Knowledge
DIS-CO (MovieTection)
Individual movie-title guesses from four vision-language models, queried with movie frames or their released captions.
28,000items
4subjects
MovieTection frames and captions: CC-BY-NC-SA-4.0. DIS-CO code and result repository: Apache-2.0, as declared upstream.license
knowledgedomain
imagemodality
textmodality
item-level responses released
Saturation status: No
Response matrix
Loading response matrix…
Correct (1)Incorrect (0)Unobserved
Scale: 1 = correct · 0 = incorrect