-
I have some questions about the algorithm of qb-norm described as follows.
The process described in paper is  and fine-tuned the model o…
-
Hi ,
I saw "We pre-train ALPRO for 100k iterations, roughly equivalent to 10 epochs" in your paper. So there will be ten checkpoints, which one is the zero-shot checkpoint for testing MSRVTT, and h…
-
Dear Author, really thanks you all for opening this open source.
I'm a novice and do not have much techniques in dealing with and running all kinds of framework, so today, I've been suffered from …
-
Hi, thank you so much for such an excellent job!
Can you provide the raw text data (including objects, actions, speech, OCR, etc.) extracted from the MSRVTT dataset. Because [here](http:/www.robots.o…
ezeli updated
2 years ago
-
I experiment the finetune procedure and run the command `python train.py --config configs/msrvtt_4f_i21k.json`.
I got:
```
[v2t_metrics]MSRVTT epoch 27, R@1: 16.1, R@5: 40.5, R@10 55.0, R@50 81…
-
when I using MSRVTT dataset, some errors happened, log is "video path: /home/admin/workspace/workgroup/mayiwei.myw/data/MSRVTT/data/MSRVTT/videos/all/video5397.mp4 error. video id:video5397"
![image]…
-
Hi,
Thanks for sharing the code!
I saw "use 7k videos for training and report results on the 1k test split" in your paper. When I downloaded the MSR-VTT dataset, there are only 7K train sets and …
-
Dear author,
I tried to use the released checkpoints (model_base_retrieval_coco.pth and model_large_retrieval_coco.pth) to test on the msrvtt retrieval dataset, but I got R1 35.8 and 39.74, respect…