2019 IEEE/CVF International Conference on Computer Vision (ICCV) 2019
DOI: 10.1109/iccv.2019.00241
|View full text |Cite
|
Sign up to set email alerts
|

Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
76
0

Year Published

2020
2020
2021
2021

Publication Types

Select...
5
2
1

Relationship

0
8

Authors

Journals

citations
Cited by 139 publications
(78 citation statements)
references
References 24 publications
0
76
0
Order By: Relevance
“…PA MPJPE Chen et al [11] 82.7 Moreno et al [32] 76.5 Zhou et al [56] 55.3 Sun et al [47] 48.3 Sharma et al [44] 40.9 Sun et al [48] 40.6 Moon et al [31] 34.0 Baseline * 34.7 Baseline 2 * * 34.3 ours 33.1 Table A1. 3-D human pose estimation evaluation on the Hu-man3.6M dataset using Protocol I.…”
Section: Methodsmentioning
confidence: 99%
“…PA MPJPE Chen et al [11] 82.7 Moreno et al [32] 76.5 Zhou et al [56] 55.3 Sun et al [47] 48.3 Sharma et al [44] 40.9 Sun et al [48] 40.6 Moon et al [31] 34.0 Baseline * 34.7 Baseline 2 * * 34.3 ours 33.1 Table A1. 3-D human pose estimation evaluation on the Hu-man3.6M dataset using Protocol I.…”
Section: Methodsmentioning
confidence: 99%
“…At the same time, some works use a deep CNN [ 27 , 28 ]. (iii) The deep learning-based approaches [ 12 , 14 , 27 , 28 , 31 , 32 ] which do not rely on hand-crafted features/descriptors but learn features and mapping to 3D human poses directly. (iv) There also exist hybrid approaches [ 6 , 33 , 34 ] that combine together the generative as well as discriminative methods.…”
Section: Related Workmentioning
confidence: 99%
“…Hence, to meet the massive demand for MoCap data, many research works have been performed to infer 3D human poses from internet-based in-the-wild real 2D images/videos [ 7 , 8 , 9 , 10 , 11 , 12 , 13 ]. Due to the curse of dimensionality and the ill-posed nature [ 14 ], there are open challenges connected to lifting 2D poses up to 3D poses. 3D human motion capturing from in-the-wild 2D pictures and videos will empower many vision-dependent applications such as health rehabilitation-based industries, robotics, virtual reality, entertainment, surveillance systems, and human-computer interaction [ 15 ].…”
Section: Introductionmentioning
confidence: 99%
“…performed by 7 actors. Following, [6,7,4,12,13,11,22,19], we adopt a 17-joint skeleton, train on five subjects (S1, S5, S6, S7, S8), and test on two subjects (S9 and S11). Following [4], we apply same pre-processing to ground truth annotations.…”
Section: Datasetmentioning
confidence: 99%
“…Different hypothesis generation approaches like Bayesian framework, [10], Gaussian Mixture Model [11], Variational Autoencoder [12] have been proposed in recent years. However, end-to-end encoder-decoder network has not been explored much for hypothesis generation in 3D pose estimation problem.…”
Section: Introductionmentioning
confidence: 99%