paper
-with-
me
Papers
Browse State-of-the-Art
Datasets
Methods
AI Agents
Trends
Digest
🌙
Keypoint Detection
벤치마크
Keypoint Detection on COCO test-dev
48개 결과 ·
⬇ CSV
·
JSON
APM
57.1
61.18
65.25
69.33
73.4
2016-11
2026-11
AE — 60.6 (2016-11-16)
AE — 60.6 (2016-11-16)
AE — 60.6 (2016-11-16)
CMU Pose — 57.1 (2016-11-24)
CMU Pose — 57.1 (2016-11-24)
CMU Pose — 57.1 (2016-11-24)
G-RMI — 62.3 (2017-01-06)
G-RMI — 62.3 (2017-01-06)
G-RMI — 62.3 (2017-01-06)
Mask R-CNN — 57.8 (2017-03-20)
Mask R-CNN — 57.8 (2017-03-20)
Mask R-CNN — 57.8 (2017-03-20)
CPN+ — 69.5 (2017-11-20)
CPN — 68.7 (2017-11-20)
CPN+ — 69.5 (2017-11-20)
CPN — 68.7 (2017-11-20)
CPN+ — 69.5 (2017-11-20)
CPN — 68.7 (2017-11-20)
Simple Base+* — 73.0 (2018-04-17)
Simple Base — 70.3 (2018-04-17)
Simple Base+* — 73.0 (2018-04-17)
Simple Base — 70.3 (2018-04-17)
Simple Base+* — 73.0 (2018-04-17)
Simple Base — 70.3 (2018-04-17)
MSPN — 72.3 (2019-01-01)
MSPN — 72.3 (2019-01-01)
MSPN — 72.3 (2019-01-01)
HRNet* — 73.4 (2019-02-25)
HRNet — 71.9 (2019-02-25)
HRNet* — 73.4 (2019-02-25)
HRNet — 71.9 (2019-02-25)
HRNet* — 73.4 (2019-02-25)
HRNet — 71.9 (2019-02-25)
PifPaf (single-scale) — 62.6 (2019-03-15)
PifPaf (single-scale) — 62.6 (2019-03-15)
PifPaf (single-scale) — 62.6 (2019-03-15)
DirectPose (ResNet-101) — 60.4 (2019-11-18)
DirectPose (ResNet-101) — 60.4 (2019-11-18)
DirectPose (ResNet-101) — 60.4 (2019-11-18)
Simple Pose — 66.8 (2019-11-24)
Simple Pose — 66.8 (2019-11-24)
Simple Pose — 66.8 (2019-11-24)
OpenPifPaf — 67.1 (2021-03-03)
OpenPifPaf — 67.1 (2021-03-03)
OpenPifPaf — 67.1 (2021-03-03)
AE — 60.6 (2016-11-16)
G-RMI — 62.3 (2017-01-06)
CPN+ — 69.5 (2017-11-20)
Simple Base+* — 73.0 (2018-04-17)
HRNet* — 73.4 (2019-02-25)
2016-11-16 — AE: APM 60.6
2017-01-06 — G-RMI: APM 62.3
2017-11-20 — CPN+: APM 69.5
2018-04-17 — Simple Base+*: APM 73.0
2019-02-25 — HRNet*: APM 73.4
Rank
Model
APM
APL
AP50
AP75
AR
AR50
AR75
ARM
Paper
Code
Year
1
HRNet*
73.4
83.1
92.7
84.5
82.0
–
–
–
Deep High-Resolution Representation Learning for Human Pose Estimation
open-mmlab/mmdetection
·
PaddlePaddle/PaddleDetection
·
open-mmlab/mmpose
·
+36
2019
2
Simple Base+*
73.0
82.7
92.4
84.0
81.5
95.8
88.2
77.4
Simple Baselines for Human Pose Estimation and Tracking
PaddlePaddle/PaddleDetection
·
open-mmlab/mmpose
·
osmr/imgclsmob
·
+24
2018
3
MSPN
72.3
81.5
93.4
83.8
81.6
96.3
88.1
77.5
Rethinking on Multi-Stage Networks for Human Pose Estimation
open-mmlab/mmpose
·
chenyilun95/tf-cpn
·
megvii-detection/MSPN
·
+4
2019
4
HRNet
71.9
81.5
92.5
83.3
80.5
–
–
–
Deep High-Resolution Representation Learning for Human Pose Estimation
open-mmlab/mmdetection
·
PaddlePaddle/PaddleDetection
·
open-mmlab/mmpose
·
+36
2019
5
Simple Base
70.3
80.0
91.9
81.1
79.0
–
–
–
Simple Baselines for Human Pose Estimation and Tracking
PaddlePaddle/PaddleDetection
·
