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/Unified VLP

Unified VLP

Reported on 9 benchmarks across 2 tasks · 1 paper · 6 SOTA

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

Natural Language Processing9 results

  • Image CaptioningonCOCO Captions test
    CIDEr· 2019-09-24
    116.9
    SOTA
    Unified Vision-Language Pre-Training for Image Captioning and VQAarXiv:1909.11059
  • Image CaptioningonCOCO Captions test
    SPICE· 2019-09-24
    21.2
    SOTA
    Unified Vision-Language Pre-Training for Image Captioning and VQAarXiv:1909.11059
  • Image CaptioningonFlickr30k Captions test
    BLEU-4· 2019-09-24
    30.1
    SOTA
    Unified Vision-Language Pre-Training for Image Captioning and VQAarXiv:1909.11059
  • Image CaptioningonFlickr30k Captions test
    CIDEr· 2019-09-24
    67.4
    SOTA
    Unified Vision-Language Pre-Training for Image Captioning and VQAarXiv:1909.11059
  • Image CaptioningonFlickr30k Captions test
    METEOR· 2019-09-24
    23
    SOTA
    Unified Vision-Language Pre-Training for Image Captioning and VQAarXiv:1909.11059
  • Image CaptioningonFlickr30k Captions test
    SPICE· 2019-09-24
    17
    SOTA
    Unified Vision-Language Pre-Training for Image Captioning and VQAarXiv:1909.11059
  • Visual Question Answering (VQA)onVQA v2 test-std
    overall· 2019-09-24
    70.7
    best: 84.03 (BEiT-3)
    Unified Vision-Language Pre-Training for Image Captioning and VQAarXiv:1909.11059
  • Image CaptioningonCOCO Captions test
    BLEU-4· 2019-09-24
    36.5
    best: 56.7 (From Captions to Visual Concepts and Back)
    Unified Vision-Language Pre-Training for Image Captioning and VQAarXiv:1909.11059
  • Image CaptioningonCOCO Captions test
    METEOR· 2019-09-24
    28.4
    best: 33.1 (From Captions to Visual Concepts and Back)
    Unified Vision-Language Pre-Training for Image Captioning and VQAarXiv:1909.11059