Egocentric video sees what is in front of you; a room camera sees all of you, but only in its room. We add the active acoustics of two everyday wearables, a smartwatch and camera glasses, and ask how far they take egocentric video toward the room camera's view of unscripted cooking.
Held-out test moments, some from unseen users, people the models never saw in training. Often the room camera sees the person's back while the wearables follow the hands. The strip under each clip marks where the chosen setup names the verb right (green) or wrong (red).