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/DiffusionRet

DiffusionRet

Reported on 100 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 Vision100 results

  • VideoonMSR-VTT-1kA
    text-to-video Mean Rank· 2023-03-17
    12.1
    best: 28.2 (Collaborative Experts)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonMSR-VTT-1kA
    text-to-video Median Rank· 2023-03-17
    2
    best: 13 (JSFusion)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonMSR-VTT-1kA
    text-to-video R@1· 2023-03-17
    49
    best: 62.9 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonMSR-VTT-1kA
    text-to-video R@10· 2023-03-17
    82.7
    best: 90.8 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonMSR-VTT-1kA
    text-to-video R@5· 2023-03-17
    75.2
    best: 84.5 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonMSR-VTT-1kA
    video-to-text Mean Rank· 2023-03-17
    8.8
    best: 10.2 (CenterCLIP (ViT-B/16))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonMSR-VTT-1kA
    video-to-text Median Rank· 2023-03-17
    2
    best: 5 (CLIP)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonMSR-VTT-1kA
    video-to-text R@1· 2023-03-17
    47.7
    best: 64.8 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonMSR-VTT-1kA
    video-to-text R@10· 2023-03-17
    84.5
    best: 91.1 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonMSR-VTT-1kA
    video-to-text R@5· 2023-03-17
    73.8
    best: 783 (PIDRo)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonActivityNet
    text-to-video Mean Rank· 2023-03-17
    6.5
    best: 23.1 (Collaborative Experts)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonActivityNet
    text-to-video Median Rank· 2023-03-17
    2
    best: 6 (Collaborative Experts)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonActivityNet
    text-to-video R@1· 2023-03-17
    45.8
    best: 74.1 (InternVideo2-6B)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonActivityNet
    text-to-video R@10· 2023-03-17
    86.3
    best: 96.1 (GRAM)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonActivityNet
    text-to-video R@5· 2023-03-17
    75.6
    best: 90.9 (VAST)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonActivityNet
    video-to-text Mean Rank· 2023-03-17
    6.3
    best: 6.7 (DiffusionRet+QB-Norm)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonActivityNet
    video-to-text Median Rank· 2023-03-17
    2
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonActivityNet
    video-to-text R@1· 2023-03-17
    43.8
    best: 69.7 (InternVideo2-6B)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonActivityNet
    video-to-text R@10· 2023-03-17
    86.7
    best: 95.4 (GRAM)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonActivityNet
    video-to-text R@5· 2023-03-17
    75.3
    best: 89.1 (UMT-L (ViT-L/16))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonDiDeMo
    text-to-video Mean Rank· 2023-03-17
    14.3
    best: 43.7 (Collaborative Experts)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonDiDeMo
    text-to-video Median Rank· 2023-03-17
    2
    best: 8.3 (Collaborative Experts)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonDiDeMo
    text-to-video R@1· 2023-03-17
    46.7
    best: 74.2 (InternVideo2-6B)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonDiDeMo
    text-to-video R@10· 2023-03-17
    82.7
    best: 94.2 (vid-TLDR (UMT-L))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonDiDeMo
    text-to-video R@5· 2023-03-17
    74.7
    best: 91.2 (vid-TLDR (UMT-L))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonDiDeMo
    video-to-text Mean Rank· 2023-03-17
    10.7
    best: 39.6 (PO Loss)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonDiDeMo
    video-to-text Median Rank· 2023-03-17
    2
    best: 8 (PO Loss)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonDiDeMo
    video-to-text R@1· 2023-03-17
    46.2
    best: 71.9 (InternVideo2-6B)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonDiDeMo
    video-to-text R@10· 2023-03-17
    82.2
    best: 93.8 (vid-TLDR (UMT-L))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonDiDeMo
    video-to-text R@5· 2023-03-17
    74.3
    best: 89.8 (vid-TLDR (UMT-L))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonLSMDC
    text-to-video Mean Rank· 2023-03-17
    40.7
    best: 58 (CLIP4Clip)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonLSMDC
    text-to-video Median Rank· 2023-03-17
    8
