Pose-Group / DCPose

This is an official implementation of our CVPR 2021 paper "Deep Dual Consecutive Network for Human Pose Estimation" (https://openaccess.thecvf.com/content/CVPR2021/papers/Liu_Deep_Dual_Consecutive_Network_for_Human_Pose_Estimation_CVPR_2021_paper.pdf)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

两个问题

shoutOutYangJie opened this issue · comments

  1. 在测试阶段,使用的行人检测框架是?
  2. 从当前帧crop出的人体,扩大25%用于截取前一帧和后一帧的同一个人体,这是假设时序连贯。但你们如何能将整个视频的同一个人物的相同节点连贯起来? 这才是tracking的定义,论文中没有提到。

谢谢。

Thanks for your questions.

Problem 1

To ensure the fairness of the method comparison, we use the bounding box detection results provided by posewarper.

Problem 2

DCPose focuses on solving the human pose estimation for video and does not involve tracking.