General
MOCHI
Published per-image-set accuracy estimates for vision models identifying the different object among multiple views.
3,717items
24subjects
CC-BY-NC-SA-4.0 for benchmark assets (paper section 2.2); no separate code license is stated in the captured repository.license
visiondomain
imagemodality
item-level responses released
Saturation status: No
Response matrix
Loading response matrix…
lowhighUnobserved
Scale: Score in [-0.5, 1]