20% is an incredibly high number though, if a store has 400 people/hour that means you're manually reviewing 80 transactions per hour, over one transaction per minute. That's multiple human employees.
One transaction per minute is nothing at all when the transaction can be as simple as "did the person put that back on the shelf" with a 5 seconds clip.
Hum, yes it does? It's not because it's not a complex action that it's necessarily supported by the models.
It's not hard to imagine edge scenarios for which the models aren't trained, like a customer dropping an item, or putting an item back in a random shelf instead of the one it's intended for, or someone picking up that previously randomly placed item, etc.
Just a big assumption on your part when the more reasonable conclusion was just that it was not working and it was not a 5 second thing (hence why receipts were taking so long, etc).