    best: 56.5 (CLIP)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonLSMDC
    text-to-video R@1· 2023-03-17
    24.4
    best: 46.4 (InternVideo2-6B)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonLSMDC
    text-to-video R@10· 2023-03-17
    54.3
    best: 92.8 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonLSMDC
    text-to-video R@5· 2023-03-17
    43.1
    best: 80.1 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonLSMDC
    video-to-text Mean Rank· 2023-03-17
    40.2
    best: 48.9 (HunYuan_tvr)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonLSMDC
    video-to-text Median Rank· 2023-03-17
    9
    best: 73 (CLIP)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonLSMDC
    video-to-text R@1· 2023-03-17
    23
    best: 46.7 (InternVideo2-6B)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonLSMDC
    video-to-text R@10· 2023-03-17
    51.5
    best: 91.8 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonLSMDC
    video-to-text R@5· 2023-03-17
    43.5
    best: 71.8 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonMSVD
    text-to-video Mean Rank· 2023-03-17
    15.7
    best: 23.1 (Collaborative Experts)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonMSVD
    text-to-video Median Rank· 2023-03-17
    2
    best: 6 (SSML)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonMSVD
    text-to-video R@1· 2023-03-17
    46.6
    best: 61.4 (InternVideo2-6B)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonMSVD
    text-to-video R@10· 2023-03-17
    84.1
    best: 90.3 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonMSVD
    text-to-video R@5· 2023-03-17
    75.9
    best: 87.6 (CAMoE)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonMSVD
    video-to-text Mean Rank· 2023-03-17
    4.5
    best: 7.6 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonMSVD
    video-to-text Median Rank· 2023-03-17
    1
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonMSVD
    video-to-text R@1· 2023-03-17
    61.9
    best: 85.2 (InternVideo2-6B)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonMSVD
    video-to-text R@10· 2023-03-17
    92.9
    best: 97.1 (PAU)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • VideoonMSVD
    video-to-text R@5· 2023-03-17
    88.3
    best: 94.5 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonMSR-VTT-1kA
    text-to-video Mean Rank· 2023-03-17
    12.1
    best: 28.2 (Collaborative Experts)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonMSR-VTT-1kA
    text-to-video Median Rank· 2023-03-17
    2
    best: 13 (JSFusion)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@1· 2023-03-17
    49
    best: 62.9 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@10· 2023-03-17
    82.7
    best: 90.8 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@5· 2023-03-17
    75.2
    best: 84.5 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonMSR-VTT-1kA
    video-to-text Mean Rank· 2023-03-17
    8.8
    best: 10.2 (CenterCLIP (ViT-B/16))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonMSR-VTT-1kA
    video-to-text Median Rank· 2023-03-17
    2
    best: 5 (CLIP)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonMSR-VTT-1kA
    video-to-text R@1· 2023-03-17
    47.7
    best: 64.8 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonMSR-VTT-1kA
    video-to-text R@10· 2023-03-17
    84.5
    best: 91.1 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonMSR-VTT-1kA
    video-to-text R@5· 2023-03-17
    73.8
    best: 783 (PIDRo)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonActivityNet
    text-to-video Mean Rank· 2023-03-17
    6.5
    best: 23.1 (Collaborative Experts)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonActivityNet
    text-to-video Median Rank· 2023-03-17
    2
    best: 6 (Collaborative Experts)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonActivityNet
    text-to-video R@1· 2023-03-17
    45.8
    best: 74.1 (InternVideo2-6B)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonActivityNet
    text-to-video R@10· 2023-03-17
    86.3
    best: 96.1 (GRAM)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonActivityNet
    text-to-video R@5· 2023-03-17
    75.6
    best: 90.9 (VAST)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonActivityNet
    video-to-text Mean Rank· 2023-03-17
    6.3
    best: 6.7 (DiffusionRet+QB-Norm)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonActivityNet
    video-to-text Median Rank· 2023-03-17
