OmniVec (pretrained)

Reported on 4 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

VideoonMSR-VTT-1kA
text-to-video R@10· uses extra data· 2023-11-07
78.6
best: 90.8 (HunYuan_tvr (huge))
OmniVec: Learning robust representations with cross modal sharing arXiv:2311.05709
VideoonYouCook2
text-to-video R@10· uses extra data· 2023-11-07
64.2
best: 80.8 (VAST)
OmniVec: Learning robust representations with cross modal sharing arXiv:2311.05709
Video RetrievalonMSR-VTT-1kA
text-to-video R@10· uses extra data· 2023-11-07
78.6
best: 90.8 (HunYuan_tvr (huge))
OmniVec: Learning robust representations with cross modal sharing arXiv:2311.05709
Video RetrievalonYouCook2
text-to-video R@10· uses extra data· 2023-11-07
64.2
best: 80.8 (VAST)
OmniVec: Learning robust representations with cross modal sharing arXiv:2311.05709