Wang Tan

I have just found that the `embeddings` module is in `RobertaAdapterModel.roberta`. Therefore, a simple method is to just set `model = RobertaAdapterModel.roberta`. What's the difference of `RobertaAdapterModel` and `RobertaAdapterModel.roberta`? Can...

Hi, sorry for the delay replay since I haven't seen the issue. Actually, the triplet loss is hard to converge and the parameters are very important and sensible. The loss...

Hi, I have checked the results and training. It seems normal in my case. And I also just find that the previous user can implement the results with this code...

Hi, I think use feature mean is not a bad idea. However, a more important thing you may notice is that, if the video frame has clear objects. Since VC...

Hi, 1. Yolov5 can be ok for extracting the bounding box. 2. For the whole image size bounding box, I think 2 options you mentioned can both be ok. 3....

Hi, sorry for the late reply. The re-ranking is exactly used and it's a kind of "an after treatment". As discussed in paper, the rerank is not a loss during...

Hi, the T2i rerank needs to train the text-text fusion network firstly to get the similarity between sentences. BTW, what the "unbelievable results" represent? Actually, the Rerank performance just depends...

1. The t2i results is slightly better than i2t : I am not sure about this actually, since the i2t and t2i results don't have very close relation. 2. Because...

Hi, the i2t rerank is exactly right as I just said. For the t2i rerank (which is commented in the 'rerank.py' now), if you directly run, it will use the...