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/FROZEN

FROZEN

Reported on 45 benchmarks across 3 tasks · 1 paper · 20 SOTA

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

Computer Vision45 results

  • VideoonDiDeMo
    text-to-video R@1· uses extra data· 2021-04-01
    31
    best: 74.2 (InternVideo2-6B)
    SOTA
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • VideoonDiDeMo
    text-to-video R@10· uses extra data· 2021-04-01
    72.4
    best: 94.2 (vid-TLDR (UMT-L))
    SOTA
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • VideoonDiDeMo
    text-to-video R@5· uses extra data· 2021-04-01
    59.8
    best: 91.2 (vid-TLDR (UMT-L))
    SOTA
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • VideoonMSR-VTT
    text-to-video R@1· 2021-04-01
    32.5
    best: 64 (GRAM)
    SOTA
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • VideoonMSR-VTT
    text-to-video R@10· 2021-04-01
    71.2
    best: 89.6 (VAST)
    SOTA
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • VideoonMSR-VTT
    text-to-video R@5· 2021-04-01
    61.5
    best: 84.3 (VAST)
    SOTA
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • VideoonMSVD
    text-to-video R@10· uses extra data· 2021-04-01
    76.3
    best: 90.3 (HunYuan_tvr (huge))
    SOTA
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • VideoonMSVD
    text-to-video R@5· uses extra data· 2021-04-01
    64.7
    best: 87.6 (CAMoE)
    SOTA
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Video RetrievalonDiDeMo
    text-to-video R@1· uses extra data· 2021-04-01
    31
    best: 74.2 (InternVideo2-6B)
    SOTA
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Video RetrievalonDiDeMo
    text-to-video R@10· uses extra data· 2021-04-01
    72.4
    best: 94.2 (vid-TLDR (UMT-L))
    SOTA
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Video RetrievalonDiDeMo
    text-to-video R@5· uses extra data· 2021-04-01
    59.8
    best: 91.2 (vid-TLDR (UMT-L))
    SOTA
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Video RetrievalonMSR-VTT
    text-to-video R@1· 2021-04-01
    32.5
    best: 64 (GRAM)
    SOTA
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Video RetrievalonMSR-VTT
    text-to-video R@10· 2021-04-01
    71.2
    best: 89.6 (VAST)
    SOTA
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Video RetrievalonMSR-VTT
    text-to-video R@5· 2021-04-01
    61.5
    best: 84.3 (VAST)
    SOTA
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Video RetrievalonMSVD
    text-to-video R@10· uses extra data· 2021-04-01
    76.3
    best: 90.3 (HunYuan_tvr (huge))
    SOTA
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Video RetrievalonMSVD
    text-to-video R@5· uses extra data· 2021-04-01
    64.7
    best: 87.6 (CAMoE)
    SOTA
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Zero-Shot Video RetrievalonMSR-VTT
    text-to-video R@1· 2021-04-01
    24.7
    best: 55.9 (InternVideo2-6B)
    SOTA
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Zero-Shot Video RetrievalonMSR-VTT
    text-to-video R@10· 2021-04-01
    57.2
    best: 85.1 (InternVideo2-6B)
    SOTA
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Zero-Shot Video RetrievalonMSR-VTT
    text-to-video R@5· 2021-04-01
    46.9
    best: 78.3 (InternVideo2-6B)
    SOTA
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Zero-Shot Video RetrievalonDiDeMo
    text-to-video R@1· uses extra data· 2021-04-01
    21.1
    best: 57.9 (InternVideo2-6B)
    SOTA
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • VideoonMSR-VTT-1kA
    text-to-video Median Rank· uses extra data· 2021-04-01
    3
    best: 13 (JSFusion)
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • VideoonMSR-VTT-1kA
    text-to-video R@1· uses extra data· 2021-04-01
    31
    best: 62.9 (HunYuan_tvr (huge))
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • VideoonMSR-VTT-1kA
    text-to-video R@10· uses extra data· 2021-04-01
    70.5
    best: 90.8 (HunYuan_tvr (huge))
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • VideoonMSR-VTT-1kA
    text-to-video R@5· uses extra data· 2021-04-01
    59.5
    best: 84.5 (HunYuan_tvr (huge))
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • VideoonDiDeMo
    text-to-video Median Rank· uses extra data· 2021-04-01
    3
    best: 8.3 (Collaborative Experts)
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • VideoonLSMDC
    text-to-video Median Rank· uses extra data· 2021-04-01
    20
    best: 56.5 (CLIP)
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • VideoonLSMDC
    text-to-video R@1· uses extra data· 2021-04-01
    15
    best: 46.4 (InternVideo2-6B)
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • VideoonLSMDC
    text-to-video R@10· uses extra data· 2021-04-01
    39.8
    best: 92.8 (HunYuan_tvr (huge))
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • VideoonLSMDC
    text-to-video R@5· uses extra data· 2021-04-01
    30.8
    best: 80.1 (HunYuan_tvr (huge))
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • VideoonMSVD
    text-to-video Median Rank· uses extra data· 2021-04-01
    3
    best: 6 (SSML)
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • VideoonMSVD
    text-to-video R@1· uses extra data· 2021-04-01
    33.7
    best: 61.4 (InternVideo2-6B)
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Video RetrievalonMSR-VTT-1kA
    text-to-video Median Rank· uses extra data· 2021-04-01
    3
    best: 13 (JSFusion)
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@1· uses extra data· 2021-04-01
    31
    best: 62.9 (HunYuan_tvr (huge))
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@10· uses extra data· 2021-04-01
    70.5
    best: 90.8 (HunYuan_tvr (huge))
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@5· uses extra data· 2021-04-01
    59.5
    best: 84.5 (HunYuan_tvr (huge))
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Video RetrievalonDiDeMo
    text-to-video Median Rank· uses extra data· 2021-04-01
    3
    best: 8.3 (Collaborative Experts)
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Video RetrievalonLSMDC
    text-to-video Median Rank· uses extra data· 2021-04-01
    20
    best: 56.5 (CLIP)
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Video RetrievalonLSMDC
    text-to-video R@1· uses extra data· 2021-04-01
    15
    best: 46.4 (InternVideo2-6B)
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Video RetrievalonLSMDC
    text-to-video R@10· uses extra data· 2021-04-01
    39.8
    best: 92.8 (HunYuan_tvr (huge))
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Video RetrievalonLSMDC
    text-to-video R@5· uses extra data· 2021-04-01
    30.8
    best: 80.1 (HunYuan_tvr (huge))
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Video RetrievalonMSVD
    text-to-video Median Rank· uses extra data· 2021-04-01
    3
    best: 6 (SSML)
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Video RetrievalonMSVD
    text-to-video R@1· uses extra data· 2021-04-01
    33.7
    best: 61.4 (InternVideo2-6B)
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Zero-Shot Video RetrievalonMSR-VTT
    text-to-video Median Rank· 2021-04-01
    7
    best: 66 (MMT)
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Zero-Shot Video RetrievalonDiDeMo
    text-to-video R@10· uses extra data· 2021-04-01
    56.2
    best: 85.1 (InternVideo2-1B)
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650
  • Zero-Shot Video RetrievalonDiDeMo
    text-to-video R@5· uses extra data· 2021-04-01
    46
    best: 80 (InternVideo2-6B)
    Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalarXiv:2104.00650