HyperAI

Visual Dialog On Visual Dialog V1 0 Test Std

Metrics

MRR (x 100)
Mean
NDCG (x 100)
R@1
R@10
R@5

Results

Performance results of various models on this benchmark

Comparison Table
Model NameMRR (x 100)MeanNDCG (x 100)R@1R@10R@5
multi-view-attention-networks-for-visual64.843.9759.3751.4590.6581.12
Model 256.425.4776.1744.3284.5270.23
Model 364.434.1358.1950.790.1880.83
Model 457.135.8572.3345.1782.469.95
Model 564.793.9858.2551.3290.3881.0
Model 656.055.7276.1444.7582.7568.4
factor-graph-attention69.33.1457.2055.6594.0586.73
recursive-visual-attention-in-visual-dialog63.034.1855.5949.0389.8380.40
Model 948.377.0573.0834.6577.5362.98
Model 1063.74.2658.5950.389.1579.47
Model 1153.1911.9647.5141.474.1565.85
Model 1255.116.5572.4143.2379.7767.65
Model 1356.355.7976.4345.1782.1768.12
Model 1466.633.4160.9152.5292.2784.1
visual-dialog54.26.4145.539.9381.5070.45
Model 1662.655.8974.6254.3783.3370.75
efficient-attention-mechanism-for-handling52.146.5374.8838.9280.6566.6
Model 1856.25.4177.9244.4583.7868.9
Model 1961.094.6552.5746.8387.4278.22
Model 2049.037.0772.8535.8877.7562.88
iterative-context-aware-graph-inference-for63.494.1156.6449.8590.1580.63
Model 2264.584.0359.2351.2590.0580.92
Model 2366.533.460.3352.6292.584.12
Model 2456.736.072.9945.4281.7368.92
Model 2545.756.5478.729.582.4565.7
dualvd-an-adaptive-dual-encoding-model-for63.234.1156.3249.2589.780.23
Model 2743.077.4273.1527.8276.5560.38
image-question-answer-synergistic-network-for62.204.1757.3247.90-80.43
visual-dialog55.45.9545.340.9582.8372.45
Model 3062.654.559.049.4888.3578.1
Model 3164.624.2964.7951.8289.9580.35
Model 3262.563.8255.2147.4592.081.55
Model 3364.953.4460.3150.4893.1583.15
Model 3463.34.255.9449.1889.681.0
Model 3539.619.0170.0825.6570.1253.62
Model 3658.575.1364.4844.2786.4276.15
Model 3762.684.2256.3848.689.4880.1
Model 3849.267.073.3636.3578.1262.42
Model 3960.114.749.9445.687.977.53
Model 4063.314.3158.1449.6889.2580.45
Model 4167.53.3263.8753.8593.2584.67
Model 4257.196.0472.3545.382.3870.15
Model 4350.746.2874.4737.9580.064.12
Model 4463.924.2868.0850.7889.679.53
Model 4564.573.6757.649.7591.6782.23
ensemble-of-mrr-and-ndcg-models-for-visual69.923.8472.8358.389.681.55
dual-attention-networks-for-visual-reference63.24.357.5949.6389.3579.75
making-history-matter-gold-critic-sequence64.224.2057.1750.8889.4580.63
Model 4949.476.972.5835.7778.2564.15
Model 5051.176.6975.3538.977.9862.82
Model 5156.675.9872.844.8281.968.67
Model 5247.0313.357.3936.9365.856.47
Model 5355.697.8751.8742.779.7270.17
Model 5464.34.0757.8250.5890.0381.25
Model 5566.23.2559.3351.6293.785.05
Model 5645.8420.7153.1935.961.754.97
visual-dialog55.55.9247.540.9883.3072.30
Model 587.2549.6111.843.0212.227.22
Model 5961.874.4958.5648.488.678.0
Model 6068.163.363.9454.6793.184.95
learning-to-reason-end-to-end-module-networks58.84.458.144.1586.8876.88
Model 6247.547.1472.3333.577.3363.28
Model 6364.254.1160.1950.8890.680.92
Model 6467.53.3263.8753.8593.2584.67
Model 6553.35.9146.7536.8383.173.45
Model 6641.668.371.9125.8574.6760.12
Model 6762.244.0955.8847.5889.7280.45
reasoning-visual-dialogs-with-structural-and61.374.5752.8247.3387.8377.98
Model 6964.144.1859.6950.6289.8380.77
Model 7065.73.6858.5151.7391.9782.97
Model 7156.035.9873.0744.281.6268.45
Model 7270.413.6672.1658.1790.8383.85
Model 7371.242.9664.0458.2794.4587.55
Model 7467.493.3163.7553.7593.2585.02
Model 7559.965.1253.246.3586.4876.78
Model 7670.952.9167.0957.0795.0888.42
Model 7756.346.0471.8244.2281.769.65
Model 7864.314.1158.4950.889.6580.8
visual-coreference-resolution-in-visual61.504.4054.7047.5588.8078.10
Model 8029.9722.0523.016.6253.0543.58