheng Zheng , Qibin Sun

Predicting 3D human pose from a single monoscopic video can be highly challenging due to factors such as low resolution, motion blur and occlusion, in addition to the fundamental ambiguity in estimating 3D from 2D. Approaches that directly…

Computer Vision and Pattern Recognition · Computer Science 2021-04-26 Tao Jiang , Necati Cihan Camgoz , Richard Bowden

Human actions comprise of joint motion of articulated body parts or `gestures'. Human skeleton is intuitively represented as a sparse graph with joints as nodes and natural connections between them as edges. Graph convolutional networks…

Computer Vision and Pattern Recognition · Computer Science 2018-09-14 Kalpit Thakkar , P J Narayanan

We propose a Dynamic Graph-Based Spatial-Temporal Attention (DG-STA) method for hand gesture recognition. The key idea is to first construct a fully-connected graph from a hand skeleton, where the node features and edges are then…

Computer Vision and Pattern Recognition · Computer Science 2019-07-23 Yuxiao Chen , Long Zhao , Xi Peng , Jianbo Yuan , Dimitris N. Metaxas

Video 3D human pose estimation aims to localize the 3D coordinates of human joints from videos. Recent transformer-based approaches focus on capturing the spatiotemporal information from sequential 2D poses, which cannot model the…

Computer Vision and Pattern Recognition · Computer Science 2022-08-09 Zhongwei Qiu , Qiansheng Yang , Jian Wang , Dongmei Fu

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…

Computer Vision and Pattern Recognition · Computer Science 2024-10-23 Mengmeng Cui , Kunbo Zhang , Zhenan Sun

This paper addresses the challenge of 3D full-body human pose estimation from a monocular image sequence. Here, two cases are considered: (i) the image locations of the human joints are provided and (ii) the image locations of joints are…

Computer Vision and Pattern Recognition · Computer Science 2016-04-29 Xiaowei Zhou , Menglong Zhu , Spyridon Leonardos , Kosta Derpanis , Kostas Daniilidis

Recognizing human actions in videos requires spatial and temporal understanding. Most existing action recognition models lack a balanced spatio-temporal understanding of videos. In this work, we propose a novel two-stream architecture,…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Dongho Lee , Jongseo Lee , Jinwoo Choi

Graph convolutional networks (GCNs), which can model the human body skeletons as spatial and temporal graphs, have shown remarkable potential in skeleton-based action recognition. However, in the existing GCN-based methods, graph-structured…

Computer Vision and Pattern Recognition · Computer Science 2022-10-13 Han Chen , Yifan Jiang , Hanseok Ko