computer-vision-7

Multi-Person Pose Estimation

3260 papers • 126 benchmarks • 313 datasets

Multi-person pose estimation is the task of estimating the pose of multiple people in one frame. ( Image credit: Human Pose Estimation with TensorFlow )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in multi-person-pose-estimation-7

Trend

Dataset

Best Model

Actions

CrowdPose

MS COCO

COCO test-dev

Libraries

i

Use these libraries to find multi-person-pose-estimation-7 models and implementations

open-mmlab/mmpose

13 papers 6,325

Datasets

Subtasks

Semi-Supervised Human Pose Estimation

Most implemented papers

Mask R-CNN

Kaiming He, Georgia Gkioxari, Ross B. Girshick, Piotr Dollár•Sun Mar 19 2017

This work presents a conceptually simple, flexible, and general framework for object instance segmentation, which extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition.

30711

Content

MPII Multi-Person

OCHuman

PoseTrack2018

COCO minival

WAF

PoseTrack2017

COCO-WholeBody

Multi-Person PoseTrack

COCO

PoseTrack21

PaddlePaddle/PaddleDetection

5 papers 13,296

osmr/imgclsmob

5 papers 3,001

CMU-Perceptual-Computing-Lab/openpo…

2 papers 32,281

aim-uofa/AdelaiDet

2 papers 3,431

aim-uofa/adet

2 papers 3,431

chenyilun95/tf-cpn

2 papers 790

CMU-Perceptual-Computing-Lab/openpo…

2 papers 731

hikvision-research/opera

2 papers 161

soulslicer/staf

2 papers 151

michel-liu/grouppose

2 papers 87

D1vyansh/BodyJointDetection

2 papers 11

0

Paper Graph

Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields

T. Simon, Yaser Sheikh, Zhe Cao, S. Wei•Wed Nov 23 2016

This work presents an approach to efficiently detect the 2D pose of multiple people in an image using a nonparametric representation, which it refers to as Part Affinity Fields (PAFs), to learn to associate body parts with individuals in the image.

7075 0

Paper Graph

OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields

T. Simon, Yaser Sheikh, Zhe Cao, S. Wei, Gines Hidalgo•Mon Dec 17 2018

OpenPose is released, the first open-source realtime system for multi-person 2D pose detection, including body, foot, hand, and facial keypoints, and the first combined body and foot keypoint detector, based on an internal annotated foot dataset.

5253 0

Paper Graph

Deep High-Resolution Representation Learning for Human Pose Estimation

Ke Sun, Bin Xiao, Dong Liu, Jingdong Wang•Sun Feb 24 2019

This paper proposes a network that maintains high-resolution representations through the whole process of human pose estimation and empirically demonstrates the effectiveness of the network through the superior pose estimation results over two benchmark datasets: the COCO keypoint detection dataset and the MPII Human Pose dataset.

4672 0

Paper Graph

Simple Baselines for Human Pose Estimation and Tracking

Bin Xiao, Yichen Wei, Haiping Wu•Mon Apr 16 2018

This work provides simple and effective baseline methods for pose estimation that are helpful for inspiring and evaluating new ideas for the field and achieved on challenging benchmarks.

1995 0

Paper Graph

HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation

Bin Xiao, Jingdong Wang, Thomas S. Huang, Humphrey Shi, Lei Zhang, Bowen Cheng•Mon Aug 26 2019

HigherHRNet is presented, a novel bottom-up human pose estimation method for learning scale-aware representations using high-resolution feature pyramids that surpasses all top-down methods on CrowdPose test and achieves new state-of-the-art result on COCO test-dev, suggesting its robustness in crowded scene.

782 0

Paper Graph

DeeperCut: A Deeper, Stronger, and Faster Multi-person Pose Estimation Model

Mykhaylo Andriluka, B. Schiele, Eldar Insafutdinov, Bjoern Andres, L. Pishchulin•Mon May 09 2016

The goal of this paper is to advance the state-of-the-art of articulated pose estimation in scenes with multiple people. To that end we contribute on three fronts. We propose (1) improved body part detectors that generate effective bottom-up proposals for body parts; (2) novel image-conditioned pairwise terms that allow to assemble the proposals into a variable number of consistent body part configurations; and (3) an incremental optimization strategy that explores the search space more efficiently thus leading both to better performance and significant speed-up factors. Evaluation is done on two single-person and two multi-person pose estimation benchmarks. The proposed approach significantly outperforms best known multi-person pose estimation results while demonstrating competitive performance on the task of single person pose estimation (Models and code available at http://pose.mpi-inf.mpg.de).

1165 0

Paper Graph

RMPE: Regional Multi-person Pose Estimation

Haoshu Fang, Yu-Wing Tai, Cewu Lu, Shuqin Xie•Wed Nov 30 2016

This paper proposes a novel regional multi-person pose estimation (RMPE) framework to facilitate pose estimation in the presence of inaccurate human bounding boxes and can achieve 76:7 mAP on the MPII (multi person) dataset.

1722 0

Paper Graph

ArtTrack: Articulated Multi-Person Tracking in the Wild

Mykhaylo Andriluka, B. Schiele, Siyu Tang, Evgeny Levinkov, Eldar Insafutdinov, Bjoern Andres, L. Pishchulin•Sun Dec 04 2016

This paper uses a model that resembles existing architectures for single-frame pose estimation but is substantially faster to generate proposals for body joint locations and forms articulated tracking as spatio-temporal grouping of such proposals.

278 0

Paper Graph

Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose

D. Osokin•Wed Nov 28 2018

This work adapts multi-person pose estimation architecture to use it on edge devices using the bottom-up approach from OpenPose, the winner of COCO 2016 Keypoints Challenge, because of its decent quality and robustness to number of people inside the frame.

324 0

Paper Graph

Adding a benchmark result helps the community track progress.