raw results
kongbia opened this issue · comments
Could you please share the raw results of VOT2018 and LaSOT
@kongbia
Hi, thank you for your interest in our work. We will provide all raw results and complete models after this paper is accepted.
Hi, I am interested in the raw numbers of NFS. In particular, do you know why your numbers for SuperDiMP (Success: 66.9) are more than 2% higher than the once reported by the authors (64.7) https://github.com/visionml/pytracking/blob/master/MODEL_ZOO.md#Raw-Results? I am just curious. Did you do anything different here? Did you use their evaluation protocol? How often did you run the stochastic tracker? I know that the authors of SuperDiMP report on five runs and then average? Could this explain the diff? Anyway, nice work and looking forward to checkout the raw results and the code.