Sobeney

@joaanna , I can't achieve the result reported in your paper with I3D model. When using compositional split, the Top1 result should be 46.8 according to your paper, but I...

@ruiyan1995 have you tried the globel_i3d and get the expected result?

> > @ruiyan1995 have you tried the globel_i3d and get the expected result? > > I tested the VideoModelGlobalCoordLatent without overriding the default train function, it works. I guess the...

> @Sobeney Did you get the expected acc on I3D baseline? I have the same problem. No, the result of i3d is still far to paper. But according to your...

> Hi @ruiyan1995 @Sobeney, what's your final result on global_coord_latent and coord_latent_nl? It looks like difficult to achieve the reported result. 52.3 for global_coord_latent, haven't try coord_latent_nl yet.