open-mmlab/mmpose
·
osmr/imgclsmob
·
+24
2018
6
CPN+
69.5
78.1
91.7
80.9
79.0
95.1
85.9
74.8
Cascaded Pyramid Network for Multi-Person Pose Estimation
chenyilun95/tf-cpn
·
caiyuanhao1998/RSN
·
megvii-detection/MSPN
·
+2
2017
7
CPN
68.7
77.2
91.4
80.0
78.5
95.1
85.3
74.2
Cascaded Pyramid Network for Multi-Person Pose Estimation
chenyilun95/tf-cpn
·
caiyuanhao1998/RSN
·
megvii-detection/MSPN
·
+2
2017
8
OpenPifPaf
67.1
76.8
–
–
–
–
–
–
OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association
openpifpaf/openpifpaf
·
openpifpaf/openpifpafwebdemo
·
vita-epfl/openpifpaf
·
+3
2021
9
Simple Pose
66.8
70.5
–
–
72.1
88.2
–
–
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation
osmr/imgclsmob
·
hellojialee/Improved-Body-Parts
·
hellojialee/Multi-Person-Pose-using-Body-Parts
·
+5
2019
10
PifPaf (single-scale)
62.6
72.1
–
–
–
–
–
–
PifPaf: Composite Fields for Human Pose Estimation
thanhtrung98/human_pose_estimation
·
thanhtrung98/Pose_estimation
2019
11
G-RMI
62.3
70.0
85.5
71.3
69.7
88.7
75.5
64.4
Towards Accurate Multi-person Pose Estimation in the Wild
2017
12
AE
60.6
72.6
86.8
72.3
70.2
89.5
76.0
64.6
Associative Embedding: End-to-End Learning for Joint Detection and Grouping
open-mmlab/mmpose
·
princeton-vl/pose-ae-train
·
raymon-tian/hourglass-facekeypoints-detection
·
+2
2016
13
DirectPose (ResNet-101)
60.4
71.5
87.8
71.1
–
–
–
–
DirectPose: Direct End-to-End Multi-Person Pose Estimation
aim-uofa/adet
·
aim-uofa/AdelaiDet
·
idea-research/x-pose
·
+6
2019
14
Mask R-CNN
57.8
71.4
87.3
68.7
–
–
–
–
Mask R-CNN
tensorflow/models
·
facebookresearch/detectron2
·
facebookresearch/detectron
·
+176
2017
15
CMU Pose
57.1
68.2
84.9
67.5
66.5
87.2
–
60.6
Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
CMU-Perceptual-Computing-Lab/openpose
·
ZheC/Realtime_Multi-Person_Pose_Estimation
·
shihenw/convolutional-pose-machines-release
·
+58
2016
16
AlphaPose
–
81.5
–
–
–
–
–
–
RMPE: Regional Multi-person Pose Estimation
MVIG-SJTU/AlphaPose
·
osmr/imgclsmob
·
mindspore-ai/models
·
+11
2016
17
HRNet*
73.4
83.1
92.7
84.5
82.0
–
–
–
Deep High-Resolution Representation Learning for Human Pose Estimation
open-mmlab/mmdetection
·
PaddlePaddle/PaddleDetection
·
open-mmlab/mmpose
·
+36
2019
18
Simple Base+*
73.0
82.7
92.4
84.0
81.5
95.8
88.2
77.4
Simple Baselines for Human Pose Estimation and Tracking
PaddlePaddle/PaddleDetection
·
open-mmlab/mmpose
·
osmr/imgclsmob
·
+24
2018
19
MSPN
72.3
81.5
93.4
83.8
81.6
96.3
88.1
77.5
Rethinking on Multi-Stage Networks for Human Pose Estimation
open-mmlab/mmpose
·
chenyilun95/tf-cpn
·
megvii-detection/MSPN
·
+4
2019
20
HRNet
71.9
81.5
92.5
83.3
80.5
–
–
–
Deep High-Resolution Representation Learning for Human Pose Estimation
open-mmlab/mmdetection
·
PaddlePaddle/PaddleDetection
·
open-mmlab/mmpose
·
+36
2019
1–20 / 48
다음 →
페이지당
10
20
50
100