-
-
Hi,
when I reproduced the test process, I found that the results were inconsistent with the results reported in your paper. Especially on MSVD dataset, there was a large gap.
When I use **test.yam…
-
Thanks for the great work!
I notice that in the Table 4 of your paper, PDVC can achieve "B@4 11.80| M 15.93 | C 27.27" in ActivityNet Captions ae-val set, but it is "B@4 10.18 | M 15.96 | C 20.66" f…
-
Hi,
Thank you for sharing your work and congrats on the paper.
I am trying to extract 100m video features using the video embedding network provided by Miech et al., 2020 (https://github.com/antoi…
-
What gpus and how many gpus do you use for training? How long does it take?
-
I follow the command
`python -m pip install -vq .`
and get this error:
`Building wheels for collected packages: scenic
Building wheel for scenic (setup.py) ... error
error: subprocess-exited-…
-
微博内容精选
-
I tested your model on YouCookII with this [protocol](https://github.com/antoine77340/S3D_HowTo100M/issues/2) (4x32 contiguous frames at 10FPS). I extrcated images from video in two ways.
1. `ff…
-
I took this model
```
wget https://www.rocq.inria.fr/cluster-willow/amiech/howto100m/s3d_howto100m.pth
wget https://www.rocq.inria.fr/cluster-willow/amiech/howto100m/s3d_dict.npy
```
and code fro…
-
Hi, I experimented with your code, but the performance at YouCook2, Yocook2+HowTo100M written in the paper was not reproduced.
I experimented with
OS: Ubuntu 20.04
CUDA: 11.2
torch: 1.9.0 + cu11…