Video-Action-Transformer-Network-Pytorch-
Video-Action-Transformer-Network-Pytorch- copied to clipboard
Query, key, and value are different from the paper
Hi!
In the paper, it mentions that the query is an ROI, and key and values are from the clip around an ROI. But in this implementation, it seems that all query, key and value are from the features in the same spatial locations. In that case, it will not be able to aggregate another person that the target person is talking to.
Please clarify this I am mistaken. Thank you very much!