MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation
Author:
Affiliation:
1. Shenzhen Graduate School, Peking University,Key Laboratory of Machine Perception
2. Computer Vision Lab, ETH Zurich
3. Alibaba Group
Funder
National Key R&D Program of China
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/9878378/9878366/09880430.pdf?arnumber=9880430
Reference47 articles.
1. Depth Pooling Based Large-Scale 3-D Action Recognition With Convolutional Neural Networks
2. Motion guided 3D pose estimation from videos;wang;Proceedings of the European Conference on Computer Vision (ECCV),0
3. Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose
4. GraphMDN: Leveraging graph structure and deep learning to solve inverse problems
5. VNect: Real-time 3D human pose estimation with a single rgb camera;mehta;ACM Transactions on Graphics,2017
Cited by 72 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Neural ordinary differential equation for irregular human motion prediction;Pattern Recognition Letters;2024-02
2. HDPose: Post-Hierarchical Diffusion with Conditioning for 3D Human Pose Estimation;Sensors;2024-01-26
3. Masked Kinematic Continuity-aware Hierarchical Attention Network for pose estimation in videos;Neural Networks;2024-01
4. MHCanonNet: Multi-Hypothesis Canonical lifting Network for self-supervised 3D human pose estimation in the wild video;Pattern Recognition;2024-01
5. MPTFormer: Toward Robust Arm Gesture Pose Tracking Using Dual-View Radar System;IEEE Sensors Journal;2024-01-01
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3