Image Captioning on nocaps entire

Metric: SPICE (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	SPICE▼	Extra Data	Paper	Date↕	Code
1	GIT, Single Model	15.94	No	GIT: A Generative Image-to-text Transformer for ...	2022-05-27	Code
2	CoCa - Google Brain	15.47	No	-	-	-
3	Prismer	14.91	No	Prismer: A Vision-Language Model with Multi-Task...	2023-03-04	Code
4	Microsoft Cognitive Services team	14.85	No	Scaling Up Vision-Language Pre-training for Imag...	2021-11-24	-
5	firethehole	14.74	No	-	-	-
6	FudanFVL	14.72	No	-	-	-
7	Human	14.67	No	-	-	-
8	FudanWYZ	14.56	No	-	-	-
9	Single Model	14.49	No	SimVLM: Simple Visual Language Model Pretraining...	2021-08-24	Code
10	vll@mk514	14.06	No	-	-	-
11	IEDA-LAB	13.9	No	-	-	-
12	MD	13.35	No	-	-	-
13	VinVL (Microsoft Cognitive Services + MSR)	13.07	No	VinVL: Revisiting Visual Representations in Visi...	2021-01-02	Code
14	ViTCAP-CIDEr-136.7-ENC-DEC-ViTbfocal10-test-CBS	12.81	No	-	-	-
15	RCAL	12.2	No	-	-	-
16	evertyhing	12.1	No	-	-	-
17	icgp2ssi1_coco_si_0.02_5_test	12.01	No	-	-	-
18	vinvl_yuan_cbs	11.9	No	-	-	-
19	camel XE	11.89	No	-	-	-
20	MQ-UpDown-C	11.68	No	-	-	-
21	Xinyi	11.62	No	-	-	-
22	cxy_nocaps_training	11.57	No	-	-	-
23	Oscar	11.29	No	-	-	-
24	UpDown + ELMo + CBS	11.2	No	-	-	-
25	ClipCap (MLP + GPT2 tuning)	11.1	No	ClipCap: CLIP Prefix for Image Captioning	2021-11-18	Code
26	7_10-7_40000_predict_test.json	10.96	No	-	-	-
27	ClipCap (Transformer)	10.86	No	ClipCap: CLIP Prefix for Image Captioning	2021-11-18	Code
28	nocaps_training	10.14	No	-	-	-
29	UpDown	10.14	No	-	-	-
30	None	10.1	No	-	-	-
31	Neural Baby Talk + CBS	9.69	No	-	-	-
32	area_attention	9.56	No	-	-	-
33	YX	9.54	No	-	-	-
34	B2	9.42	No	-	-	-
35	Neural Baby Talk	9.15	No	-	-	-
36	coco_all_19	9.13	No	-	-	-
37	Yu-Wu	8.35	No	-	-	-
38	CS395T	8.2	No	-	-	-

#1GIT, Single ModelSOTA
15.94
SPICE· 2022-05-27
GIT: A Generative Image-to-text Transformer for Vision and Language Code
#2CoCa - Google Brain
15.47
SPICE
No paper
#3Prismer
14.91
SPICE· 2023-03-04
Prismer: A Vision-Language Model with Multi-Task Experts Code
#4Microsoft Cognitive Services teamSOTA
14.85
SPICE· 2021-11-24
Scaling Up Vision-Language Pre-training for Image Captioning
#5firethehole
14.74
SPICE
No paper
#6FudanFVL
14.72
SPICE
No paper
#7Human
14.67
SPICE
No paper
#8FudanWYZ
14.56
SPICE
No paper
#9Single ModelSOTA
14.49
SPICE· 2021-08-24
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision Code
#10vll@mk514
14.06
SPICE
No paper
#11IEDA-LAB
13.9
SPICE
No paper
#12MD
13.35
SPICE
No paper
#13VinVL (Microsoft Cognitive Services + MSR)SOTA
13.07
SPICE· 2021-01-02
VinVL: Revisiting Visual Representations in Vision-Language Models Code
#14ViTCAP-CIDEr-136.7-ENC-DEC-ViTbfocal10-test-CBS
12.81
SPICE
No paper
#15RCAL
12.2
SPICE
No paper
#16evertyhing
12.1
SPICE
No paper
#17icgp2ssi1_coco_si_0.02_5_test
12.01
SPICE
No paper
#18vinvl_yuan_cbs
11.9
SPICE
No paper
#19camel XE
11.89
SPICE
No paper
#20MQ-UpDown-C
11.68
SPICE
No paper
#21Xinyi
11.62
SPICE
No paper
#22cxy_nocaps_training
11.57
SPICE
No paper
#23Oscar
11.29
SPICE
No paper
#24UpDown + ELMo + CBS
11.2
SPICE
No paper
#25ClipCap (MLP + GPT2 tuning)
11.1
SPICE· 2021-11-18
ClipCap: CLIP Prefix for Image Captioning Code
#267_10-7_40000_predict_test.json
10.96
SPICE
No paper
#27ClipCap (Transformer)
10.86
SPICE· 2021-11-18
ClipCap: CLIP Prefix for Image Captioning Code
#28nocaps_training
10.14
SPICE
No paper
#29UpDown
10.14
SPICE
No paper
#30None
10.1
SPICE
No paper
#31Neural Baby Talk + CBS
9.69
SPICE
No paper
#32area_attention
9.56
SPICE
No paper
#33YX
9.54
SPICE
No paper
#34B2
9.42
SPICE
No paper
#35Neural Baby Talk
9.15
SPICE
No paper
#36coco_all_19
9.13
SPICE
No paper
#37Yu-Wu
8.35
SPICE
No paper
#38CS395T
8.2
SPICE
No paper