Jiaheng Liu comments

Results 10 comments of


                                            Jiaheng Liu

Training error in VIDSTG.

I have run for 500 iters successfully. This error happens randomly.

Training error in VIDSTG.

Could you provide the download link of the ffmpeg (4.2.2 amd64 static)? Besides, I also suppose the generated annotation json files after processing may be not accurate. Could you provide...

The question on the curve of Figure 3

Hi, thanks for your kind reply. This is a nice work, and I am following your work for other video understanding task. I still have one question. The inference strategy...

The question on the curve of Figure 3

There is an error. The TSN can be parallel, but the TSM can not be parallel(due to shift operation.)

The question on the curve of Figure 3

Thanks.

The question on the curve of Figure 3

Hi, I have a question about the details of the ablation study on "skipping" in table 4. You mentioned that you only use the policy network to decide how many...

SoftGroup model trained on kitti dataset

@thangvubk Could you provide the training script of the kitti dataset? Just like the ScanNet and S3DIS

Anyone got approved?

![image](https://user-images.githubusercontent.com/27964642/222317821-1e7cff25-de3e-4105-8a41-e54776113a4e.png) I have got the URL. But this URL is not worked

Question on the train_net.sh

Besides, could you provide a training log of your baseline model? I just want to confirm that whether I have split the train and validation splits in the right way....

Tokenizer alignment code

I have the same question. Could you share the alignment code?