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-BERTLARGE

VL-BERTLARGE

Reported on 8 benchmarks across 1 task · 1 paper · 7 SOTA

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

Natural Language Processing8 results

  • Visual Question Answering (VQA)onVCR (Q-AR) test
    Accuracy· 2019-08-22
    59.7
    best: 81.6 (GPT4RoI)
    SOTA
    VL-BERT: Pre-training of Generic Visual-Linguistic RepresentationsarXiv:1908.08530
  • Visual Question Answering (VQA)onVCR (Q-AR) dev
    Accuracy· 2019-08-22
    58.9
    SOTA
    VL-BERT: Pre-training of Generic Visual-Linguistic RepresentationsarXiv:1908.08530
  • Visual Question Answering (VQA)onVCR (Q-A) dev
    Accuracy· 2019-08-22
    75.5
    SOTA
    VL-BERT: Pre-training of Generic Visual-Linguistic RepresentationsarXiv:1908.08530
  • Visual Question Answering (VQA)onVCR (QA-R) dev
    Accuracy· 2019-08-22
    77.9
    SOTA
    VL-BERT: Pre-training of Generic Visual-Linguistic RepresentationsarXiv:1908.08530
  • Visual Question Answering (VQA)onVCR (QA-R) test
    Accuracy· 2019-08-22
    78.4
    best: 91 (GPT4RoI)
    SOTA
    VL-BERT: Pre-training of Generic Visual-Linguistic RepresentationsarXiv:1908.08530
  • Visual Question Answering (VQA)onVCR (Q-A) test
    Accuracy· 2019-08-22
    75.8
    best: 89.4 (GPT4RoI)
    SOTA
    VL-BERT: Pre-training of Generic Visual-Linguistic RepresentationsarXiv:1908.08530
  • Visual Question Answering (VQA)onVQA v2 test-dev
    Accuracy· 2019-08-22
    71.79
    best: 84.3 (PaLI)
    SOTA
    VL-BERT: Pre-training of Generic Visual-Linguistic RepresentationsarXiv:1908.08530
  • Visual Question Answering (VQA)onVQA v2 test-std
    overall· 2019-08-22
    72.2
    best: 84.03 (BEiT-3)
    VL-BERT: Pre-training of Generic Visual-Linguistic RepresentationsarXiv:1908.08530