3DV-Action icon indicating copy to clipboard operation
3DV-Action copied to clipboard

Action Recognition CVPR2020

Results 5 3DV-Action issues
Sort by recently updated
recently updated
newest added

Hi, Thanks for your great work. Recently I use the construction code to process NTU60 dataset, but I don't know what the meaning of Seg_i and v_i , consequently I...

很抱歉打扰您。我在复现代码的过程中遇到了一些问题,希望得到您的解答。NTU120_Net模块train.py中group_points_pro我并未在代码中找到这个函数,以及module中from utils import group_points_2,group_points_2_3DV,都未找到这些函数。我在论文中看到您使用了四个数据集,NTU RGB数据集十分庞大,请问您是使用了其中的全部深度数据吗?还是仅仅使用您百度云分享的数据就可以了呢?

Hi, Thanks for your interesting work. I use the python code to train the 3DV-PointNet++ on NTU 60. However, I only get 93.4 for cross_view and 85.6 for cross_subject. I...

#file_dir = 'D:\\MY_Paper\\3ddi\\pointclouddemo\\S001C001P001R001A058' file_dir = 'D:\\MY_Paper\\3ddi\\pointclouddemo\\S026C002P076R002A098' file_dir = 'D:\\MY_Paper\\3ddi\\data_depth\\Make_OK_sign\\S025C003P068R001A071' file_dir = 'D:\\MY_Paper\\3ddi\\pointclouddemo\\S001C001P001R001A051_ljy\\S001C001P001R001A051' #file_dir = 'D:\\MY_Paper\\3ddi\\data_depth\\Move_object\\S019C003P051R002A092' hi 请问你们有这些数据嘛 可以上传测试一下嘛 想看看效果

S001C001P001R001A001 Traceback (most recent call last): File "ntu120_3dv_pre.py", line 240, in main() File "ntu120_3dv_pre.py", line 149, in main points_xyzc = np.concatenate((xyz,cc.T), axis = 1) #final 3DV point feature shape N*(x,y,z,m_g,m_1,...m_t)...