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/X-Pool

X-Pool

Reported on 60 benchmarks across 2 tasks · 1 paper · 10 SOTA

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

Computer Vision60 results

  • VideoonLSMDC
    video-to-text Mean Rank· uses extra data· 2022-03-28
    47.4
    best: 48.9 (HunYuan_tvr)
    SOTA
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonLSMDC
    video-to-text R@1· uses extra data· 2022-03-28
    22.7
    best: 46.7 (InternVideo2-6B)
    SOTA
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonLSMDC
    video-to-text R@10· uses extra data· 2022-03-28
    51.2
    best: 91.8 (HunYuan_tvr (huge))
    SOTA
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonLSMDC
    video-to-text R@5· uses extra data· 2022-03-28
    42.6
    best: 71.8 (HunYuan_tvr (huge))
    SOTA
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonMSVD
    video-to-text Mean Rank· uses extra data· 2022-03-28
    3.3
    best: 7.6 (HunYuan_tvr (huge))
    SOTA
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonLSMDC
    video-to-text Mean Rank· uses extra data· 2022-03-28
    47.4
    best: 48.9 (HunYuan_tvr)
    SOTA
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonLSMDC
    video-to-text R@1· uses extra data· 2022-03-28
    22.7
    best: 46.7 (InternVideo2-6B)
    SOTA
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonLSMDC
    video-to-text R@10· uses extra data· 2022-03-28
    51.2
    best: 91.8 (HunYuan_tvr (huge))
    SOTA
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonLSMDC
    video-to-text R@5· uses extra data· 2022-03-28
    42.6
    best: 71.8 (HunYuan_tvr (huge))
    SOTA
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonMSVD
    video-to-text Mean Rank· uses extra data· 2022-03-28
    3.3
    best: 7.6 (HunYuan_tvr (huge))
    SOTA
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonMSR-VTT-1kA
    text-to-video Mean Rank· uses extra data· 2022-03-28
    14.3
    best: 28.2 (Collaborative Experts)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonMSR-VTT-1kA
    text-to-video Median Rank· uses extra data· 2022-03-28
    2
    best: 13 (JSFusion)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonMSR-VTT-1kA
    text-to-video R@1· uses extra data· 2022-03-28
    46.9
    best: 62.9 (HunYuan_tvr (huge))
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonMSR-VTT-1kA
    text-to-video R@10· uses extra data· 2022-03-28
    82.2
    best: 90.8 (HunYuan_tvr (huge))
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonMSR-VTT-1kA
    text-to-video R@5· uses extra data· 2022-03-28
    72.8
    best: 84.5 (HunYuan_tvr (huge))
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonMSR-VTT-1kA
    video-to-text Mean Rank· uses extra data· 2022-03-28
    9
    best: 10.2 (CenterCLIP (ViT-B/16))
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonMSR-VTT-1kA
    video-to-text Median Rank· uses extra data· 2022-03-28
    2
    best: 5 (CLIP)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonMSR-VTT-1kA
    video-to-text R@1· uses extra data· 2022-03-28
    44.4
    best: 64.8 (HunYuan_tvr (huge))
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonMSR-VTT-1kA
    video-to-text R@10· uses extra data· 2022-03-28
    84
    best: 91.1 (HunYuan_tvr (huge))
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonMSR-VTT-1kA
    video-to-text R@5· uses extra data· 2022-03-28
    73.3
    best: 783 (PIDRo)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonLSMDC
    text-to-video Mean Rank· uses extra data· 2022-03-28
    53.2
    best: 58 (CLIP4Clip)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonLSMDC
    text-to-video Median Rank· uses extra data· 2022-03-28
    8
    best: 56.5 (CLIP)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonLSMDC
    text-to-video R@1· uses extra data· 2022-03-28
    25.2
    best: 46.4 (InternVideo2-6B)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonLSMDC
    text-to-video R@10· uses extra data· 2022-03-28
    53.5
    best: 92.8 (HunYuan_tvr (huge))
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonLSMDC
    text-to-video R@5· uses extra data· 2022-03-28
    43.7
    best: 80.1 (HunYuan_tvr (huge))
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonLSMDC
    video-to-text Median Rank· uses extra data· 2022-03-28
    10
    best: 73 (CLIP)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonMSVD
    text-to-video Mean Rank· uses extra data· 2022-03-28
    9.3
    best: 23.1 (Collaborative Experts)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonMSVD
    text-to-video Median Rank· uses extra data· 2022-03-28
    2
    best: 6 (SSML)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonMSVD
    text-to-video R@1· uses extra data· 2022-03-28
    47.2
