Filters








32,653 Hits in 4.0 sec

Learning Human Pose Estimation Features with Convolutional Networks [article]

Arjun Jain, Jonathan Tompson, Mykhaylo Andriluka, Graham W. Taylor, Christoph Bregler
2014 arXiv   pre-print
This paper introduces a new architecture for human pose estimation using a multi- layer convolutional network architecture and a modified learning technique that learns low-level features and higher-level  ...  Unconstrained human pose estimation is one of the hardest problems in computer vision, and our new architecture and learning schema shows significant improvement over the current state-of-the-art results  ...  In this paper, we present the first end-to-end learning approach for full-body human pose estimation.  ... 
arXiv:1312.7302v6 fatcat:wfyjghaigrgzblndnyft4fahvq

Human Pose Estimation with Parsing Induced Learner

Xuecheng Nie, Jiashi Feng, Yiming Zuo, Shuicheng Yan
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
features for more accurate pose estimation.  ...  Human pose estimation still faces various difficulties in challenging scenarios.  ...  The parameter adapter network is trained with supervision from human pose to learn adaptive parameters for boosting pose estimation.  ... 
doi:10.1109/cvpr.2018.00224 dblp:conf/cvpr/NieFZY18 fatcat:qyer4pqlnna7dcy2ft7gkcylui

Human Action Recognition Based on Temporal Pose CNN and Multi-dimensional Fusion [chapter]

Yi Huang, Shang-Hong Lai, Shao-Heng Tai
2019 Landolt-Börnstein - Group III Condensed Matter  
To take advantage of recent advances in human pose estimation from images, we develop a deep neural network model for action recognition from videos by computing temporal human pose features with a 3D  ...  The proposed temporal pose features can provide more discriminative human action information than previous video features, such as appearance and short-term motion.  ...  With the help of human pose features and proposed channel-wise convolution techniques. We present a novel way of utilizing pose features for human action recognition.  ... 
doi:10.1007/978-3-030-11012-3_33 fatcat:nz3q2f7hrjeqjoszc6iam2a4zu

Human Pose Estimation with Deeply Learned Multi-Scale Compositional Models

Rui Wang, Zhongzheng Cao, Xiangyang Wanga, Zhi Liu, Xiaoqiang Zhu
2019 IEEE Access  
Deeply learned compositional model (DLCM) utilizes deep neural networks to learn compositionality of human body parts and has achieved great improvements in human pose estimation.  ...  Compositional models are meant for human pose estimation (HPE) due to their abilities to capture relationships among human body parts.  ...  DeepPose [13] is the first deep learning based approach for human pose estimation, which takes the pose estimation as a body keypoints regression problem using convolutional Neural Networks, and outperforms  ... 
doi:10.1109/access.2019.2919154 fatcat:joc7z2o2ebhzrjnwu3o5wqiwm4

3D Human Pose Estimation from Monocular Images with Deep Convolutional Neural Network [chapter]

Sijin Li, Antoni B. Chan
2015 Lecture Notes in Computer Science  
In this paper, we propose a deep convolutional neural network for 3D human pose estimation from monocular images.  ...  Discriminative methods view pose estimation as a regression problem [4, [9] [10] [11] . After extracting features from the image, a mapping is learned from the feature space to the pose space.  ...  This work was supported by the Research Grants Council of the Hong Kong Special Administrative Region, China (CityU 123212 and CityU 110513). 3D Human Pose Estimation from Monocular Images with Deep  ... 
doi:10.1007/978-3-319-16808-1_23 fatcat:4rwf5y3avnbfxgahnyhn6nzbdy

Lightweight Stacked Hourglass Network for Human Pose Estimation

Seung-Taek Kim, Hyo Jong Lee
2020 Applied Sciences  
Additionally, the size of the convolutional receptive field has a decisive effect in learning to detect features of the full human body.  ...  While the stacked structure of an hourglass network has enabled substantial progress in human pose estimation and key-point detection areas, it is largely used as a backbone network.  ...  Residual Block Design Dilated Convolution In human pose estimation, it is important to increase the receptive field so that the network can learn to recognize the features of the full human body.  ... 
doi:10.3390/app10186497 fatcat:5abjzvl6hbd4vjsefpbmk5qmeq

Feature Boosting Network For 3D Pose Estimation [article]

Jun Liu, Henghui Ding, Amir Shahroudy, Ling-Yu Duan, Xudong Jiang, Gang Wang, Alex C. Kot
2019 arXiv   pre-print
In this paper, a feature boosting network is proposed for estimating 3D hand pose and 3D body pose from a single RGB image.  ...  In this method, the features learned by the convolutional layers are boosted with a new long short-term dependence-aware (LSTD) module, which enables the intermediate convolutional feature maps to perceive  ...  [42] augmented the 2D pose estimation subnetwork with a 3D depth regression sub-network to perform 3D human pose estimation. Tome et al.  ... 
arXiv:1901.04877v2 fatcat:r7jxpikarraojluylvz6t2dr6q

