Retrieval-Augmented-Visual-Question-Answering
Retrieval-Augmented-Visual-Question-Answering copied to clipboard
This is the official repository for Retrieval Augmented Visual Question Answering
Thank you very much for your work on FVQA 2.0. I noticed that the augmentation training data is not included in the released resources here: [https://github.com/LinWeizheDragon/Retrieval-Augmented-Visual-Question-Answering/blob/main/FVQA2.0.md](url). May I ask if...
Hello, I tried to run the inference of RAVQAv2. When using the following command, an error occurred in the code when calling the `eval()` method of the RunwayExperiment class. The...
关于知识库的问题
作者你好,请问论文里提及的wikipedia corpus for OK-VQA应该在哪里下载呢,我在github提供的数据集里面似乎没有找到,感谢🙏
Hi, I am trying to extract the features of Visual Genome (VG-100K) with VinVL. I have converted the images to TSV format with the given script but because I do...