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/All-in-one-B

All-in-one-B

Reported on 8 benchmarks across 3 tasks · 1 paper · 2 SOTA

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

Computer Vision6 results

  • VideoonMSR-VTT-1kA
    text-to-video R@1· uses extra data· 2022-03-14
    37.9
    best: 62.9 (HunYuan_tvr (huge))
    All in One: Exploring Unified Video-Language Pre-trainingarXiv:2203.07303
  • VideoonMSR-VTT-1kA
    text-to-video R@10· uses extra data· 2022-03-14
    77.1
    best: 90.8 (HunYuan_tvr (huge))
    All in One: Exploring Unified Video-Language Pre-trainingarXiv:2203.07303
  • VideoonMSR-VTT-1kA
    text-to-video R@5· uses extra data· 2022-03-14
    68.1
    best: 84.5 (HunYuan_tvr (huge))
    All in One: Exploring Unified Video-Language Pre-trainingarXiv:2203.07303
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@1· uses extra data· 2022-03-14
    37.9
    best: 62.9 (HunYuan_tvr (huge))
    All in One: Exploring Unified Video-Language Pre-trainingarXiv:2203.07303
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@10· uses extra data· 2022-03-14
    77.1
    best: 90.8 (HunYuan_tvr (huge))
    All in One: Exploring Unified Video-Language Pre-trainingarXiv:2203.07303
  • Video RetrievalonMSR-VTT-1kA
    text-to-video R@5· uses extra data· 2022-03-14
    68.1
    best: 84.5 (HunYuan_tvr (huge))
    All in One: Exploring Unified Video-Language Pre-trainingarXiv:2203.07303

Natural Language Processing2 results

  • Visual Question Answering (VQA)onMSRVTT-QA
    Accuracy· uses extra data· 2022-03-14
    0.443
    best: 0.496 (VLAB)
    SOTA
    All in One: Exploring Unified Video-Language Pre-trainingarXiv:2203.07303
  • Visual Question Answering (VQA)onMSVD-QA
    Accuracy· uses extra data· 2022-03-14
    0.483
    best: 0.61 (VLAB)
    SOTA
    All in One: Exploring Unified Video-Language Pre-trainingarXiv:2203.07303