    2
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonActivityNet
    video-to-text R@1· 2023-03-17
    43.8
    best: 69.7 (InternVideo2-6B)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonActivityNet
    video-to-text R@10· 2023-03-17
    86.7
    best: 95.4 (GRAM)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonActivityNet
    video-to-text R@5· 2023-03-17
    75.3
    best: 89.1 (UMT-L (ViT-L/16))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonDiDeMo
    text-to-video Mean Rank· 2023-03-17
    14.3
    best: 43.7 (Collaborative Experts)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonDiDeMo
    text-to-video Median Rank· 2023-03-17
    2
    best: 8.3 (Collaborative Experts)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonDiDeMo
    text-to-video R@1· 2023-03-17
    46.7
    best: 74.2 (InternVideo2-6B)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonDiDeMo
    text-to-video R@10· 2023-03-17
    82.7
    best: 94.2 (vid-TLDR (UMT-L))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonDiDeMo
    text-to-video R@5· 2023-03-17
    74.7
    best: 91.2 (vid-TLDR (UMT-L))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonDiDeMo
    video-to-text Mean Rank· 2023-03-17
    10.7
    best: 39.6 (PO Loss)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonDiDeMo
    video-to-text Median Rank· 2023-03-17
    2
    best: 8 (PO Loss)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonDiDeMo
    video-to-text R@1· 2023-03-17
    46.2
    best: 71.9 (InternVideo2-6B)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonDiDeMo
    video-to-text R@10· 2023-03-17
    82.2
    best: 93.8 (vid-TLDR (UMT-L))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonDiDeMo
    video-to-text R@5· 2023-03-17
    74.3
    best: 89.8 (vid-TLDR (UMT-L))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonLSMDC
    text-to-video Mean Rank· 2023-03-17
    40.7
    best: 58 (CLIP4Clip)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonLSMDC
    text-to-video Median Rank· 2023-03-17
    8
    best: 56.5 (CLIP)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonLSMDC
    text-to-video R@1· 2023-03-17
    24.4
    best: 46.4 (InternVideo2-6B)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonLSMDC
    text-to-video R@10· 2023-03-17
    54.3
    best: 92.8 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonLSMDC
    text-to-video R@5· 2023-03-17
    43.1
    best: 80.1 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonLSMDC
    video-to-text Mean Rank· 2023-03-17
    40.2
    best: 48.9 (HunYuan_tvr)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonLSMDC
    video-to-text Median Rank· 2023-03-17
    9
    best: 73 (CLIP)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonLSMDC
    video-to-text R@1· 2023-03-17
    23
    best: 46.7 (InternVideo2-6B)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonLSMDC
    video-to-text R@10· 2023-03-17
    51.5
    best: 91.8 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonLSMDC
    video-to-text R@5· 2023-03-17
    43.5
    best: 71.8 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonMSVD
    text-to-video Mean Rank· 2023-03-17
    15.7
    best: 23.1 (Collaborative Experts)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonMSVD
    text-to-video Median Rank· 2023-03-17
    2
    best: 6 (SSML)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonMSVD
    text-to-video R@1· 2023-03-17
    46.6
    best: 61.4 (InternVideo2-6B)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonMSVD
    text-to-video R@10· 2023-03-17
    84.1
    best: 90.3 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonMSVD
    text-to-video R@5· 2023-03-17
    75.9
    best: 87.6 (CAMoE)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonMSVD
    video-to-text Mean Rank· 2023-03-17
    4.5
    best: 7.6 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonMSVD
    video-to-text Median Rank· 2023-03-17
    1
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonMSVD
    video-to-text R@1· 2023-03-17
    61.9
    best: 85.2 (InternVideo2-6B)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonMSVD
    video-to-text R@10· 2023-03-17
    92.9
    best: 97.1 (PAU)
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867
  • Video RetrievalonMSVD
    video-to-text R@5· 2023-03-17
    88.3
    best: 94.5 (HunYuan_tvr (huge))
    DiffusionRet: Generative Text-Video Retrieval with Diffusion ModelarXiv:2303.09867