| 74 |
|
|
|
71.100 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 75.900 |
79.300 |
73.000 |
69.800 |
61.100 |
68.500 |
68.000 |
74.600 |
71.100 |
|
Abbreviation
|
2017-05-25 13:09:53 |
| 82 |
EP108 |
|
|
87.600 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 95.000 |
93.000 |
89.100 |
86.700 |
75.900 |
85.500 |
86.200 |
91.100 |
87.600 |
|
Abbreviation
|
2017-06-10 17:14:56 |
| 96 |
ttest |
|
|
73.400 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 63.800 |
86.700 |
78.400 |
72.700 |
67.800 |
74.300 |
68.900 |
75.400 |
73.400 |
|
Abbreviation
|
2017-05-31 08:39:34 |
| 59 |
LTL |
|
|
87.500 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 94.900 |
93.100 |
89.900 |
87.600 |
75.900 |
84.900 |
84.400 |
91.400 |
87.500 |
|
Abbreviation
|
2017-09-01 10:43:40 |
| 106 |
|
|
|
68.400 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 73.800 |
76.100 |
68.600 |
66.200 |
55.400 |
67.900 |
70.600 |
71.300 |
68.400 |
|
Abbreviation
|
2017-06-04 06:21:42 |
| 27 |
Hybrid Pose Matchine |
|
|
77.200 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 71.700 |
87.100 |
82.300 |
78.200 |
69.200 |
77.000 |
73.500 |
79.800 |
77.200 |
|
Abbreviation
| Contributors |
Description |
| Yue Liao*[1], Ruihe Qian*[1], Si Liu[1], Yao Sun[1] and Yinglu Liu[2],Yanli Li[2],Junjun Xiong[2]
[1]IIE,CAS
[2]Beijing Samsung Telecom R&D Center |
We have proposed a hybrid method of inferring the pose of humans. We first extract human bounding boxes from the pose ground truth. Then we train a Faster R-CNN [1] based human detector to infer the human box in testing phase. Then Convolutional Pose Machines with Part Affinity Fields [2] and Stacked Hourglass Networks [3] are applied to estimate the poses. And the results are merged. No extra data are used in our method.
[1]Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.Shaoqing Ren, Kaiming He,et al.TPAMI2016
[2] Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields.Cao Z, Simon T, Wei S E, et al.CVPR2017.
[3]Stacked Hourglass Networks for Human Pose Estimation. Newell et al., POCV 2016 |
|
2017-06-04 13:38:59 |
| 107 |
BUPTMM-POSE |
|
|
80.200 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 90.400 |
87.300 |
81.900 |
78.800 |
68.500 |
75.300 |
75.800 |
84.800 |
80.200 |
|
Abbreviation
| Contributors |
Description |
| Wu Liu, Huadong Ma, Peng Cheng, Cheng Zhang, Haoran Lv, Xiongxiong Dong |
We revised and finetuned Stacked Hourglass [1] and Convolutional Pose Machines [2] on LIP training set, then combined them with different fusion strategies.
[1] Stacked Hourglass Networks for Human Pose Estimation, Alejandro Newell, Kaiyu Yang, and Jia Deng, ECCV 2016;
[2] Convolutional pose machines, Shih-En Wei, Varun Ramakrishna, Takeo Kanade, Yaser Sheikh, CVPR 2016. |
|
2017-06-04 14:53:20 |
| 18 |
Tightly Connected ResNet-101 |
|
|
81.000 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 93.200 |
87.900 |
82.300 |
79.800 |
69.100 |
75.500 |
75.400 |
85.900 |
81.000 |
|
Abbreviation
|
2017-06-04 15:29:10 |
| 215 |
cs_ft-2 |
|
|
87.000 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 94.400 |
92.400 |
88.300 |
86.000 |
76.100 |
84.700 |
85.000 |
90.400 |
87.000 |
|
Abbreviation
| Contributors |
Description |
| Zhuowan Li, Chenxu Luo |
8 stack hourglass pre-trained on MPII, fine-tuned on LIP |
|
2017-07-05 00:00:00 |
| 92 |
tst6 |
|
|
80.600 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 93.900 |
88.600 |
82.200 |
78.300 |
69.700 |
73.300 |
73.200 |
86.000 |
80.600 |
|
Abbreviation
|
2017-09-13 15:20:38 |
| 260 |
1 |
|
|
61.300 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 84.400 |
74.400 |
58.300 |
47.300 |
53.500 |
53.400 |
51.500 |
66.500 |
61.300 |
|
Abbreviation
| Contributors |
Description |
| q |
s |
|
2018-04-19 21:36:49 |
| 258 |
h |
|
|
82.500 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 93.100 |
89.600 |
84.500 |
82.400 |
69.800 |
77.300 |
77.700 |
87.500 |
82.500 |
|
Abbreviation
|
2018-05-18 04:23:34 |
| 288 |
JDAI-human |
|
|
90.900 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 95.900 |
94.800 |
92.300 |
90.400 |
81.400 |
90.300 |
90.200 |
93.400 |
90.900 |
|
Abbreviation
| Contributors |
Description |
| Fangyu Li,
Wu Liu, Qian Bao, Peng Cheng, Tao Mei. JD AI Research. |
Our final method is based on cascading pyramid network [1], stacked hourglass [2] and RMPE [3]. We modified and fine-tuned the above models on the LIP dataset with increasing the size of inputs and feature maps, data augmentation, hard point mining, and other strategies. Finally, we fused the models to get the best results.
