Wenzheng Zeng comments

Results 9 comments of


                                            Wenzheng Zeng

Could you please release the indexes of the 38365 points selected from the original 09 BFM?

Hi! I have the same question about the correspondence between the 38365 indexs and its actual position on face. Anyone could help?

About the online inference

Thanks for your great work. Can you release the code of the near online inference? A demo code with a smaller input clip length (e.g., 15) on YouTubeVIS2019 would be...

The loss function seems to be error

> About the seconde question, I have found the answer. Torch.nn.CrossEntropyLoss() combines nn.LogSoftmax() and nn.NLLLoss() in one single class. So is the implementation here of ArcFace loss right?

Landmark detection example.

Thanks for your great work! Can you provide a demo for face alignment?

Getting Inference time for SCRFD_500M => 31.227 millisecond vs 3.6 millisecond claimed ? how ?

@jiangxiangchuan I obtain a similar result on 3090. I think the reported time (i.e., 4.9ms) just contains the session.run function. The time for data pre-processing is not included.

An error and a warning when run setup.py

Can this code work with torch>1.7.0? The reason is that my CUDA version is 11, which may not work with torch 1.4. I have tried to run setup.py but failed,...

What is the schedule for uCF24

Thanks for the great work. Can you give an approximate date for the code release of UCF24? Thanks.

Questions about the code for JHMDB

Thank you very much for the detailed reply! I am looking forward to the complete version of the TubeR-UCF code.

Questions about the code for JHMDB

Hi. I have one more question. Since the input of TubeR is a video clip, how to merge the prediction results from the adjacent clips? Is the same linking strategy...