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/CLIP2TV

CLIP2TV

Reported on 30 benchmarks across 2 tasks · 1 paper · 12 SOTA

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

Computer Vision30 results

  • VideoonMSR-VTT-1kA
    text-to-video R@1· uses extra data· 2021-11-10
    52.9
    best: 62.9 (HunYuan_tvr (huge))
    SOTA
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • VideoonMSR-VTT-1kA
    text-to-video R@10· uses extra data· 2021-11-10
    86.5
    best: 90.8 (HunYuan_tvr (huge))
    SOTA
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • VideoonMSR-VTT-1kA
    text-to-video R@5· uses extra data· 2021-11-10
    78.5
    best: 84.5 (HunYuan_tvr (huge))
    SOTA
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • VideoonMSR-VTT-1kA
    video-to-text R@1· uses extra data· 2021-11-10
    54.1
    best: 64.8 (HunYuan_tvr (huge))
    SOTA
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • VideoonMSR-VTT-1kA
    video-to-text R@10· uses extra data· 2021-11-10
    85.7
    best: 91.1 (HunYuan_tvr (huge))
    SOTA
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • VideoonMSR-VTT-1kA
    video-to-text R@5· uses extra data· 2021-11-10
    77.4
    best: 783 (PIDRo)
    SOTA
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@1· uses extra data· 2021-11-10
    52.9
    best: 62.9 (HunYuan_tvr (huge))
    SOTA
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@10· uses extra data· 2021-11-10
    86.5
    best: 90.8 (HunYuan_tvr (huge))
    SOTA
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@5· uses extra data· 2021-11-10
    78.5
    best: 84.5 (HunYuan_tvr (huge))
    SOTA
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • Video RetrievalonMSR-VTT-1kA
    video-to-text R@1· uses extra data· 2021-11-10
    54.1
    best: 64.8 (HunYuan_tvr (huge))
    SOTA
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • Video RetrievalonMSR-VTT-1kA
    video-to-text R@10· uses extra data· 2021-11-10
    85.7
    best: 91.1 (HunYuan_tvr (huge))
    SOTA
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • Video RetrievalonMSR-VTT-1kA
    video-to-text R@5· uses extra data· 2021-11-10
    77.4
    best: 783 (PIDRo)
    SOTA
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • VideoonMSR-VTT-1kA
    text-to-video Mean Rank· uses extra data· 2021-11-10
    12.8
    best: 28.2 (Collaborative Experts)
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • VideoonMSR-VTT-1kA
    text-to-video Median Rank· uses extra data· 2021-11-10
    1
    best: 13 (JSFusion)
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • VideoonMSR-VTT-1kA
    video-to-text Mean Rank· uses extra data· 2021-11-10
    9
    best: 10.2 (CenterCLIP (ViT-B/16))
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • VideoonMSR-VTT-1kA
    video-to-text Median Rank· uses extra data· 2021-11-10
    1
    best: 5 (CLIP)
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • VideoonMSR-VTT
    text-to-video Mean Rank· uses extra data· 2021-11-10
    44.7
    best: 213.8 (JEMC)
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • VideoonMSR-VTT
    text-to-video Median Rank· uses extra data· 2021-11-10
    3
    best: 55 (C+LSTM+SA+FC7)
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • VideoonMSR-VTT
    text-to-video R@1· uses extra data· 2021-11-10
    33.1
    best: 64 (GRAM)
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • VideoonMSR-VTT
    text-to-video R@10· uses extra data· 2021-11-10
    68.9
    best: 89.6 (VAST)
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • VideoonMSR-VTT
    text-to-video R@5· uses extra data· 2021-11-10
    58.9
    best: 84.3 (VAST)
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • Video RetrievalonMSR-VTT-1kA
    text-to-video Mean Rank· uses extra data· 2021-11-10
    12.8
    best: 28.2 (Collaborative Experts)
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • Video RetrievalonMSR-VTT-1kA
    text-to-video Median Rank· uses extra data· 2021-11-10
    1
    best: 13 (JSFusion)
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • Video RetrievalonMSR-VTT-1kA
    video-to-text Mean Rank· uses extra data· 2021-11-10
    9
    best: 10.2 (CenterCLIP (ViT-B/16))
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • Video RetrievalonMSR-VTT-1kA
    video-to-text Median Rank· uses extra data· 2021-11-10
    1
    best: 5 (CLIP)
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • Video RetrievalonMSR-VTT
    text-to-video Mean Rank· uses extra data· 2021-11-10
    44.7
    best: 213.8 (JEMC)
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • Video RetrievalonMSR-VTT
    text-to-video Median Rank· uses extra data· 2021-11-10
    3
    best: 55 (C+LSTM+SA+FC7)
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • Video RetrievalonMSR-VTT
    text-to-video R@1· uses extra data· 2021-11-10
    33.1
    best: 64 (GRAM)
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • Video RetrievalonMSR-VTT
    text-to-video R@10· uses extra data· 2021-11-10
    68.9
    best: 89.6 (VAST)
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610
  • Video RetrievalonMSR-VTT
    text-to-video R@5· uses extra data· 2021-11-10
    58.9
    best: 84.3 (VAST)
    CLIP2TV: Align, Match and Distill for Video-Text RetrievalarXiv:2111.05610