-
Hello Author:
I have recently reproduced your paper, and according to the data set you gave, it is 'number': 50.91 in vqa-2.0.
'other': 59.45,
'overall': 69.13,
'yes/no': 85.29}}
The result is a …
-
Visual Quality Assurance (VQA) issues numerical scores for the user-perceived quality of an endcoded video segment. Multiple different types of scoring exists - VMAF, PSNR, SSIM etc.
The proposal i…
-
Hello
I think you are doing a fantastic job! However, I am now having some problems reproducing your experimental results, the problem reads as follows: i am reproducing the VQA_RAD dataset very po…
-
Hello, this error occurred when I wanted to train the model. How can I download this pth file?
/home/jinw/anaconda3/envs/KVQ/lib/python3.8/site-packages/torch/functional.py:504: UserWarning: torc…
ads2d updated
2 weeks ago
-
In your paper, from the table of “Results of adding individual techniques of our framework in text-rich VQA benchmarks“,I get the improvement vals of +7.40% ,+31.72%,etc. I want to kn…
-
Hi team,
I'd be interested to see whether we could add the [MobileCaptureVQA](https://huggingface.co/datasets/arnaudstiegler/mobile_capture_vqa) dataset on this benchmark.
This VQA dataset focused…
-
Hi,
Can you add the VQA fine-tuning function of BLIP2?
In the paper, when you fine-tune the VQA task, you will fine-tune the image encoder. When I use the `freeze_vit: False` command.
But I encoun…
-
Hello
Thanks for your great work!
Is the code of the video-mamba-suite on EgoSchema released?
-
Wonderful work! Could you provide the relevant files and training and testing files of RAD dataset?
For example, train_labeldir = r'/Dataset1/cjw/VQA_RAD/train.jsol'
test_labeldir = r'/Dataset1/cjw/…
-
I am using Lora to finetune Qwen-VL model, there are about 10,000 VQA data samples I used for finetuning, but the loss of final model is still high, I set train epoch == 3, did I need to increase the …