Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Computer Vision
/
Visual Dialog
/
Visual Dialog v1.0 test-std
Visual Dialog on Visual Dialog v1.0 test-std
Metric: Mean (higher is better)
Leaderboard
Dataset
Loading chart...
Results
Submit a result
Export CSV
Sort:
Mean (best first)
Mean (worst first)
Date (newest first)
Date (oldest first)
Model name (A→Z)
#
Model
↕
Mean
▼
Extra Data
Paper
Date
↕
Code
1
qqhe
49.61
No
-
-
-
2
czczx
22.05
No
-
-
-
3
trainval_ch_9
20.71
No
-
-
-
4
mvan_len40_test
13.3
No
-
-
-
5
gat_disc_3
11.96
No
-
-
-
6
5TS
9.01
No
-
-
-
7
simple_test
8.3
No
-
-
-
8
gat_disc_relto_4
7.87
No
-
-
-
9
2
7.42
No
-
-
-
10
20
7.14
No
-
-
-
11
5-2
7.07
No
-
-
-
12
5_4
7.05
No
-
-
-
13
2
7
No
-
-
-
14
10
6.9
No
-
-
-
15
Ensemble
6.69
No
-
-
-
16
Disc, Dense, 4 Ensemble.
6.55
No
-
-
-
17
Single
6.54
No
-
-
-
18
Ensemble + Finetune
6.53
No
Efficient Attention Mechanism for Visual Dialog ...
2019-11-26
Code
19
HRE-QIH-D
6.41
No
Visual Dialog
2016-11-26
Code
20
CE-finetuned, single model
6.28
No
-
-
-
21
shanshandu
6.04
No
-
-
-
22
1
6.04
No
-
-
-
23
1
6
No
-
-
-
24
7
5.98
No
-
-
-
25
1
5.98
No
-
-
-
26
MN-QIH-D
5.95
No
Visual Dialog
2016-11-26
Code
27
MN-QIH-D
5.92
No
Visual Dialog
2016-11-26
Code
28
paratraining1epoch
5.91
No
-
-
-
29
bert-double-stream-finetuning
5.89
No
-
-
-
30
1
5.85
No
-
-
-
31
Ensemble + Fine-tuning
5.79
No
-
-
-
32
VD-PCR
5.72
No
-
-
-
33
ensemble, finetune
5.47
No
-
-
-
34
P1P2+Distill+Ensemble
5.41
No
-
-
-
35
sdfsdaf
5.13
No
-
-
-
36
jkl
5.12
No
-
-
-
37
adasd
4.7
No
-
-
-
38
DLC-4
4.65
No
-
-
-
39
GNN
4.57
No
Reasoning Visual Dialogs with Structural and Par...
2019-04-11
Code
40
lkh(single-model)
4.5
No
-
-
-
41
wqedasd(single model)
4.49
No
-
-
-
42
NMN
4.4
No
Learning to Reason: End-to-End Module Networks f...
2017-04-18
Code
43
CorefNMN (ResNet-152)
4.4
No
Visual Coreference Resolution in Visual Dialog u...
2018-09-06
Code
44
lijunlin_9
4.31
No
-
-
-
45
DAN
4.3
No
Dual Attention Networks for Visual Reference Res...
2019-02-25
Code
46
CARE(Single Model)
4.29
No
-
-
-
47
Bert(two-stream)
4.28
No
-
-
-
48
lijunlin_7
4.26
No
-
-
-
49
kbgn_disc_5
4.22
No
-
-
-
50
HACAN
4.2
No
Making History Matter: History-Advantage Sequenc...
2019-02-25
-
51
ERIC666
4.2
No
-
-
-
52
211
4.18
No
-
-
-
53
RVA
4.18
No
Recursive Visual Attention in Visual Dialog
2018-12-06
Code
54
Synergistic
4.17
No
Image-Question-Answer Synergistic Network for Vi...
2019-02-26
-
55
disc
4.13
No
-
-
-
56
1
4.11
No
-
-
-
57
zxcdd
4.11
No
-
-
-
58
CAG
4.11
No
Iterative Context-Aware Graph Inference for Visu...
2020-04-05
Code
59
DualVD
4.11
No
DualVD: An Adaptive Dual Encoding Model for Deep...
2019-11-17
Code
60
eightepoch
4.09
No
-
-
-
61
zuizhong
4.07
No
-
-
-
62
gr
4.03
No
-
-
-
63
jiuyigedian
3.98
No
-
-
-
64
MVAN
3.97
No
Multi-View Attention Network for Visual Dialog
2020-04-29
Code
65
2 Step: Factor Graph Attention + VD-Bert
3.84
No
Ensemble of MRR and NDCG models for Visual Dialog
2021-04-15
Code
66
single-model
3.82
No
-
-
-
67
Bert2constraints
3.68
No
-
-
-
68
clean_wac_4freeze
3.67
No
-
-
-
69
Two-Step(refactor)
3.66
No
-
-
-
70
single-model
3.44
No
-
-
-
71
SCL_48
3.41
No
-
-
-
72
Transformer+2cons
3.4
No
-
-
-
73
w/ VQA + CC, single model
3.32
No
-
-
-
74
test1
3.32
No
-
-
-
75
sh101
3.31
No
-
-
-
76
CAF
3.3
No
-
-
-
77
single model
3.25
No
-
-
-
78
5xFGA (F-RCNNx101)
3.14
No
Factor Graph Attention
2019-04-11
Code
79
MRR ensemble (Naive)
2.96
No
-
-
-
80
Ensemble FGA + BERT
2.91
No
-
-
-
#1
qqhe
49.61
Mean
No paper
#2
czczx
22.05
Mean
No paper
#3
trainval_ch_9
20.71
Mean
No paper
#4
mvan_len40_test
13.3
Mean
No paper
#5
gat_disc_3
11.96
Mean
No paper
#6
5TS
9.01
Mean
No paper
#7
simple_test
8.3
Mean
No paper
#8
gat_disc_relto_4
7.87
Mean
No paper
#9
2
7.42
Mean
No paper
#10
20
7.14
Mean
No paper
#11
5-2
7.07
Mean
No paper
#12
5_4
7.05
Mean
No paper
#13
2
7
Mean
No paper
#14
10
6.9
Mean
No paper
#15
Ensemble
6.69
Mean
No paper
#16
Disc, Dense, 4 Ensemble.