[1] Chen, Yilun, et al. "Cascaded Pyramid Network for Multi-Person Pose Estimation." arXiv preprint arXiv:1711.07319 (2017).
[2] Newell, Alejandro, et al. "Stacked hourglass networks for human pose estimation." European Conference on Computer Vision. 2016.
[3] Fang, Hao-Shu, et al. "RMPE: Regional multi-person pose estimation." The IEEE International Conference on Computer Vision. 2017. |
|
2018-06-10 03:27:17 |
| 283 |
|
|
|
83.300 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 93.600 |
89.800 |
85.000 |
83.700 |
70.400 |
78.800 |
78.900 |
88.100 |
83.300 |
|
Abbreviation
|
2018-05-24 09:21:20 |
| 298 |
|
|
|
92.600 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 96.600 |
95.700 |
94.300 |
92.900 |
83.400 |
92.500 |
92.300 |
94.900 |
92.600 |
|
Abbreviation
|
2019-06-02 15:41:44 |
| 325 |
|
|
|
81.400 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 92.800 |
88.500 |
83.400 |
82.000 |
67.100 |
76.400 |
76.300 |
86.800 |
81.400 |
|
Abbreviation
|
2018-10-10 03:45:06 |
| 333 |
IR-new |
|
|
87.600 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 94.100 |
93.100 |
88.400 |
86.500 |
78.000 |
85.900 |
86.000 |
90.600 |
87.600 |
|
Abbreviation
| Contributors |
Description |
| IR |
|
|
2018-12-18 02:57:55 |
| 340 |
|
|
|
87.500 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 95.100 |
93.000 |
89.200 |
87.500 |
76.600 |
84.600 |
84.500 |
91.300 |
87.500 |
|
Abbreviation
|
2019-04-06 00:11:37 |
| 344 |
MPP |
|
|
82.800 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 93.600 |
89.700 |
84.500 |
82.800 |
70.100 |
77.000 |
78.500 |
87.800 |
82.800 |
|
Abbreviation
| Contributors |
Description |
| fdu_taoshiqian |
tsq6 |
|
2018-12-05 07:44:28 |
| 270 |
|
|
|
90.500 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 95.500 |
94.400 |
92.400 |
90.400 |
80.600 |
90.000 |
89.700 |
93.200 |
90.500 |
|
Abbreviation
|
2019-05-23 03:28:45 |
| 369 |
Zll |
|
|
86.000 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 94.300 |
92.100 |
87.800 |
85.300 |
75.300 |
82.800 |
82.300 |
90.000 |
86.000 |
|
Abbreviation
| Contributors |
Description |
| zllrunning |
Try! |
|
2019-01-23 02:13:34 |
| 306 |
CFA |
|
|
91.000 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 95.800 |
94.700 |
92.500 |
90.400 |
81.700 |
90.600 |
90.500 |
93.400 |
91.000 |
|
Abbreviation
|
2019-03-11 08:39:23 |
| 377 |
747474 |
|
|
0.200 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 0.500 |
0.200 |
0.200 |
0.300 |
0.100 |
0.200 |
0.100 |
0.300 |
0.200 |
|
Abbreviation
|
2019-05-29 23:51:35 |
| 384 |
how |
|
|
78.300 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 88.200 |
84.700 |
79.900 |
78.200 |
66.300 |
73.700 |
74.100 |
82.900 |
78.300 |
|
Abbreviation
|
2019-03-14 14:10:59 |
| 385 |
GCCPM (160 fps) |
|
|
88.600 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 95.300 |
93.700 |
90.300 |
87.800 |
78.500 |
86.700 |
86.500 |
91.900 |
88.600 |
|
Abbreviation
| Contributors |
Description |
| Daniil Osokin (IOTG Computer Vision (ICV), Intel Russia) |
