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/Enc-Dec

Enc-Dec

Reported on 8 benchmarks across 1 task · 1 paper · 1 SOTA

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

Natural Language Processing8 results

  • Image Captioningonnocaps-val-out-domain
    CIDEr· 2021-02-17
    94.5
    best: 124.8 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
    SOTA
    Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual ConceptsarXiv:2102.08981
  • Image Captioningonnocaps-val-out-domain
    SPICE· 2021-02-17
    11.9
    best: 15.1 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
    Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual ConceptsarXiv:2102.08981
  • Image Captioningonnocaps-val-near-domain
    CIDEr· 2021-02-17
    88.3
    best: 120.2 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
    Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual ConceptsarXiv:2102.08981
  • Image Captioningonnocaps-val-near-domain
    SPICE· 2021-02-17
    12.1
    best: 15.9 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
    Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual ConceptsarXiv:2102.08981
  • Image Captioningonnocaps-val-overall
    CIDEr· 2021-02-17
    90.2
    best: 121.6 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
    Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual ConceptsarXiv:2102.08981
  • Image Captioningonnocaps-val-overall
    SPICE· 2021-02-17
    12.1
    best: 15.8 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
    Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual ConceptsarXiv:2102.08981
  • Image Captioningonnocaps-val-in-domain
    CIDEr· 2021-02-17
    92.6
    best: 123.7 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
    Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual ConceptsarXiv:2102.08981
  • Image Captioningonnocaps-val-in-domain
    SPICE· 2021-02-17
    12.5
    best: 16.3 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
    Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual ConceptsarXiv:2102.08981