News for hackers. Stuff that matters.

A comment on Show HN: OmniNet:- A unified architecture for multi-modal multi-task learning. Parent comment

Re:Show HN: OmniNet:- A unified architecture for multi-modal... by subho406 on Friday July 19, 2019 @04:54PM (#20482361)
The model was trained on video classification, image qa and image captioning. Video captioning and video qa is not trained, yet the model shows results on those tasks.
[ Parent | on HN ]

There are no comments on this comment yet.