6.55
Mean
No paper
#17
Single
6.54
Mean
No paper
#18
Ensemble + Finetune
SOTA
6.53
Mean
· 2019-11-26
Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple Inputs
Code
#19
HRE-QIH-D
SOTA
6.41
Mean
· 2016-11-26
Visual Dialog
Code
#20
CE-finetuned, single model
6.28
Mean
No paper
#21
shanshandu
6.04
Mean
No paper
#22
1
6.04
Mean
No paper
#23
1
6
Mean
No paper
#24
7
5.98
Mean
No paper
#25
1
5.98
Mean
No paper
#26
MN-QIH-D
5.95
Mean
· 2016-11-26
Visual Dialog
Code
#27
MN-QIH-D
5.92
Mean
· 2016-11-26
Visual Dialog
Code
#28
paratraining1epoch
5.91
Mean
No paper
#29
bert-double-stream-finetuning
5.89
Mean
No paper
#30
1
5.85
Mean
No paper
#31
Ensemble + Fine-tuning
5.79
Mean
No paper
#32
VD-PCR
5.72
Mean
No paper
#33
ensemble, finetune
5.47
Mean
No paper
#34
P1P2+Distill+Ensemble
5.41
Mean
No paper
#35
sdfsdaf
5.13
Mean
No paper
#36
jkl
5.12
Mean
No paper
#37
adasd
4.7
Mean
No paper
#38
DLC-4
4.65
Mean
No paper
#39
GNN
4.57
Mean
· 2019-04-11
Reasoning Visual Dialogs with Structural and Partial Observations
Code
#40
lkh(single-model)
4.5
Mean
No paper
#41
wqedasd(single model)
4.49
Mean
No paper
#42
NMN
4.4
Mean
· 2017-04-18
Learning to Reason: End-to-End Module Networks for Visual Question Answering
Code
#43
CorefNMN (ResNet-152)
4.4
Mean
· 2018-09-06
Visual Coreference Resolution in Visual Dialog using Neural Module Networks
Code
#44
lijunlin_9
4.31
Mean
No paper
#45
DAN
4.3
Mean
· 2019-02-25
Dual Attention Networks for Visual Reference Resolution in Visual Dialog
Code
#46
CARE(Single Model)
4.29
Mean
No paper
#47
Bert(two-stream)
4.28
Mean
No paper
#48
lijunlin_7
4.26
Mean
No paper
#49
kbgn_disc_5
4.22
Mean
No paper
#50
HACAN
4.2
Mean
· 2019-02-25
Making History Matter: History-Advantage Sequence Training for Visual Dialog
#51
ERIC666
4.2
Mean
No paper
#52
211
4.18
Mean
No paper
#53
RVA
4.18
Mean
· 2018-12-06
Recursive Visual Attention in Visual Dialog
Code
#54
Synergistic
4.17
Mean
· 2019-02-26
Image-Question-Answer Synergistic Network for Visual Dialog
#55
disc
4.13
Mean
No paper
#56
1
4.11
Mean
No paper
#57
zxcdd
4.11
Mean
No paper
#58
CAG
4.11
Mean
· 2020-04-05
Iterative Context-Aware Graph Inference for Visual Dialog
Code
#59
DualVD
4.11
Mean
· 2019-11-17
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue
Code
#60
eightepoch
4.09
Mean
No paper
#61
zuizhong
4.07
Mean
No paper
#62
gr
4.03
Mean
No paper
#63
jiuyigedian
3.98
Mean
No paper
#64
MVAN
3.97
Mean
· 2020-04-29
Multi-View Attention Network for Visual Dialog
Code
#65
2 Step: Factor Graph Attention + VD-Bert
3.84
Mean
· 2021-04-15
Ensemble of MRR and NDCG models for Visual Dialog
Code
#66
single-model
3.82
Mean
No paper
#67
Bert2constraints
3.68
Mean
No paper
#68
clean_wac_4freeze
3.67
Mean
No paper
#69
Two-Step(refactor)
3.66
Mean
No paper
#70
single-model
3.44
Mean
No paper
#71
SCL_48
3.41
Mean
No paper
#72
Transformer+2cons
3.4
Mean
No paper
#73
w/ VQA + CC, single model
3.32
Mean
No paper
#74
test1
3.32
Mean
No paper
#75
sh101
3.31
Mean
No paper
#76
CAF
3.3
Mean
No paper
#77
single model
3.25
Mean
No paper
#78
5xFGA (F-RCNNx101)
3.14
Mean
· 2019-04-11
Factor Graph Attention
Code
#79
MRR ensemble (Naive)
2.96
Mean
No paper
#80
Ensemble FGA + BERT
2.91
Mean
No paper