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/GVL

GVL

Reported on 16 benchmarks across 3 tasks · 1 paper · 3 SOTA

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

Computer Vision16 results

  • Video CaptioningonActivityNet Captions
    SODA· 2023-03-11
    7.11
    SOTA
    Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed VideosarXiv:2303.06378
  • Dense Video CaptioningonActivityNet Captions
    CIDEr· 2023-03-11
    33.33
    SOTA
    Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed VideosarXiv:2303.06378
  • Dense Video CaptioningonActivityNet Captions
    SODA· 2023-03-11
    7.11
    SOTA
    Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed VideosarXiv:2303.06378
  • VideoonTACoS
    R@1,IoU=0.3· 2023-03-11
    45.92
    best: 58.1 (SG-DETR (w/ PT))
    Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed VideosarXiv:2303.06378
  • VideoonTACoS
    R@1,IoU=0.5· 2023-03-11
    34.57
    best: 46.79 (DeCafNet)
    Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed VideosarXiv:2303.06378
  • VideoonActivityNet Captions
    R@1,IoU=0.5· 2023-03-11
    49.18
    best: 60.67 (GVL (paragraph-level))
    Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed VideosarXiv:2303.06378
  • VideoonActivityNet Captions
    R@1,IoU=0.7· 2023-03-11
    29.69
    best: 38.55 (GVL (paragraph-level))
    Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed VideosarXiv:2303.06378
  • Video CaptioningonYouCook2
    CIDEr· 2023-03-11
    26.52
    best: 116.4 (HowToCaption)
    Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed VideosarXiv:2303.06378
  • Video CaptioningonYouCook2
    METEOR· 2023-03-11
    5.01
    best: 22.56 (UniVL + MELTR)
    Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed VideosarXiv:2303.06378
  • Video CaptioningonYouCook2
    SODA· 2023-03-11
    4.91
    best: 10.73 (HiCM²)
    Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed VideosarXiv:2303.06378
  • Video CaptioningonActivityNet Captions
    CIDEr· 2023-03-11
    33.33
    best: 39.3 (VideoCoCa)
    Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed VideosarXiv:2303.06378
  • Video CaptioningonActivityNet Captions
    METEOR· 2023-03-11
    10.03
    best: 17.97 (VLTinT (ae-test split) C3D/Ling)
    Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed VideosarXiv:2303.06378
  • Dense Video CaptioningonYouCook2
    CIDEr· 2023-03-11
    26.52
    best: 71.84 (HiCM²)
    Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed VideosarXiv:2303.06378
  • Dense Video CaptioningonYouCook2
    METEOR· 2023-03-11
    5.01
    best: 12.8 (HiCM²)
    Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed VideosarXiv:2303.06378
  • Dense Video CaptioningonYouCook2
    SODA· 2023-03-11
    4.91
    best: 10.73 (HiCM²)
    Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed VideosarXiv:2303.06378
  • Dense Video CaptioningonActivityNet Captions
    METEOR· 2023-03-11
    10.03
    best: 17 (Vid2Seq)
    Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed VideosarXiv:2303.06378