Name
Abstract | ||
|---|---|---|
We propose a novel method for multi-person 2D pose estimation. Our model zooms in the image gradually, which we refer to as the Magnify-Net, to solve the bottleneck problem of mean average precision (mAP) versus pixel error. Moreover, we squeeze the network efficiently by an inspired design that increases the mAP while saving the processing time. It is a simple, yet robust, bottom-up approach consisting of one stage. The architecture is designed to detect the part position and their association jointly via two branches of the same sequential prediction process, resulting in a remarkable performance and efficiency rise. Our method outcompetes the previous state-of-the-art results on the challenging COCO key-points task and MPII Multi-Person Dataset. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/ICME.2018.8486591 | 2018 IEEE International Conference on Multimedia and Expo (ICME) |
Keywords | Field | DocType |
Deep Learning,Convolutional Neural Network,Multi-Person Pose Estimation,Magnify-Net | Sequence prediction,Computer vision,Bottleneck,Architecture,Pattern recognition,Convolution,Computer science,Feature extraction,Pose,Pixel,Artificial intelligence,Image resolution | Conference |
ISSN | ISBN | Citations |
1945-7871 | 978-1-5386-1738-0 | 0 |
PageRank | References | Authors |
0.34 | 6 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Wang H | 1 | 71 | 29.35 |
| W. P. An | 2 | 0 | 0.34 |
| Xingzheng Wang | 3 | 0 | 1.35 |
| Lu Fang | 4 | 343 | 55.27 |
| Jiahui Yuan | 5 | 0 | 0.34 |