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/IBM Research AI

IBM Research AI

Reported on 16 benchmarks across 1 task

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

Natural Language Processing16 results

  • Image CaptioningonVizWiz 2020 test-dev
    B1
    72.48
  • Image CaptioningonVizWiz 2020 test-dev
    B2
    53.93
  • Image CaptioningonVizWiz 2020 test-dev
    B3
    38.79
    best: 39.28 (CASIA_IVA)
  • Image CaptioningonVizWiz 2020 test-dev
    B4
    27.35
    best: 28.27 (CASIA_IVA)
  • Image CaptioningonVizWiz 2020 test-dev
    CIDEr
    80.67
  • Image CaptioningonVizWiz 2020 test-dev
    METEOR
    22.21
  • Image CaptioningonVizWiz 2020 test-dev
    ROUGE-L
    50.11
    best: 50.27 (CASIA_IVA)
  • Image CaptioningonVizWiz 2020 test-dev
    SPICE
    16.96
    best: 17.9 (CASIA_IVA)
  • Image CaptioningonVizWiz 2020 test
    B1
    72.77
  • Image CaptioningonVizWiz 2020 test
    B2
    54.17
  • Image CaptioningonVizWiz 2020 test
    B3
    38.97
  • Image CaptioningonVizWiz 2020 test
    B4
    27.44
    best: 27.96 (CASIA_IVA)
  • Image CaptioningonVizWiz 2020 test
    CIDEr
    81.04
  • Image CaptioningonVizWiz 2020 test
    METEOR
    22.25
  • Image CaptioningonVizWiz 2020 test
    ROUGE-L
    50.2
  • Image CaptioningonVizWiz 2020 test
    SPICE
    17
    best: 17.79 (CASIA_IVA)