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/CLIP2Video

CLIP2Video

Reported on 46 benchmarks across 2 tasks · 1 paper · 26 SOTA

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

Computer Vision46 results

  • VideoonMSR-VTT-1kA
    text-to-video R@1· uses extra data· 2021-06-21
    45.6
    best: 62.9 (HunYuan_tvr (huge))
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • VideoonMSR-VTT-1kA
    text-to-video R@10· uses extra data· 2021-06-21
    81.7
    best: 90.8 (HunYuan_tvr (huge))
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • VideoonMSR-VTT-1kA
    text-to-video R@5· uses extra data· 2021-06-21
    72.6
    best: 84.5 (HunYuan_tvr (huge))
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • VideoonMSR-VTT-1kA
    video-to-text Mean Rank· uses extra data· 2021-06-21
    10.2
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • VideoonMSR-VTT-1kA
    video-to-text R@1· uses extra data· 2021-06-21
    43.3
    best: 64.8 (HunYuan_tvr (huge))
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • VideoonMSR-VTT-1kA
    video-to-text R@10· uses extra data· 2021-06-21
    82.1
    best: 91.1 (HunYuan_tvr (huge))
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • VideoonMSR-VTT-1kA
    video-to-text R@5· uses extra data· 2021-06-21
    72.3
    best: 783 (PIDRo)
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • VideoonVATEX
    text-to-video R@1· uses extra data· 2021-06-21
    57.3
    best: 87.7 (GRAM)
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • VideoonVATEX
    text-to-video R@10· uses extra data· 2021-06-21
    90
    best: 100 (GRAM)
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • VideoonVATEX
    text-to-video R@50· uses extra data· 2021-06-21
    95.5
    best: 96.3 (LAFF)
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • VideoonMSR-VTT
    video-to-text R@1· uses extra data· 2021-06-21
    54.6
    best: 64.8 (GRAM)
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • VideoonMSR-VTT
    video-to-text R@10· uses extra data· 2021-06-21
    90.8
    best: 92.8 (CAMoE)
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • VideoonMSR-VTT
    video-to-text R@5· uses extra data· 2021-06-21
    82.1
    best: 86.2 (CAMoE)
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@1· uses extra data· 2021-06-21
    45.6
    best: 62.9 (HunYuan_tvr (huge))
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@10· uses extra data· 2021-06-21
    81.7
    best: 90.8 (HunYuan_tvr (huge))
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@5· uses extra data· 2021-06-21
    72.6
    best: 84.5 (HunYuan_tvr (huge))
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonMSR-VTT-1kA
    video-to-text Mean Rank· uses extra data· 2021-06-21
    10.2
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonMSR-VTT-1kA
    video-to-text R@1· uses extra data· 2021-06-21
    43.3
    best: 64.8 (HunYuan_tvr (huge))
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonMSR-VTT-1kA
    video-to-text R@10· uses extra data· 2021-06-21
    82.1
    best: 91.1 (HunYuan_tvr (huge))
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonMSR-VTT-1kA
    video-to-text R@5· uses extra data· 2021-06-21
    72.3
    best: 783 (PIDRo)
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonVATEX
    text-to-video R@1· uses extra data· 2021-06-21
    57.3
    best: 87.7 (GRAM)
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonVATEX
    text-to-video R@10· uses extra data· 2021-06-21
    90
    best: 100 (GRAM)
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonVATEX
    text-to-video R@50· uses extra data· 2021-06-21
    95.5
    best: 96.3 (LAFF)
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonMSR-VTT
    video-to-text R@1· uses extra data· 2021-06-21
    54.6
    best: 64.8 (GRAM)
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonMSR-VTT
    video-to-text R@10· uses extra data· 2021-06-21
    90.8
    best: 92.8 (CAMoE)
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonMSR-VTT
    video-to-text R@5· uses extra data· 2021-06-21
    82.1
    best: 86.2 (CAMoE)
    SOTA
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • VideoonMSR-VTT-1kA
    text-to-video Mean Rank· uses extra data· 2021-06-21
    14.6
    best: 28.2 (Collaborative Experts)
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • VideoonMSR-VTT-1kA
    text-to-video Median Rank· uses extra data· 2021-06-21
    2
    best: 13 (JSFusion)
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • VideoonMSR-VTT-1kA
    video-to-text Median Rank· uses extra data· 2021-06-21
    2
    best: 5 (CLIP)
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • VideoonMSR-VTT
    text-to-video Mean Rank· uses extra data· 2021-06-21
    45.4
    best: 213.8 (JEMC)
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • VideoonMSR-VTT
    text-to-video Median Rank· uses extra data· 2021-06-21
    4
    best: 55 (C+LSTM+SA+FC7)
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • VideoonMSR-VTT
    text-to-video R@1· uses extra data· 2021-06-21
    29.8
    best: 64 (GRAM)
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • VideoonMSR-VTT
    text-to-video R@10· uses extra data· 2021-06-21
    66.2
    best: 89.6 (VAST)
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • VideoonMSR-VTT
    text-to-video R@5· uses extra data· 2021-06-21
    55.5
    best: 84.3 (VAST)
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • VideoonMSR-VTT
    video-to-text Mean Rank· uses extra data· 2021-06-21
    5.3
    best: 134 (JEMC)
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • VideoonMSR-VTT
    video-to-text Median Rank· uses extra data· 2021-06-21
    1
    best: 16 (JEMC)
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonMSR-VTT-1kA
    text-to-video Mean Rank· uses extra data· 2021-06-21
    14.6
    best: 28.2 (Collaborative Experts)
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonMSR-VTT-1kA
    text-to-video Median Rank· uses extra data· 2021-06-21
    2
    best: 13 (JSFusion)
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonMSR-VTT-1kA
    video-to-text Median Rank· uses extra data· 2021-06-21
    2
    best: 5 (CLIP)
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonMSR-VTT
    text-to-video Mean Rank· uses extra data· 2021-06-21
    45.4
    best: 213.8 (JEMC)
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonMSR-VTT
    text-to-video Median Rank· uses extra data· 2021-06-21
    4
    best: 55 (C+LSTM+SA+FC7)
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonMSR-VTT
    text-to-video R@1· uses extra data· 2021-06-21
    29.8
    best: 64 (GRAM)
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonMSR-VTT
    text-to-video R@10· uses extra data· 2021-06-21
    66.2
    best: 89.6 (VAST)
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonMSR-VTT
    text-to-video R@5· uses extra data· 2021-06-21
    55.5
    best: 84.3 (VAST)
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonMSR-VTT
    video-to-text Mean Rank· uses extra data· 2021-06-21
    5.3
    best: 134 (JEMC)
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097
  • Video RetrievalonMSR-VTT
    video-to-text Median Rank· uses extra data· 2021-06-21
    1
    best: 16 (JEMC)
    CLIP2Video: Mastering Video-Text Retrieval via Image CLIParXiv:2106.11097