Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/DualVD

DualVD

Reported on 22 benchmarks across 2 tasks · 1 paper

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

Speech11 results

DialogueonVisDial v0.9 val
MRR· 2019-11-17
62.94
best: 68.92 (9xFGA (VGG))
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue arXiv:1911.07251
DialogueonVisDial v0.9 val
Mean Rank· 2019-11-17
4.17
best: 5.84 (HieCoAtt-QI)
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue arXiv:1911.07251
DialogueonVisDial v0.9 val
R@1· 2019-11-17
48.64
best: 55.16 (9xFGA (VGG))
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue arXiv:1911.07251
DialogueonVisDial v0.9 val
R@10· 2019-11-17
89.94
best: 92.95 (9xFGA (VGG))
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue arXiv:1911.07251
DialogueonVisDial v0.9 val
R@5· 2019-11-17
80.89
best: 86.26 (9xFGA (VGG))
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue arXiv:1911.07251
DialogueonVisual Dialog v1.0 test-std
MRR (x 100)· 2019-11-17
63.23
best: 71.24 (MRR ensemble (Naive))
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue arXiv:1911.07251
DialogueonVisual Dialog v1.0 test-std
Mean· 2019-11-17
4.11
best: 49.61 (qqhe)
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue arXiv:1911.07251
DialogueonVisual Dialog v1.0 test-std
NDCG (x 100)· 2019-11-17
56.32
best: 78.7 (Single)
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue arXiv:1911.07251
DialogueonVisual Dialog v1.0 test-std
R@1· 2019-11-17
49.25
best: 58.3 (2 Step: Factor Graph Attention + VD-Bert)
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue arXiv:1911.07251
DialogueonVisual Dialog v1.0 test-std
R@10· 2019-11-17
89.7
best: 95.08 (Ensemble FGA + BERT)
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue arXiv:1911.07251
DialogueonVisual Dialog v1.0 test-std
R@5· 2019-11-17
80.23
best: 88.42 (Ensemble FGA + BERT)
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue arXiv:1911.07251

Computer Vision11 results

Visual DialogonVisDial v0.9 val
MRR· 2019-11-17
62.94
best: 68.92 (9xFGA (VGG))
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue arXiv:1911.07251
Visual DialogonVisDial v0.9 val
Mean Rank· 2019-11-17
4.17
best: 5.84 (HieCoAtt-QI)
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue arXiv:1911.07251
Visual DialogonVisDial v0.9 val
R@1· 2019-11-17
48.64
best: 55.16 (9xFGA (VGG))
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue arXiv:1911.07251
Visual DialogonVisDial v0.9 val
R@10· 2019-11-17
89.94
best: 92.95 (9xFGA (VGG))
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue arXiv:1911.07251
Visual DialogonVisDial v0.9 val
R@5· 2019-11-17
80.89
best: 86.26 (9xFGA (VGG))
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue arXiv:1911.07251
Visual DialogonVisual Dialog v1.0 test-std
MRR (x 100)· 2019-11-17
63.23
best: 71.24 (MRR ensemble (Naive))
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue arXiv:1911.07251
Visual DialogonVisual Dialog v1.0 test-std
Mean· 2019-11-17
4.11
best: 49.61 (qqhe)
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue arXiv:1911.07251
Visual DialogonVisual Dialog v1.0 test-std
NDCG (x 100)· 2019-11-17
56.32
best: 78.7 (Single)
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue arXiv:1911.07251
Visual DialogonVisual Dialog v1.0 test-std
R@1· 2019-11-17
49.25
best: 58.3 (2 Step: Factor Graph Attention + VD-Bert)
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue arXiv:1911.07251
Visual DialogonVisual Dialog v1.0 test-std
R@10· 2019-11-17
89.7
best: 95.08 (Ensemble FGA + BERT)
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue arXiv:1911.07251
Visual DialogonVisual Dialog v1.0 test-std
R@5· 2019-11-17
80.23
best: 88.42 (Ensemble FGA + BERT)
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue arXiv:1911.07251