Skip to main content
zenodoopen

Keyframe-level Captions for V3C

<p>Image captions generated using <a href="https://github.com/j-min/CLIP-Caption-Reward">CLIP-Caption-Reward</a> and <a href="https://github.com/rmokady/CLIP_prefix_caption">CLIP_prefix_caption</a> for every Keyframe in the Vimeo Creative Commons Collection. Captions are grouped by captioning method and dataset shard and provided as CSV.</p>

ShareScore

40/100

Overall dataset sharing score

Score breakdown

These five areas show where the dataset supports — or may limit — practical reuse.

Stewardship
4
Harmonization
8
Access
20
Reuse readiness
8
Engagement
0