    best: 61.4 (InternVideo2-6B)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonMSVD
    text-to-video R@10· uses extra data· 2022-03-28
    86
    best: 90.3 (HunYuan_tvr (huge))
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonMSVD
    text-to-video R@5· uses extra data· 2022-03-28
    77.4
    best: 87.6 (CAMoE)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonMSVD
    video-to-text Median Rank· uses extra data· 2022-03-28
    1
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonMSVD
    video-to-text R@1· uses extra data· 2022-03-28
    66.4
    best: 85.2 (InternVideo2-6B)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonMSVD
    video-to-text R@10· uses extra data· 2022-03-28
    94.2
    best: 97.1 (PAU)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • VideoonMSVD
    video-to-text R@5· uses extra data· 2022-03-28
    90
    best: 94.5 (HunYuan_tvr (huge))
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonMSR-VTT-1kA
    text-to-video Mean Rank· uses extra data· 2022-03-28
    14.3
    best: 28.2 (Collaborative Experts)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonMSR-VTT-1kA
    text-to-video Median Rank· uses extra data· 2022-03-28
    2
    best: 13 (JSFusion)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@1· uses extra data· 2022-03-28
    46.9
    best: 62.9 (HunYuan_tvr (huge))
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@10· uses extra data· 2022-03-28
    82.2
    best: 90.8 (HunYuan_tvr (huge))
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@5· uses extra data· 2022-03-28
    72.8
    best: 84.5 (HunYuan_tvr (huge))
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonMSR-VTT-1kA
    video-to-text Mean Rank· uses extra data· 2022-03-28
    9
    best: 10.2 (CenterCLIP (ViT-B/16))
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonMSR-VTT-1kA
    video-to-text Median Rank· uses extra data· 2022-03-28
    2
    best: 5 (CLIP)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonMSR-VTT-1kA
    video-to-text R@1· uses extra data· 2022-03-28
    44.4
    best: 64.8 (HunYuan_tvr (huge))
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonMSR-VTT-1kA
    video-to-text R@10· uses extra data· 2022-03-28
    84
    best: 91.1 (HunYuan_tvr (huge))
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonMSR-VTT-1kA
    video-to-text R@5· uses extra data· 2022-03-28
    73.3
    best: 783 (PIDRo)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonLSMDC
    text-to-video Mean Rank· uses extra data· 2022-03-28
    53.2
    best: 58 (CLIP4Clip)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonLSMDC
    text-to-video Median Rank· uses extra data· 2022-03-28
    8
    best: 56.5 (CLIP)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonLSMDC
    text-to-video R@1· uses extra data· 2022-03-28
    25.2
    best: 46.4 (InternVideo2-6B)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonLSMDC
    text-to-video R@10· uses extra data· 2022-03-28
    53.5
    best: 92.8 (HunYuan_tvr (huge))
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonLSMDC
    text-to-video R@5· uses extra data· 2022-03-28
    43.7
    best: 80.1 (HunYuan_tvr (huge))
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonLSMDC
    video-to-text Median Rank· uses extra data· 2022-03-28
    10
    best: 73 (CLIP)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonMSVD
    text-to-video Mean Rank· uses extra data· 2022-03-28
    9.3
    best: 23.1 (Collaborative Experts)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonMSVD
    text-to-video Median Rank· uses extra data· 2022-03-28
    2
    best: 6 (SSML)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonMSVD
    text-to-video R@1· uses extra data· 2022-03-28
    47.2
    best: 61.4 (InternVideo2-6B)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonMSVD
    text-to-video R@10· uses extra data· 2022-03-28
    86
    best: 90.3 (HunYuan_tvr (huge))
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonMSVD
    text-to-video R@5· uses extra data· 2022-03-28
    77.4
    best: 87.6 (CAMoE)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonMSVD
    video-to-text Median Rank· uses extra data· 2022-03-28
    1
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonMSVD
    video-to-text R@1· uses extra data· 2022-03-28
    66.4
    best: 85.2 (InternVideo2-6B)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonMSVD
    video-to-text R@10· uses extra data· 2022-03-28
    94.2
    best: 97.1 (PAU)
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086
  • Video RetrievalonMSVD
    video-to-text R@5· uses extra data· 2022-03-28
    90
    best: 94.5 (HunYuan_tvr (huge))
    X-Pool: Cross-Modal Language-Video Attention for Text-Video RetrievalarXiv:2203.15086