what‘s the meaning of BOS_POSE in pose.py

[aryanna384]

Hi, I am still confused about:

1. the meaning of BOS_POSE in pose.py which used while training, is the initialization of the skeleton? How does it get? And used for what? BOS_POSE = np.array([ -0.00647944, -0.540766, -0.00655532, -0.3829, -0.0862469, -0.388304, -0.107649, -0.137507, -0.0648178, 0.0423361, 0.0791047, -0.382726, 0.0882645, -0.148286, 0.0699688, 0.0641147, 0.0056175, 0.05319, -0.0464647, 0.0476973, -0.0465082, 0.467254, -0.031224, 0.854397, 0.0576743, 0.0585055, 0.0394117, 0.478282, 0.0208931, 0.854322, -0.0158758, -0.568058, 0.0147899, -0.568106, -0.0465137, -0.568036, 0.0391742, -0.562693, 0.0209782, 0.936187, 0.0424097, 0.930442, 0.0148087, 0.886806, -0.0249588, 0.935932, -0.0434218, 0.935805, -0.0280986, 0.886854 ]) 2)How to detect kinematic beat? 3)How to use FID to evaluate?

THANKS VERY MUCH!!!

[stonyhu]

@aryanna384 Hi, could you try to visualize this BOS_POSE by the provided keypoint2img.py? It is just a predefined beginning pose.

[Givyuscss]

@stonyhu Hi, I have the same question as Aryanna, how to detect kinematic beat from the given sequence of key-points?

[stonyhu]

@Givyuscss The paper has described the details about detecting kinematic beats, please refer to Section 5.1 on Page 8.

[stonyhu]

@aryanna384 Fréchet inception distance (FID) is a well-known metric in computer vision, I think Google/Bing can give you the better answer than me with regarding to this question :)