We have improved original Convolutional Pose Machine architecture with addition of global context module to enhance receptive field. Also proposed body-masking augmentation technique which improved the prediction results for occluded body parts. 2-stage version of this network runs more than 160 fps on GPU and ~20 fps on CPU. More details can be found in the paper "Global Context for Convolutional Pose Machines", code is available: https://github.com/opencv/openvino_training_extensions/tree/develop/pytorch_toolkit/human_pose_estimation. |
|
2019-05-30 10:08:07 |
| 383 |
|
|
|
81.900 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 75.800 |
90.200 |
87.200 |
87.800 |
68.700 |
81.200 |
82.900 |
85.200 |
81.900 |
|
Abbreviation
|
2019-03-25 09:35:05 |
| 393 |
|
|
|
85.800 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 93.400 |
91.500 |
87.700 |
85.400 |
74.700 |
83.400 |
82.300 |
89.600 |
85.800 |
|
Abbreviation
|
2019-03-26 05:33:32 |
| 401 |
|
|
|
91.100 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 95.800 |
94.700 |
92.800 |
91.100 |
81.400 |
90.900 |
90.300 |
93.700 |
91.100 |
|
Abbreviation
|
2019-04-01 09:40:18 |
| 402 |
DAN |
|
|
89.400 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 95.500 |
93.800 |
90.700 |
88.500 |
79.600 |
88.300 |
88.000 |
92.200 |
89.400 |
|
Abbreviation
|
2019-04-08 02:25:28 |
| 410 |
ZFpose |
|
|
6.800 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 13.400 |
8.400 |
5.800 |
5.400 |
5.300 |
4.200 |
3.600 |
8.300 |
6.800 |
|
Abbreviation
|
2019-04-08 05:45:30 |
| 411 |
ZFpose |
|
|
84.500 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 93.200 |
91.100 |
86.400 |
83.000 |
73.900 |
81.100 |
80.300 |
88.500 |
84.500 |
|
Abbreviation
|
2019-04-09 08:01:50 |
| 413 |
|
|
|
72.300 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 90.700 |
81.300 |
72.300 |
71.800 |
59.100 |
60.800 |
64.300 |
79.200 |
72.300 |
|
Abbreviation
|
2019-04-21 11:17:27 |
| 422 |
S_9 |
|
|
92.000 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 96.300 |
95.300 |
93.700 |
92.200 |
82.800 |
92.000 |
91.100 |
94.400 |
92.000 |
|
Abbreviation
|
2019-06-02 20:03:01 |
| 399 |
|
|
|
73.200 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 91.400 |
81.600 |
72.100 |
73.800 |
57.800 |
61.800 |
69.400 |
80.000 |
73.200 |
|
Abbreviation
|
2019-05-06 09:40:08 |
| 285 |
G |
|
|
90.200 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 95.700 |
94.400 |
92.400 |
90.400 |
79.600 |
89.300 |
88.600 |
93.300 |
90.200 |
|
Abbreviation
|
2019-06-01 11:10:22 |
| 434 |
666 |
|
|
92.000 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 96.200 |
95.300 |
93.800 |
92.400 |
82.500 |
91.800 |
91.100 |
94.500 |
92.000 |
|
Abbreviation
|
2019-06-02 21:40:56 |
| 398 |
|
|
|
92.600 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 96.600 |
95.800 |
94.300 |
93.000 |
83.300 |
92.800 |
92.300 |
95.000 |
92.600 |
|
Abbreviation
|
2019-06-02 15:14:57 |
| 516 |
try_0 |
|
|
0.200 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 0.500 |
0.200 |
0.200 |
0.300 |
0.100 |
0.200 |
0.100 |
0.300 |
0.200 |
|
Abbreviation
|
2020-06-11 03:22:15 |
| 538 |
|
|
|
89.400 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 95.300 |
93.900 |
91.000 |
88.900 |
79.100 |
87.900 |
88.400 |
92.400 |
89.400 |
|
Abbreviation
|
2020-12-21 08:38:15 |
| 543 |
NPP |
|
|
88.900 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 95.800 |
93.600 |
90.300 |
88.500 |
79.000 |
86.700 |
86.700 |
92.200 |
88.900 |
|
Abbreviation
|
2021-01-31 03:18:11 |
