amirmk89

Thank you both for your work and useful insights. @fjchange , what results are you getting using the reimplementation when scoring as Liu et al.?

Thank you, and what are the best results you are able to achieve using your reimplementation? both calculated as the authors and as Liu et al.?

> At my bst, as the authors, > > * Avenue 64.11% (only 5500 object detected in training part) > * ped2 86.51% > * ShanghaiTech 80.35% > No norm,...

Thank you for your questions, it's been a while so I'll do my best to answer these, but the paper/code remembers best :) * Train/Test split - NTU clips have...

Hi! Thanks, it is available on the NTU website and requires registration, I'm unable to share it myself. Amir On Tue, Aug 24, 2021, 06:38 philno27 ***@***.***> wrote: > Thank...

Hi, Thank you for your question. It may depend on the environment settings, as the two results you got are also very different from one another, and in my experience...