3D CNNs and MViT #22

Open

dhruvgrover1251

opened

on Mar 25, 2022

Hi,
Can I use this to generate attention maps for video action recognition done using models such as r3d18, i3d, r2plus1d18? Also, can it be used for transformer models like MViT?
Thank You!

Metadata

Assignees

No one assigned

Labels

No labels

No labels

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests