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/VL-T5

VL-T5

Reported on 7 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Natural Language Processing7 results

  • Image Captioningonnocaps val
    CIDEr· 2021-02-04
    4.4
    best: 107.9 (Prismer)
    SOTA
    Unifying Vision-and-Language Tasks via Text GenerationarXiv:2102.02779
  • Image Captioningonnocaps val
    SPICE· 2021-02-04
    5.3
    best: 14.8 (Prismer)
    SOTA
    Unifying Vision-and-Language Tasks via Text GenerationarXiv:2102.02779
  • Visual Question Answering (VQA)onVCR (Q-AR) test
    Accuracy· 2021-02-04
    58.9
    best: 81.6 (GPT4RoI)
    Unifying Vision-and-Language Tasks via Text GenerationarXiv:2102.02779
  • Visual Question Answering (VQA)onVCR (QA-R) test
    Accuracy· 2021-02-04
    77.8
    best: 91 (GPT4RoI)
    Unifying Vision-and-Language Tasks via Text GenerationarXiv:2102.02779
  • Visual Question Answering (VQA)onVCR (Q-A) test
    Accuracy· 2021-02-04
    75.3
    best: 89.4 (GPT4RoI)
    Unifying Vision-and-Language Tasks via Text GenerationarXiv:2102.02779
  • Image CaptioningonFlickr30k Captions test
    CIDEr· 2021-02-04
    2.6
    best: 67.4 (Unified VLP)
    Unifying Vision-and-Language Tasks via Text GenerationarXiv:2102.02779
  • Image CaptioningonFlickr30k Captions test
    SPICE· 2021-02-04
    2
    best: 17 (Unified VLP)
    Unifying Vision-and-Language Tasks via Text GenerationarXiv:2102.02779