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 ambiguity, self-occlusion, and complex or rare poses is still far from satisfactory. In this work, we target these hard poses and present a novel skeletal GNN learning solution. To be specific, we propose a hop-aware hierarchical channel-squeezing fusion layer to effectively extract relevant information from neighboring nodes while suppressing undesired noises in GNN learning. In addition, we propose a temporal-aware dynamic graph construction procedure that is robust and effective for 3D pose estimation. Experimental results on the Human3.6M dataset show that our solution achieves 10.3\% average prediction accuracy improvement and greatly improves on hard poses over state-of-the-art techniques. We further apply the proposed technique on the skeleton-based action recognition task and also achieve state-of-the-art performance. Our code is available at https://github.com/ailingzengzzz/Skeletal-GNN.
School of Computer Science and Engineering, Nanjing University of Science and Technology(南京理工大学计算机科学与工程学院);Artificial Intelligence Industrial Technology Research Institute, Nanjing Institute of Technology(南京工程学院人工智能产业技术研究院);School of Computer Science, Nanjing University(南京大学计算机科学学院)
针对无监督骨骼动作识别中随机增强难以产生直接语义扰动且会软化正负对的问题,提出 A²MC,利用攻击增强生成困难正样本并由 PNM 混合生成困难负样本,在三个公开数据集上达到与 SOTA 相当的性能。
A Deep Learning Approach for Real-Time 3D Human Action Recognition from Skeletal Data
Cerema(法国路桥与道路研究中心);Université Toulouse III - Paul Sabatier(图卢兹第三大学(保罗·萨巴蒂埃大学));Aparnix;Cortexica Vision Systems Ltd.(Cortexica视觉系统有限公司);Queen Mary University of London(伦敦玛丽女王大学);University Carlos III of Madrid(马德里卡洛斯三世大学)
Skeletal Movement to Color Map: A Novel Representation for 3D Action Recognition with Inception Residual Networks
Carlos III University of Madrid(马德里卡洛斯三世大学);Cerema Research Center(Cerema研究中心);Institut de Recherche en Informatique de Toulouse(图卢兹计算机科学研究所);Université de Toulouse(图卢兹大学)
An Elastic Shape Variational Autoencoder for Skeleton Pose Trajectories
Systems and Information Engineering, University of Virginia(弗吉尼亚大学系统与信息工程系);Biomedical Engineering, Johns Hopkins University(约翰霍普金斯大学生物医学工程系);Dept. of Applied Mathematics and Statistics, Johns Hopkins University(约翰霍普金斯大学应用数学与统计学系)
ProbRadarM3F: mmWave Radar based Human Skeletal Pose Estimation with Probability Map Guided Multi-Format Feature Fusion
School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, P.R.~China(北京航空航天大学自动化科学与电气工程学院);School of Electronics and Information Engineering, Beihang University, Beijing 100191, P.R.~China(北京航空航天大学电子信息工程学院);College of Science and Engineering, James Cook University, Cairns, Australia(詹姆斯库克大学科学与工程学院);School of Computing, Engineering and Mathematical Sciences, La Trobe University, Melbourne, Australia(拉特罗布大学计算、工程与数学科学学院)
HGFreNet: Hop-hybrid GraphFomer for 3D Human Pose Estimation with Trajectory Consistency in Frequency Domain
institutetext: HGFreNet: Hop-hybrid GraphFomer for 3D Human Pose Estimation with Trajectory Consistency in Frequency Domain(机构文本:HGFreNet:Hop-混合图Former 用于具有轨迹一致性的3D人体姿态估计)
Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);IMATI-CNR(意大利国家研究委员会信息技术与应用数学研究所);Université Grenoble Alpes(格勒诺布尔阿尔卑斯大学);Inria(法国国家信息与自动化研究所);CNRS(法国国家科学研究中心);Grenoble INP(格勒诺布尔国立理工学院)
HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation
Shenzhen Cloudream Technology Co., Ltd.(深圳云创科技有限公司);The Chinese University of Hong Kong (Shenzhen)(香港中文大学(深圳));South China University of Technology(华南理工大学)
FinePhys: Fine-grained Human Action Generation by Explicitly Incorporating Physical Laws for Effective Skeletal Guidance
Unmanned System Research Institute, Northwestern Polytechnical University, Xi’an, China(无人系统研究院、西北工业大学、西安,中国);School of Software, Northwestern Polytechnical University, Xi’an, China(软件学院、西北工业大学、西安,中国);School of Automation, Northwestern Polytechnical University, Xi’an, China(自动化学院、西北工业大学、西安,中国);School of Astronautics, Northwestern Polytechnical University, Xi’an, China(航天学院、西北工业大学、西安,中国)
One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer
Jiangnan University(江南大学);University of Science and Technology of China(中国科学技术大学);Chinese Academy of Sciences(中国科学院);Beijing University of Posts and Telecommunications(北京邮电大学);Zhejiang University(浙江大学)
Sign language recognition from skeletal data using graph and recurrent neural networks
Department of Mathematics, Universidad Autónoma de Ciudad Juárez (UACJ)(数学系,自治城朱埃雷斯大学);Department of Electrical ingeniering, Universidad Autónoma de Ciudad Juárez (UACJ)(电气工程系,自治城朱埃雷斯大学);Instituto Iberoamericano San Patricio(伊比利亚美洲圣帕特里克研究所)
Towards Robust and Realistic Human Pose Estimation via WiFi Signals
Department of Computing, The Hong Kong Polytechnic University(香港理工大学计算学系);Department of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University(香港理工大学土地测量及地理资讯学系)
HEMlets PoSh: Learning Part-Centric Heatmap Triplets for 3D Human Pose and Shape Estimation
SmartMore Co., Ltd.(思谋科技有限公司);Shenzhen Institute of Big Data, The Chinese University of Hong Kong (Shenzhen)(香港中文大学(深圳)深圳大数据研究院);South China University of Technology(华南理工大学)
Skeleton Transformer Networks: 3D Human Pose and Skinned Mesh from Single RGB Image
National Institute of Advanced Industrial Science and Technology (AIST)(国立先进工业科学技术研究所(AIST));CNRS-AIST JRL (Joint Robotics Laboratory), UMI3218/RL(法国国家科学研究中心-国立先进工业科学技术研究所联合机器人实验室(UMI3218/RL))
Multi-Track Multimodal Learning on iMiGUE: Micro-Gesture and Emotion Recognition
Russian - Armenian University(俄罗斯-亚美尼亚大学);Sber AI Lab(Sber AI实验室);HSE University(俄罗斯高等经济大学);Innopolis University(Innopolis大学);ISP RAS Research Center for Trusted Artificial Intelligence(俄罗斯科学院可信人工智能研究中心)