Yana

Hi ! All the results in the paper are reported in hand-centric coordinates, so centered on the hand root joint. Therefore I do not provide a way to bring back...

Hi @yihui-he, I am looking into this, could you please confirm that you are trying to train on ObMan (vs First Person Hand Action Benchmark) so that I can provide...

Thank you very much ! The commit with the int casting makes a lot of sense. However, the updates in the README seem specific to your project. Depending on what...

Hi @zly9844, You should find some answers to this question [here](https://github.com/hassony2/obman/issues/2) Hope this helps ! Best, Yana

Hi @spk921 , Unfortunately, I only fitted MANO for this specific subset, as I never needed the fits for the full dataset. Yana

Hi @Ivamcoder, Were you able to figure this out ? I don't recall having memory issues for this. Best !

Dear @MengHao666, Thank you for your interest in our work :) 1. for this I used meshlab and the Quadric Edge Collapse Decimation (with texture) filter to downsample the HO3D...

@binghui-z, this is correct, thank you very much for providing your solution :)

Hi @past9767 ! Note that the models are trained on **small** datasets which carry very specific biases (objects, points of view, ...), they will therefore not generalize to in-the-wild image...

Hi Simon, As you might see [here](https://github.com/hassony2/kinetics_i3d_pytorch/blob/a4b815fb95d311bbf01734f4d1d3610f7f39cde1/i3d_pt_demo.py#L35), I don't do anything specific beyond loading their sample in my code. I therefore don't know what might cause this discrepancy. Let me...