The Beautiful Future
Simple and Lightweight Human Pose Estimation 본문
Zhe Zhang, Jie Tang and Gangshan Wu, Nanjing University, China
depthwise convolution and attention mechanism
Lightweight Pose Network (LPN)
LPN-50 can achieve 68.7 in AP score on the COCO test-dev set,
2.7M parameters and 1.0 GFLOPs, while the inference speed is 17 FPS on an Intel i7-8700K CPU
Simple baselines for human pose estimation and tracking ECCV2018과 유사한 구조.
Attention Mechanism
Multi-context attention for human pose estimation, in Proceedings CVPR 2017, first HPE
Gcnet: Non-local networks meet squeeze-excitation networks and beyond, upgrade NLNet + GC + SENet
NLNet: non local network
GC : global context, retain long-range dependencies
'논문' 카테고리의 다른 글
Comments