-
I just used an A800 and changed the batch size to 32. The other parameters are consistent with the appendix of the paper. Why can I only achieve 53%
-
Excuse me,thank you for your excellent project. I have successfully reproduced it on two datasets, MSRVTT and MSVD.
But when I reproduced it on the LSMDC dataset, the performance was much worse th…
-
In the Line 85 of [SwinBERT](https://github.com/microsoft/SwinBERT/tree/main/prepro)/create_image_frame_tsv.py.
" current_image_path = previous_image_path "
Does it mean when the amount of extra…
-
Hi, I found MSVD-QA json files in previous issues, but the msvd_qa_answer_list.json seems to be missing.
Could you please provide it? Thanks!
-
Hi, we appreciate your two papers and have thoroughly examined them.
The replication process for the MSRVTT results on Mug-STAN was successful, yielding outcomes that closely align with the paper's…
-
您好,您在这个repo的首页提到了用finetuned CLIP提取视频特征,finetune时候用的是CLIP4CLIP的方式,请问这个finetuned CLIP checkpoint可以提供一下吗?
谢谢!
-
-
Thanks for your work!
Could you upload the model's pretrained checkpoint file?
I want to test with the weights file to caption video input.
Thank you
-
Hi,
Thanks for your code. I found there is a gap comparing the recorded results (on the paper or the repo) after I exactly followed the "test" code. Here are my results:
MSVD:
RESULTS: Bleu_1: …
-
Thanks for the great work.
I evaluate the zero-shot performance of the 25M pre-trained ckpt on the DiDeMo dataset, my command is
```
export VL_DATA_DIR=/home/renshuhuai/VindLU/
export VL_EXP_DIR…