Image Captioning on nocaps entire

Metric: B4 (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	B4▼	Extra Data	Paper	Date↕	Code
1	CoCa - Google Brain	37.71	No	-	-	-
2	GIT, Single Model	37.35	No	GIT: A Generative Image-to-text Transformer for ...	2022-05-27	Code
3	Microsoft Cognitive Services team	34.65	No	Scaling Up Vision-Language Pre-training for Imag...	2021-11-24	-
4	Prismer	33.66	No	Prismer: A Vision-Language Model with Multi-Task...	2023-03-04	Code
5	Single Model	32.2	No	SimVLM: Simple Visual Language Model Pretraining...	2021-08-24	Code
6	FudanFVL	32.17	No	-	-	-
7	FudanWYZ	31.38	No	-	-	-
8	firethehole	30.2	No	-	-	-
9	IEDA-LAB	29.27	No	-	-	-
10	MD	28.2	No	-	-	-
11	vll@mk514	27.32	No	-	-	-
12	ViTCAP-CIDEr-136.7-ENC-DEC-ViTbfocal10-test-CBS	26.52	No	-	-	-
13	VinVL (Microsoft Cognitive Services + MSR)	26.15	No	VinVL: Revisiting Visual Representations in Visi...	2021-01-02	Code
14	icgp2ssi1_coco_si_0.02_5_test	24.62	No	-	-	-
15	evertyhing	23.52	No	-	-	-
16	camel XE	23.48	No	-	-	-
17	RCAL	21.24	No	-	-	-
18	Oscar	21.02	No	-	-	-
19	vinvl_yuan_cbs	20.3	No	-	-	-
20	MQ-UpDown-C	20.11	No	-	-	-
21	cxy_nocaps_training	19.72	No	-	-	-
22	Human	19.48	No	-	-	-
23	Xinyi	19.43	No	-	-	-
24	nocaps_training	19.16	No	-	-	-
25	UpDown	19.16	No	-	-	-
26	UpDown + ELMo + CBS	18.41	No	-	-	-
27	7_10-7_40000_predict_test.json	17.75	No	-	-	-
28	B2	17.69	No	-	-	-
29	None	16.73	No	-	-	-
30	area_attention	16.48	No	-	-	-
31	YX	16.31	No	-	-	-
32	coco_all_19	15.02	No	-	-	-
33	Neural Baby Talk	14.73	No	-	-	-
34	Neural Baby Talk + CBS	12.88	No	-	-	-
35	Yu-Wu	11.96	No	-	-	-
36	CS395T	11.72	No	-	-	-

#1CoCa - Google Brain
37.71
B4
No paper
#2GIT, Single ModelSOTA
37.35
B4· 2022-05-27
GIT: A Generative Image-to-text Transformer for Vision and Language Code
#3Microsoft Cognitive Services teamSOTA
34.65
B4· 2021-11-24
Scaling Up Vision-Language Pre-training for Image Captioning
#4Prismer
33.66
B4· 2023-03-04
Prismer: A Vision-Language Model with Multi-Task Experts Code
#5Single ModelSOTA
32.2
B4· 2021-08-24
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision Code
#6FudanFVL
32.17
B4
No paper
#7FudanWYZ
31.38
B4
No paper
#8firethehole
30.2
B4
No paper
#9IEDA-LAB
29.27
B4
No paper
#10MD
28.2
B4
No paper
#11vll@mk514
27.32
B4
No paper
#12ViTCAP-CIDEr-136.7-ENC-DEC-ViTbfocal10-test-CBS
26.52
B4
No paper
#13VinVL (Microsoft Cognitive Services + MSR)SOTA
26.15
B4· 2021-01-02
VinVL: Revisiting Visual Representations in Vision-Language Models Code
#14icgp2ssi1_coco_si_0.02_5_test
24.62
B4
No paper
#15evertyhing
23.52
B4
No paper
#16camel XE
23.48
B4
No paper
#17RCAL
21.24
B4
No paper
#18Oscar
21.02
B4
No paper
#19vinvl_yuan_cbs
20.3
B4
No paper
#20MQ-UpDown-C
20.11
B4
No paper
#21cxy_nocaps_training
19.72
B4
No paper
#22Human
19.48
B4
No paper
#23Xinyi
19.43
B4
No paper
#24nocaps_training
19.16
B4
No paper
#25UpDown
19.16
B4
No paper
#26UpDown + ELMo + CBS
18.41
B4
No paper
#277_10-7_40000_predict_test.json
17.75
B4
No paper
#28B2
17.69
B4
No paper
#29None
16.73
B4
No paper
#30area_attention
16.48
B4
No paper
#31YX
16.31
B4
No paper
#32coco_all_19
15.02
B4
No paper
#33Neural Baby Talk
14.73
B4
No paper
#34Neural Baby Talk + CBS
12.88
B4
No paper
#35Yu-Wu
11.96
B4
No paper
#36CS395T
11.72
B4
No paper