Overview
We offer a benchmark suite together with an evaluation server, such that authors can upload their results and get a ranking. We offer a Dataset that contains more than 50000 pictures, including 30462 images for training set, 10000 images for validation set and 10000 images for test set. If you would like to submit your results, please register, login, and follow the instructions on our submission page.
Note: We only display the highest submission of each person.
Single-Person Human Pose Estimation Track
Metrics
Followed MPII, we use PCKh evaluation measure with Person-Centric (PC) annotations.
| User Id |
Method |
|
|
PCKh |
|
Details |
Abbreviation |
Submit Time |
| 82 |
NTHU-Pose |
|
|
87.400 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 94.900 |
93.100 |
89.100 |
86.500 |
75.700 |
85.500 |
85.700 |
91.000 |
87.400 |
|
Abbreviation
| Contributors |
Description |
| Self Adversarial Training for Human Pose Estimation,
Chia-Jung Chou, Jui-Ting Chien, and Hwann-Tzong Chen,
National Tsing Hua University |
We adapt Boundary Equilibrium GAN as our learning model in which we set up two stacked hourglass networks, one as the generator and the other as the discriminator. The generator is used as a pose estimator after the training is done. The discriminator distinguishes ground-truth heatmaps from generated ones, and back-propagates the adversarial loss to the generator. This process enables the generator to learn the plausible human body configurations. The entire model is trained from scratch using only the LIP training data. |
|
2017-06-02 03:06:07 |
| 59 |
Pyramid Stream Network (Multi-Model) |
|
|
82.100 |
|
Details
| Head |
Shoulder |
Elbow |
Wrist |
Hip |
Knee |
Ankle |
UBody |
Total |
| 91.100 |
88.400 |
82.200 |
79.400 |
70.100 |
80.800 |
81.200 |
85.400 |
82.100 |
|
Abbreviation
| Contributors |
Description |
| NIE Xuecheng (NUS), ZHAO Jian (NUS & NUDT), XIAO Huaxin (NUS & NUDT), CHEN Yunpeng (NUS), LI Jianshu (NUS), YAN Shuicheng (NUS & Qihoo360 AI Institute) (The first 3 authors are with equal contributions.) |
Pyramid Stream Network (PSN) is composed of a stream of pyramid units, which predict body joint confidence maps at different resolutions.
The major adavantages of PSN lie in two aspects: (1) Exploiting contextual information to iteratively refine
the confidence maps by learning implicit spatial relationships between different body joints; (2) Combining
high-resolution, semantically weak features with low-resolution, semantically strong features via a top-down
pathway and lateral connections. |
|
2017-06-03 08:03:30 |
| 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 |
