TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/QB-Norm+CLIP2Video

QB-Norm+CLIP2Video

Reported on 20 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Computer Vision20 results

  • VideoonVATEX
    text-to-video R@10· uses extra data· 2021-12-23
    93.8
    best: 100 (GRAM)
    SOTA
    Cross Modal Retrieval with Querybank NormalisationarXiv:2112.12777
  • Video RetrievalonVATEX
    text-to-video R@10· uses extra data· 2021-12-23
    93.8
    best: 100 (GRAM)
    SOTA
    Cross Modal Retrieval with Querybank NormalisationarXiv:2112.12777
  • VideoonMSR-VTT-1kA
    text-to-video Median Rank· uses extra data· 2021-12-23
    2
    best: 13 (JSFusion)
    Cross Modal Retrieval with Querybank NormalisationarXiv:2112.12777
  • VideoonMSR-VTT-1kA
    text-to-video R@1· uses extra data· 2021-12-23
    47.2
    best: 62.9 (HunYuan_tvr (huge))
    Cross Modal Retrieval with Querybank NormalisationarXiv:2112.12777
  • VideoonMSR-VTT-1kA
    text-to-video R@10· uses extra data· 2021-12-23
    83
    best: 90.8 (HunYuan_tvr (huge))
    Cross Modal Retrieval with Querybank NormalisationarXiv:2112.12777
  • VideoonMSR-VTT-1kA
    text-to-video R@5· uses extra data· 2021-12-23
    73
    best: 84.5 (HunYuan_tvr (huge))
    Cross Modal Retrieval with Querybank NormalisationarXiv:2112.12777
  • VideoonVATEX
    text-to-video R@1· uses extra data· 2021-12-23
    58.8
    best: 87.7 (GRAM)
    Cross Modal Retrieval with Querybank NormalisationarXiv:2112.12777
  • VideoonMSVD
    text-to-video Median Rank· uses extra data· 2021-12-23
    2
    best: 6 (SSML)
    Cross Modal Retrieval with Querybank NormalisationarXiv:2112.12777
  • VideoonMSVD
    text-to-video R@1· uses extra data· 2021-12-23
    48
    best: 61.4 (InternVideo2-6B)
    Cross Modal Retrieval with Querybank NormalisationarXiv:2112.12777
  • VideoonMSVD
    text-to-video R@10· uses extra data· 2021-12-23
    86.2
    best: 90.3 (HunYuan_tvr (huge))
    Cross Modal Retrieval with Querybank NormalisationarXiv:2112.12777
  • VideoonMSVD
    text-to-video R@5· uses extra data· 2021-12-23
    77.9
    best: 87.6 (CAMoE)
    Cross Modal Retrieval with Querybank NormalisationarXiv:2112.12777
  • Video RetrievalonMSR-VTT-1kA
    text-to-video Median Rank· uses extra data· 2021-12-23
    2
    best: 13 (JSFusion)
    Cross Modal Retrieval with Querybank NormalisationarXiv:2112.12777
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@1· uses extra data· 2021-12-23
    47.2
    best: 62.9 (HunYuan_tvr (huge))
    Cross Modal Retrieval with Querybank NormalisationarXiv:2112.12777
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@10· uses extra data· 2021-12-23
    83
    best: 90.8 (HunYuan_tvr (huge))
    Cross Modal Retrieval with Querybank NormalisationarXiv:2112.12777
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@5· uses extra data· 2021-12-23
    73
    best: 84.5 (HunYuan_tvr (huge))
    Cross Modal Retrieval with Querybank NormalisationarXiv:2112.12777
  • Video RetrievalonVATEX
    text-to-video R@1· uses extra data· 2021-12-23
    58.8
    best: 87.7 (GRAM)
    Cross Modal Retrieval with Querybank NormalisationarXiv:2112.12777
  • Video RetrievalonMSVD
    text-to-video Median Rank· uses extra data· 2021-12-23
    2
    best: 6 (SSML)
    Cross Modal Retrieval with Querybank NormalisationarXiv:2112.12777
  • Video RetrievalonMSVD
    text-to-video R@1· uses extra data· 2021-12-23
    48
    best: 61.4 (InternVideo2-6B)
    Cross Modal Retrieval with Querybank NormalisationarXiv:2112.12777
  • Video RetrievalonMSVD
    text-to-video R@10· uses extra data· 2021-12-23
    86.2
    best: 90.3 (HunYuan_tvr (huge))
    Cross Modal Retrieval with Querybank NormalisationarXiv:2112.12777
  • Video RetrievalonMSVD
    text-to-video R@5· uses extra data· 2021-12-23
    77.9
    best: 87.6 (CAMoE)
    Cross Modal Retrieval with Querybank NormalisationarXiv:2112.12777