Visual Dialog on VisDial 0.5 (test)

0.635MRR

Human Performance

Updated 4d ago

Evaluation Results

Method
Human Performance 2016.11	0.635	48.03	83.76	-	2.83
Human Performance 2016.11	0.619	46.12	82.54	-	2.92
Memory Network (MN) 2016.11	0.529	37.33	68.47	79.54	7.03
Memory Network (MN) 2016.11	0.524	36.84	67.78	78.92	7.25
Late Fusion (LF) 2016.11	0.511	36.72	67.46	78.3	7.63
HieCoAtt 2016.11	0.509	35.54	66.79	77.94	7.68
HREA 2016.11	0.508	36.76	66.54	77.75	7.59
SAN 2016.11	0.506	36.21	67.08	78.16	7.74
Late Fusion (LF) 2016.11	0.505	36.21	66.56	77.31	7.89
Late Fusion (LF) 2016.11	0.502	35.76	66.59	77.61	7.72
Hierarchical Recurrent Encoder (HRE) 2016.11	0.502	36.26	65.67	77.05	7.79
Hierarchical Recurrent Encoder (HRE) 2016.11	0.489	34.74	64.25	75.4	8.32
Human Performance 2016.11	0.485	30.31	70.53	-	3.91
Late Fusion (LF) 2016.11	0.482	34.29	63.42	74.31	8.87
Memory Network (MN) 2016.11	0.443	34.62	53.74	60.18	21.69
Hierarchical Recurrent Encoder (HRE) 2016.11	0.442	34.37	53.4	59.74	21.75
HREA 2016.11	0.442	34.47	53.43	59.73	21.83
Human Performance 2016.11	0.441	25.1	67.37	-	4.19
Late Fusion (LF) 2016.11	0.437	34.06	52.5	58.89	22.31
Memory Network (MN) 2016.11	0.434	33.12	53.14	59.61	22.14
Late Fusion (LF) 2016.11	0.43	33.27	51.96	58.09	23.04
Hierarchical Recurrent Encoder (HRE) 2016.11	0.43	32.84	52.36	58.64	22.59
Late Fusion (LF) 2016.11	0.425	32.49	51.56	57.8	23.11
Late Fusion (LF) 2016.11	0.403	29.74	50.1	56.32	24.06
NN-Q 2016.11	0.392	30.54	46.99	49.98	30.88
NN-QI 2016.11	0.385	29.71	46.57	49.86	30.9
Answer prior 2016.11	0.311	19.85	39.14	44.28	31.56