George Balaouras

@Anurag14 A bit late to the party, but... do you have a working implementation of the dpp loss? I cant get over the paper statement for the L(s) > L(s)...

> Regarding feature vectors, did you normalize this? I mean in the MSVA repo they used RGB and FLOW feature vectors but they don't specify if they transform this or...

The logic behind normalization of the different features, is that you must convert the matching scores with **different** scales into a **common domain**. Once the matching scores are normalized, they...

> Thank you very much @mpalaourg ! Your answer was very clear and I agree with you. That's right, and the last two weeks I've been experimenting with different functions....

> No, I haven't train in all the data. I used cross validation too (there is no an official split so that's another problem), to evaluate the performance of the...

@StevRamos sorry for the late reply, but deadlines this month was crazy and I didn't have any time to response. Our work (Camera ready version) isn't publish on IEEE Xplore...

Hi @StevRamos, the pre_print version of our work was uploaded in my site (https://mpalaourg.me/#publications). Hope to find it interesting!