Published November 22, 2022 | Version v1

Keyframe-level Captions for V3C

Authors/Creators

  • 1. University of Zurich

Description

Image captions generated using CLIP-Caption-Reward and CLIP_prefix_caption for every Keyframe in the Vimeo Creative Commons Collection. Captions are grouped by captioning method and dataset shard and provided as CSV.

Files

CLIP_caption_reward_V3C1.csv

Files (558.8 MB)

Name Size
md5:3bcbc3ea76c2fdfb048b3f866dc7ecd5
80.7 MB Preview Download
md5:6471838bc767be83e31915a16a15f14e
106.3 MB Preview Download
md5:3198bf734819e176fb48a765c91f1056
122.0 MB Preview Download
md5:37bbb0589c15a092d52dc40c5c80f5b5
65.0 MB Preview Download
md5:8dfcc7610b881517e6f8c0d0bf645df0
86.4 MB Preview Download
md5:0269a1bcb2588d8235f2e670f77f16ae
98.3 MB Preview Download

Additional details

References

  • Cho, J., Yoon, S., Kale, A., Dernoncourt, F., Bui, T., & Bansal, M. (2022). Fine-grained image captioning with clip reward. arXiv preprint arXiv:2205.13115.
  • Mokady, R., Hertz, A., & Bermano, A. H. (2021). Clipcap: Clip prefix for image captioning. arXiv preprint arXiv:2111.09734.
  • Rossetto, L., Schuldt, H., Awad, G., & Butt, A. A. (2019, January). V3C–a research video collection. In International Conference on Multimedia Modeling (pp. 349-360). Springer, Cham.