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/Ensemble + Finetune

Ensemble + Finetune

Reported on 12 benchmarks across 2 tasks · 1 paper · 4 SOTA

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

Speech6 results

  • DialogueonVisual Dialog v1.0 test-std
    Mean· 2019-11-26
    6.53
    best: 49.61 (qqhe)
    SOTA
    Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple InputsarXiv:1911.11390
  • DialogueonVisual Dialog v1.0 test-std
    NDCG (x 100)· 2019-11-26
    74.88
    best: 78.7 (Single)
    SOTA
    Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple InputsarXiv:1911.11390
  • DialogueonVisual Dialog v1.0 test-std
    MRR (x 100)· 2019-11-26
    52.14
    best: 71.24 (MRR ensemble (Naive))
    Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple InputsarXiv:1911.11390
  • DialogueonVisual Dialog v1.0 test-std
    R@1· 2019-11-26
    38.92
    best: 58.3 (2 Step: Factor Graph Attention + VD-Bert)
    Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple InputsarXiv:1911.11390
  • DialogueonVisual Dialog v1.0 test-std
    R@10· 2019-11-26
    80.65
    best: 95.08 (Ensemble FGA + BERT)
    Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple InputsarXiv:1911.11390
  • DialogueonVisual Dialog v1.0 test-std
    R@5· 2019-11-26
    66.6
    best: 88.42 (Ensemble FGA + BERT)
    Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple InputsarXiv:1911.11390

Computer Vision6 results

  • Visual DialogonVisual Dialog v1.0 test-std
    Mean· 2019-11-26
    6.53
    best: 49.61 (qqhe)
    SOTA
    Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple InputsarXiv:1911.11390
  • Visual DialogonVisual Dialog v1.0 test-std
    NDCG (x 100)· 2019-11-26
    74.88
    best: 78.7 (Single)
    SOTA
    Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple InputsarXiv:1911.11390
  • Visual DialogonVisual Dialog v1.0 test-std
    MRR (x 100)· 2019-11-26
    52.14
    best: 71.24 (MRR ensemble (Naive))
    Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple InputsarXiv:1911.11390
  • Visual DialogonVisual Dialog v1.0 test-std
    R@1· 2019-11-26
    38.92
    best: 58.3 (2 Step: Factor Graph Attention + VD-Bert)
    Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple InputsarXiv:1911.11390
  • Visual DialogonVisual Dialog v1.0 test-std
    R@10· 2019-11-26
    80.65
    best: 95.08 (Ensemble FGA + BERT)
    Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple InputsarXiv:1911.11390
  • Visual DialogonVisual Dialog v1.0 test-std
    R@5· 2019-11-26
    66.6
    best: 88.42 (Ensemble FGA + BERT)
    Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple InputsarXiv:1911.11390