pytorch-coviar issues

Question about pre-processing mv and res

2

Hi man, thanks for ur good work, but i have some questions about mv and res normalization, could u pls explain in more detail about the code below? ```if self._representation...

gbyy422990

How to combine the score of CoViAR with the score of TSN?

5

After obtained the score of CoViAR, how to combine the score with TSN by late fusion? Is there any file I can use to complete this process, thank you very...

ZealACMer

Encode videos to another gop, how to adjust coviar_data_loader

1

Hi, I want to use gop = 16 ,I'm changing reencode.sh to eencode with " -g " , and I know that the data_loader doesn't like that (got segmentation fault),...

Esaada

Training parameters

3

Are the training parameters specified in the GETTING_STARTED the exact parameters that produce the expected results? (They look different from the paper). I tried the same setting given in the...

shiyuanh

About counting frames

2

I find the value of function get_num_frames is 1 less than actual video length. I use 100 frames to create a video but only get 99 decoded frames. I find...

sjtuxcx

Visualise the MV

4

Hi, in the paper you said you visualised the MV using HSV Color space, I couldn't find the code, is he attached? Thanks.

albertBohar

Training Error

8

Hi, I tried your code to reproduce the coviar result in your paper. I followed all your instructions in GET_START.md But I met this error: ` v_frame_idx = random.randint(seg_begin,seg_end -...

tzzcl

How to obtain the residual information?

1

According to the code that the residual information is obtained by subtracting the two frames, can it be directly extracted from the compressed video?

lshiwjx