Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Natural Language Processing
/
Image Captioning
/
nocaps near-domain
Image Captioning on nocaps near-domain
Metric: METEOR (higher is better)
Leaderboard
Dataset
Loading chart...
Results
Submit a result
Export CSV
Sort:
METEOR (best first)
METEOR (worst first)
Date (newest first)
Date (oldest first)
Model name (A→Z)
#
Model
↕
METEOR
▼
Extra Data
Paper
Date
↕
Code
1
PaLI
33.47
No
PaLI: A Jointly-Scaled Multilingual Language-Ima...
2022-09-14
Code
2
GIT2, Single Model
32.95
No
GIT: A Generative Image-to-text Transformer for ...
2022-05-27
Code
3
GIT, Single Model
32.86
No
GIT: A Generative Image-to-text Transformer for ...
2022-05-27
Code
4
CoCa - Google Brain
32.71
No
-
-
-
5
Microsoft Cognitive Services team
31.8
No
VIVO: Visual Vocabulary Pre-Training for Novel O...
2020-09-28
-
6
FudanFVL
31.08
No
-
-
-
7
Single Model
30.97
No
SimVLM: Simple Visual Language Model Pretraining...
2021-08-24
Code
8
FudanWYZ
30.79
No
-
-
-
9
firethehole
30.48
No
-
-
-
10
IEDA-LAB
29.53
No
-
-
-
11
vll@mk514
29.11
No
-
-
-
12
MD
28.84
No
-
-
-
13
Human
28.42
No
-
-
-
14
VinVL (Microsoft Cognitive Services + MSR)
28.24
No
VinVL: Revisiting Visual Representations in Visi...
2021-01-02
Code
15
ViTCAP-CIDEr-136.7-ENC-DEC-ViTbfocal10-test-CBS
27.89
No
-
-
-
16
camel XE
26.87
No
-
-
-
17
evertyhing
26.68
No
-
-
-
18
icgp2ssi1_coco_si_0.02_5_test
26.63
No
-
-
-
19
RCAL
26.3
No
-
-
-
20
vinvl_yuan_cbs
25.98
No
-
-
-
21
Oscar
25.91
No
-
-
-
22
cxy_nocaps_training
25.64
No
-
-
-
23
Xinyi
25.64
No
-
-
-
24
MQ-UpDown-C
25.59
No
-
-
-
25
UpDown + ELMo + CBS
24.97
No
-
-
-
26
7_10-7_40000_predict_test.json
24.52
No
-
-
-
27
nocaps_training
23.6
No
-
-
-
28
UpDown
23.6
No
-
-
-
29
None
23.12
No
-
-
-
30
Neural Baby Talk + CBS
22.55
No
-
-
-
31
area_attention
22.43
No
-
-
-
32
B2
22.41
No
-
-
-
33
YX
22.27
No
-
-
-
34
Neural Baby Talk
21.93
No
-
-
-
35
coco_all_19
21.48
No
-
-
-
36
Yu-Wu
20.18
No
-
-
-
37
CS395T
20.05
No
-
-
-
#1
PaLI
SOTA
33.47
METEOR
· 2022-09-14
PaLI: A Jointly-Scaled Multilingual Language-Image Model
Code
#2
GIT2, Single Model
SOTA
32.95
METEOR
· 2022-05-27
GIT: A Generative Image-to-text Transformer for Vision and Language
Code
#3
GIT, Single Model
32.86
METEOR
· 2022-05-27
GIT: A Generative Image-to-text Transformer for Vision and Language
Code
#4
CoCa - Google Brain
32.71
METEOR
No paper
#5
Microsoft Cognitive Services team
SOTA
31.8
METEOR
· 2020-09-28
VIVO: Visual Vocabulary Pre-Training for Novel Object Captioning
#6
FudanFVL
31.08
METEOR
No paper
#7
Single Model
30.97
METEOR
· 2021-08-24
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
Code
#8
FudanWYZ
30.79
METEOR
No paper
#9
firethehole
30.48
METEOR
No paper
#10
IEDA-LAB
29.53
METEOR
No paper
#11
vll@mk514
29.11
METEOR
No paper
#12
MD
28.84
METEOR
No paper
#13
Human
28.42
METEOR
No paper
#14
VinVL (Microsoft Cognitive Services + MSR)
28.24
METEOR
· 2021-01-02
VinVL: Revisiting Visual Representations in Vision-Language Models
Code
#15
ViTCAP-CIDEr-136.7-ENC-DEC-ViTbfocal10-test-CBS
27.89
METEOR
No paper
#16
camel XE
26.87
METEOR
No paper
#17
evertyhing
26.68
METEOR
No paper
#18
icgp2ssi1_coco_si_0.02_5_test
26.63
METEOR
No paper
#19
RCAL
26.3
METEOR
No paper
#20
vinvl_yuan_cbs
25.98
METEOR
No paper
#21
Oscar
25.91
METEOR
No paper
#22
cxy_nocaps_training
25.64
METEOR
No paper
#23
Xinyi
25.64
METEOR
No paper
#24
MQ-UpDown-C
25.59
METEOR
No paper
#25
UpDown + ELMo + CBS
24.97
METEOR
No paper
#26
7_10-7_40000_predict_test.json
24.52
METEOR
No paper
#27
nocaps_training
23.6
METEOR
No paper
#28
UpDown
23.6
METEOR
No paper
#29
None
23.12
METEOR
No paper
#30
Neural Baby Talk + CBS
22.55
METEOR
No paper
#31
area_attention
22.43
METEOR
No paper
#32
B2
22.41
METEOR
No paper
#33
YX
22.27
METEOR
No paper
#34
Neural Baby Talk
21.93
METEOR
No paper
#35
coco_all_19
21.48
METEOR
No paper
#36
Yu-Wu
20.18
METEOR
No paper
#37
CS395T
20.05
METEOR
No paper