search

BJTUJia / person_reID_DualNorm

This is the pytorch implementation of our BMVC 2019 paper "Frustratingly Easy Person Re-Identification: Generalizing Person Re-ID in Practice"
24 stars 4 forks source link

Question #1

Open edrdos101 opened 5 years ago

edrdos101 commented 5 years ago

Hi! Thanks for sharing your work

Do you plan on sharing how to run inference on the "in the wild" data? If not, can you suggest the way to rank images based on extracted features?

Thanks

BJTUJia commented 5 years ago

Hi， many thanks for your interest in our work. So far I haven't tried inference on the "in the wild" data, but it's in our future plan. As for ranking images, I am not sure what you mean, but with the extracted features, distances and similarity between query and gallery images can be easily computed. Gallery images can be simply ranked by sorting them according to their distance to the query in an ascending manner.