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/RefineCap (w/ REINFORCE)

RefineCap (w/ REINFORCE)

Reported on 8 benchmarks across 1 task · 1 paper

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

Natural Language Processing8 results

  • Image CaptioningonCOCO Captions
    BLEU-1· 2021-09-08
    80.2
    best: 84.2 (GRIT (No VL pretraining - base))
    RefineCap: Concept-Aware Refinement for Image CaptioningarXiv:2109.03529
  • Image CaptioningonCOCO Captions
    BLEU-2· 2021-09-08
    64.5
    best: 65.8 (X-Transformer)
    RefineCap: Concept-Aware Refinement for Image CaptioningarXiv:2109.03529
  • Image CaptioningonCOCO Captions
    BLEU-3· 2021-09-08
    49.9
    best: 51.5 (X-Transformer)
    RefineCap: Concept-Aware Refinement for Image CaptioningarXiv:2109.03529
  • Image CaptioningonCOCO Captions
    BLEU-4· 2021-09-08
    37.8
    best: 46.5 (mPLUG)
    RefineCap: Concept-Aware Refinement for Image CaptioningarXiv:2109.03529
  • Image CaptioningonCOCO Captions
    CIDER· 2021-09-08
    127.2
    best: 155.1 (mPLUG)
    RefineCap: Concept-Aware Refinement for Image CaptioningarXiv:2109.03529
  • Image CaptioningonCOCO Captions
    METEOR· 2021-09-08
    28.3
    best: 33.9 (CoCa)
    RefineCap: Concept-Aware Refinement for Image CaptioningarXiv:2109.03529
  • Image CaptioningonCOCO Captions
    ROUGE-L· 2021-09-08
    58
    best: 61.1 (ExpansionNet v2 (No VL pretraining))
    RefineCap: Concept-Aware Refinement for Image CaptioningarXiv:2109.03529
  • Image CaptioningonCOCO Captions
    SPICE· 2021-09-08
    22.5
    best: 27 (VAST)
    RefineCap: Concept-Aware Refinement for Image CaptioningarXiv:2109.03529