3-D Human Pose Estimation Using Iterative Conditional Squeeze and Excitation Networks
IEEE Transactions on Cybernetics(2022)
摘要
We propose a new method for single-camera real-world 3-D human pose estimation. Our method uses multitask training together with iterative pose refinement using a novel conditional attention mechanism. For iterative pose refinement, the output of each convolutional layer is conditioned on the latest pose estimate, using a conditioned squeeze-and-excitation network architecture that incorporates no...
更多查看译文
关键词
Pose estimation,Network architecture,Space heating,Task analysis,Optimization,Joints,Iterative methods
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要