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/MDMMT

MDMMT

Reported on 30 benchmarks across 2 tasks · 1 paper · 18 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· 2021-03-19
    38.9
    best: 62.9 (HunYuan_tvr (huge))
    SOTA
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • VideoonMSR-VTT-1kA
    text-to-video R@10· uses extra data· 2021-03-19
    79.7
    best: 90.8 (HunYuan_tvr (huge))
    SOTA
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • VideoonMSR-VTT-1kA
    text-to-video R@5· uses extra data· 2021-03-19
    69
    best: 84.5 (HunYuan_tvr (huge))
    SOTA
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • VideoonMSR-VTT
    text-to-video R@1· uses extra data· 2021-03-19
    23.1
    best: 64 (GRAM)
    SOTA
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • VideoonMSR-VTT
    text-to-video R@5· uses extra data· 2021-03-19
    49.8
    best: 84.3 (VAST)
    SOTA
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • VideoonLSMDC
    text-to-video Mean Rank· uses extra data· 2021-03-19
    58
    SOTA
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • VideoonLSMDC
    text-to-video R@1· uses extra data· 2021-03-19
    18.8
    best: 46.4 (InternVideo2-6B)
    SOTA
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • VideoonLSMDC
    text-to-video R@10· uses extra data· 2021-03-19
    47.9
    best: 92.8 (HunYuan_tvr (huge))
    SOTA
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • VideoonLSMDC
    text-to-video R@5· uses extra data· 2021-03-19
    38.5
    best: 80.1 (HunYuan_tvr (huge))
    SOTA
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@1· uses extra data· 2021-03-19
    38.9
    best: 62.9 (HunYuan_tvr (huge))
    SOTA
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@10· uses extra data· 2021-03-19
    79.7
    best: 90.8 (HunYuan_tvr (huge))
    SOTA
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@5· uses extra data· 2021-03-19
    69
    best: 84.5 (HunYuan_tvr (huge))
    SOTA
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • Video RetrievalonMSR-VTT
    text-to-video R@1· uses extra data· 2021-03-19
    23.1
    best: 64 (GRAM)
    SOTA
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • Video RetrievalonMSR-VTT
    text-to-video R@5· uses extra data· 2021-03-19
    49.8
    best: 84.3 (VAST)
    SOTA
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • Video RetrievalonLSMDC
    text-to-video Mean Rank· uses extra data· 2021-03-19
    58
    SOTA
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • Video RetrievalonLSMDC
    text-to-video R@1· uses extra data· 2021-03-19
    18.8
    best: 46.4 (InternVideo2-6B)
    SOTA
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • Video RetrievalonLSMDC
    text-to-video R@10· uses extra data· 2021-03-19
    47.9
    best: 92.8 (HunYuan_tvr (huge))
    SOTA
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • Video RetrievalonLSMDC
    text-to-video R@5· uses extra data· 2021-03-19
    38.5
    best: 80.1 (HunYuan_tvr (huge))
    SOTA
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • VideoonMSR-VTT-1kA
    text-to-video Mean Rank· uses extra data· 2021-03-19
    16.5
    best: 28.2 (Collaborative Experts)
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • VideoonMSR-VTT-1kA
    text-to-video Median Rank· uses extra data· 2021-03-19
    2
    best: 13 (JSFusion)
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • VideoonMSR-VTT
    text-to-video Mean Rank· uses extra data· 2021-03-19
    52.8
    best: 213.8 (JEMC)
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • VideoonMSR-VTT
    text-to-video Median Rank· uses extra data· 2021-03-19
    6
    best: 55 (C+LSTM+SA+FC7)
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • VideoonMSR-VTT
    text-to-video R@10· uses extra data· 2021-03-19
    61.8
    best: 89.6 (VAST)
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • VideoonLSMDC
    text-to-video Median Rank· uses extra data· 2021-03-19
    12.3
    best: 56.5 (CLIP)
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • Video RetrievalonMSR-VTT-1kA
    text-to-video Mean Rank· uses extra data· 2021-03-19
    16.5
    best: 28.2 (Collaborative Experts)
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • Video RetrievalonMSR-VTT-1kA
    text-to-video Median Rank· uses extra data· 2021-03-19
    2
    best: 13 (JSFusion)
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • Video RetrievalonMSR-VTT
    text-to-video Mean Rank· uses extra data· 2021-03-19
    52.8
    best: 213.8 (JEMC)
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • Video RetrievalonMSR-VTT
    text-to-video Median Rank· uses extra data· 2021-03-19
    6
    best: 55 (C+LSTM+SA+FC7)
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • Video RetrievalonMSR-VTT
    text-to-video R@10· uses extra data· 2021-03-19
    61.8
    best: 89.6 (VAST)
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699
  • Video RetrievalonLSMDC
    text-to-video Median Rank· uses extra data· 2021-03-19
    12.3
    best: 56.5 (CLIP)
    MDMMT: Multidomain Multimodal Transformer for Video RetrievalarXiv:2103.10699