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/UniVL

UniVL

Reported on 21 benchmarks across 3 tasks · 1 paper · 17 SOTA

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

Computer Vision21 results

  • VideoonYouCook2
    text-to-video R@1· uses extra data· 2020-02-15
    28.9
    best: 50.4 (VAST)
    SOTA
    UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and GenerationarXiv:2002.06353
  • VideoonYouCook2
    text-to-video R@10· uses extra data· 2020-02-15
    70
    best: 80.8 (VAST)
    SOTA
    UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and GenerationarXiv:2002.06353
  • VideoonYouCook2
    text-to-video R@5· uses extra data· 2020-02-15
    57.6
    best: 74.3 (VAST)
    SOTA
    UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and GenerationarXiv:2002.06353
  • VideoonMSR-VTT
    text-to-video R@1· uses extra data· 2020-02-15
    21.2
    best: 64 (GRAM)
    SOTA
    UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and GenerationarXiv:2002.06353
  • VideoonMSR-VTT
    text-to-video R@10· uses extra data· 2020-02-15
    63.1
    best: 89.6 (VAST)
    SOTA
    UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and GenerationarXiv:2002.06353
  • VideoonMSR-VTT
    text-to-video R@5· uses extra data· 2020-02-15
    49.6
    best: 84.3 (VAST)
    SOTA
    UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and GenerationarXiv:2002.06353
  • Video CaptioningonYouCook2
    BLEU-3· uses extra data· 2020-02-15
    23.87
    best: 24.12 (UniVL + MELTR)
    SOTA
    UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and GenerationarXiv:2002.06353
  • Video CaptioningonYouCook2
    BLEU-4· uses extra data· 2020-02-15
    17.35
    best: 18.2 (VAST)
    SOTA
    UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and GenerationarXiv:2002.06353
  • Video CaptioningonYouCook2
    CIDEr· uses extra data· 2020-02-15
    1.81
    best: 116.4 (HowToCaption)
    SOTA
    UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and GenerationarXiv:2002.06353
  • Video CaptioningonYouCook2
    METEOR· uses extra data· 2020-02-15
    22.35
    best: 22.56 (UniVL + MELTR)
    SOTA
    UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and GenerationarXiv:2002.06353
  • Video CaptioningonYouCook2
    ROUGE-L· uses extra data· 2020-02-15
    46.52
    best: 47.04 (UniVL + MELTR)
    SOTA
    UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and GenerationarXiv:2002.06353
  • Video RetrievalonYouCook2
    text-to-video R@1· uses extra data· 2020-02-15
    28.9
    best: 50.4 (VAST)
    SOTA
    UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and GenerationarXiv:2002.06353
  • Video RetrievalonYouCook2
    text-to-video R@10· uses extra data· 2020-02-15
    70
    best: 80.8 (VAST)
    SOTA
    UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and GenerationarXiv:2002.06353
  • Video RetrievalonYouCook2
    text-to-video R@5· uses extra data· 2020-02-15
    57.6
    best: 74.3 (VAST)
    SOTA
    UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and GenerationarXiv:2002.06353
  • Video RetrievalonMSR-VTT
    text-to-video R@1· uses extra data· 2020-02-15
    21.2
    best: 64 (GRAM)
    SOTA
    UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and GenerationarXiv:2002.06353
  • Video RetrievalonMSR-VTT
    text-to-video R@10· uses extra data· 2020-02-15
    63.1
    best: 89.6 (VAST)
    SOTA
    UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and GenerationarXiv:2002.06353
  • Video RetrievalonMSR-VTT
    text-to-video R@5· uses extra data· 2020-02-15
    49.6
    best: 84.3 (VAST)
    SOTA
    UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and GenerationarXiv:2002.06353
  • VideoonYouCook2
    text-to-video Median Rank· uses extra data· 2020-02-15
    4
    best: 77 (Satar et al.)
    UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and GenerationarXiv:2002.06353
  • VideoonMSR-VTT
    text-to-video Median Rank· uses extra data· 2020-02-15
    6
    best: 55 (C+LSTM+SA+FC7)
    UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and GenerationarXiv:2002.06353
  • Video RetrievalonYouCook2
    text-to-video Median Rank· uses extra data· 2020-02-15
    4
    best: 77 (Satar et al.)
    UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and GenerationarXiv:2002.06353
  • Video RetrievalonMSR-VTT
    text-to-video Median Rank· uses extra data· 2020-02-15
    6
    best: 55 (C+LSTM+SA+FC7)
    UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and GenerationarXiv:2002.06353