3D Human Pose Estimation with Spatial Structure Information

Xiaoshan Huang, Jun Huang, Zengming Tang
2021 IEEE Access  
Therefore, we represent human pose as a directed graph and propose a network implemented with graph convolution to predict 3D poses from the given 2D poses.  ...  INDEX TERMS 3D human poses, graph convolutional networks, adversarial learning, geometric priors, gradient vanish, in-the-wild scenes.  ...  POSE REFINEMENT MODULE To relieve the ambiguity of recovering depth, our network generates coarse 3D estimations and then the pose refinement module concatenates 2D and 3D pose features to learn refined  ... 
doi:10.1109/access.2021.3062426 fatcat:anfl6gqkyzfblcp3mh7lq74asm

Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network

Sijin LI, Zhi-Qiang Liu, Antoni B. Chan
2014 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops  
We propose an heterogeneous multi-task learning framework for human pose estimation from monocular image with deep convolutional neural network.  ...  In particular, we simultaneously learn a pose-joint regressor and a slidingwindow body-part detector in a deep network architecture.  ...  Conclusion In this paper, we have proposed a heterogeneous multitask learning framework with deep convolutional neural network for human pose estimation.  ... 
doi:10.1109/cvprw.2014.78 dblp:conf/cvpr/LiLC14 fatcat:qszxuz2vnzcqhf3c2nx4yaknw4

Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network [article]

Sijin Li, Zhi-Qiang Liu, Antoni B. Chan
2014 arXiv   pre-print
We propose an heterogeneous multi-task learning framework for human pose estimation from monocular image with deep convolutional neural network.  ...  In particular, we simultaneously learn a pose-joint regressor and a sliding-window body-part detector in a deep network architecture.  ...  Conclusion In this paper, we have proposed a heterogeneous multitask learning framework with deep convolutional neural network for human pose estimation.  ... 
arXiv:1406.3474v1 fatcat:3zulyhzgeffptey3kkod7v3mge

Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network

Sijin Li, Zhi-Qiang Liu, Antoni B. Chan
2014 International Journal of Computer Vision  
We propose an heterogeneous multi-task learning framework for human pose estimation from monocular image with deep convolutional neural network.  ...  In particular, we simultaneously learn a pose-joint regressor and a slidingwindow body-part detector in a deep network architecture.  ...  Conclusion In this paper, we have proposed a heterogeneous multitask learning framework with deep convolutional neural network for human pose estimation.  ... 
doi:10.1007/s11263-014-0767-8 fatcat:6mlltwkn7zdynfefb7cvqi3bla

A Study of Athlete Pose Estimation Techniques in Sports Game Videos Combining Multiresidual Module Convolutional Neural Networks

Rui Liu, Gaurav Singal
2021 Computational Intelligence and Neuroscience  
In this paper, we propose a multiresidual module convolutional neural network-based method for athlete pose estimation in sports game videos.  ...  of athlete pose estimation in sports game videos.  ...  With the rapid development of deep learning and convolutional network technology, the accuracy of athlete pose estimation for relatively simple and standard normal pose has been significantly improved,  ... 
doi:10.1155/2021/4367875 pmid:34992645 pmcid:PMC8727100 fatcat:vxqj2wz345c2bfjl36wuzvvepa

Combining Parsing Information with Joint Structure for Human Pose Estimation

Shenming Feng, Xiying Li, Haifeng Hu
2020 IEEE Access  
Recently, with the growing popularity of Convolutional Neural Networks (CNN), major progress has been made in human pose estimation.  ...  assisting human pose estimation in unconstrained environment.  ...  HUMAN POSE ESTIMATION Recently, Convolutional Neural Networks (CNN) have been widely used in human pose estimation due to their effective ability of feature extraction and the availability of powerful  ... 
doi:10.1109/access.2020.3004937 fatcat:c6dy6l53svglfhjqryuukr3z4u

Multi-person Pose Estimation Under Complex Environment Based on Progressive Rotation Correction and Multi-scale Feature Fusion

Guoheng Huang, Xiaoping Chen, Junan Chen, Weida Lin, Wing-Kuen Ling, Chi-Man Pun, Lianglun Cheng, Zhuowei Wang
2020 IEEE Access  
models of pose estimation are trained using Adaptive moment estimation (Adam) algorithm with an initial learning rate of 0.0001.  ...  Pose estimation is divided into single-person pose estimation and multi-person pose estimation, where single-person pose estimation is based on a single human body predicting key points, and multi-person  ... 
doi:10.1109/access.2020.3010257 fatcat:lx5lcvfhgbffxblo6rjrgypsu4

Semantic Graph Convolutional Networks for 3D Human Pose Regression

Long Zhao, Xi Peng, Yu Tian, Mubbasir Kapadia, Dimitris N. Metaxas
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
In this paper, we study the problem of learning Graph Convolutional Networks (GCNs) for regression.  ...  To address these limitations, we propose Semantic Graph Convolutional Networks (SemGCN), a novel neural network architecture that operates on regression tasks with graph-structured data.  ...  Figure 3 . 3 Illustration of our framework incorporating image features for 3D human pose estimation. We pre-train a 2D pose estimation network to predict 2D joint locations.  ... 
doi:10.1109/cvpr.2019.00354 dblp:conf/cvpr/00030TKM19 fatcat:csbbhetog5d7thjonvbqp54tom
« Previous Showing results 1 — 15 out of 32,653 results