Zhi Hou

Hi, thanks for your questions. That's a redundant code. It is for debug and ablation studies. From line137-149, the code is actually similar to the code in line150. However, you...

Feel free to post questions. Actually, I am also curious about BatchFormer and I am still working on a general version of BatchFormer. Please refer to [BatchFormerV2](https://arxiv.org/abs/2204.01254)

Thanks! It is really encouraging.

Sorry for getting you latter. A1: Yes, you can understand like that. A2: We can concat the two outputs of the classifier, and calculate the loss with the Ground Truth....

Sorry for the removed url. Could you try this url? https://drive.google.com/file/d/1QZcJmGVlF9f4h-XLWe9Gkmnmj2z1gSnk/view feel free to comment if u have further questions.

I thought it might be the issue from the update in google drive. I recently can’t not download file with gdown. I can download the file on safari. Could u...

Hi @PradKalkar, Thanks for your comment. There is indeed some issue in ``lib/ult/Download_data.py`` file. I have switch to use gdown to download the files, and update the script. Many Thanks...

Hi, I am sorry that I did not implement this repo based on PyTorch successfully. (see this failed repo https://github.com/zhihou7/VCL_Pytorch, I find it is not convergent). I implement the compositional...

Hi, thanks for your interest. In fact, we also spent a long time to understand affordance. Sorry for still causing you confusion. Affordances (also related to functionalities) mean what actions...

Sorry for getting confusing you. The object detection results provide both object category information and bounding boxes. Here, we only use the bounding boxes for inferring the HOI category. The...