Image Captioning on nocaps near-domain

Metric: CIDEr (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	CIDEr▼	Extra Data	Paper	Date↕	Code
1	GIT2, Single Model	125.51	No	GIT: A Generative Image-to-text Transformer for ...	2022-05-27	Code
2	PaLI	124.35	No	PaLI: A Jointly-Scaled Multilingual Language-Ima...	2022-09-14	Code
3	GIT, Single Model	123.92	No	GIT: A Generative Image-to-text Transformer for ...	2022-05-27	Code
4	CoCa - Google Brain	120.73	No	-	-	-
5	Microsoft Cognitive Services team	115.54	No	VIVO: Visual Vocabulary Pre-Training for Novel O...	2020-09-28	-
6	Single Model	110.76	No	SimVLM: Simple Visual Language Model Pretraining...	2021-08-24	Code
7	FudanFVL	109.33	No	-	-	-
8	FudanWYZ	108.04	No	-	-	-
9	IEDA-LAB	100.15	No	-	-	-
10	firethehole	99.51	No	-	-	-
11	MD	95.73	No	-	-	-
12	vll@mk514	95.69	No	-	-	-
13	VinVL (Microsoft Cognitive Services + MSR)	95.16	No	VinVL: Revisiting Visual Representations in Visi...	2021-01-02	Code
14	ViTCAP-CIDEr-136.7-ENC-DEC-ViTbfocal10-test-CBS	89.87	No	-	-	-
15	icgp2ssi1_coco_si_0.02_5_test	87.41	No	-	-	-
16	evertyhing	85.89	No	-	-	-
17	Human	84.58	No	-	-	-
18	RCAL	84	No	-	-	-
19	Oscar	82.07	No	-	-	-
20	vinvl_yuan_cbs	80.21	No	-	-	-
21	cxy_nocaps_training	79.72	No	-	-	-
22	Xinyi	79.44	No	-	-	-
23	camel XE	79.14	No	-	-	-
24	MQ-UpDown-C	76.34	No	-	-	-
25	UpDown + ELMo + CBS	74.2	No	-	-	-
26	ClipCap (MLP + GPT2 tuning)	67.69	No	ClipCap: CLIP Prefix for Image Captioning	2021-11-18	Code
27	ClipCap (Transformer)	66.82	No	ClipCap: CLIP Prefix for Image Captioning	2021-11-18	Code
28	7_10-7_40000_predict_test.json	63.96	No	-	-	-
29	Neural Baby Talk + CBS	61.98	No	-	-	-
30	None	58.5	No	-	-	-
31	nocaps_training	56.85	No	-	-	-
32	UpDown	56.85	No	-	-	-
33	Neural Baby Talk	53.21	No	-	-	-
34	YX	51.16	No	-	-	-
35	area_attention	50.34	No	-	-	-
36	B2	49.62	No	-	-	-
37	coco_all_19	47.53	No	-	-	-
38	Yu-Wu	46.64	No	-	-	-
39	CS395T	40.45	No	-	-	-

#1GIT2, Single ModelSOTA
125.51
CIDEr· 2022-05-27
GIT: A Generative Image-to-text Transformer for Vision and Language Code
#2PaLI
124.35
CIDEr· 2022-09-14
PaLI: A Jointly-Scaled Multilingual Language-Image Model Code
#3GIT, Single Model
123.92
CIDEr· 2022-05-27
GIT: A Generative Image-to-text Transformer for Vision and Language Code
#4CoCa - Google Brain
120.73
CIDEr
No paper
#5Microsoft Cognitive Services teamSOTA
115.54
CIDEr· 2020-09-28
VIVO: Visual Vocabulary Pre-Training for Novel Object Captioning
#6Single Model
110.76
CIDEr· 2021-08-24
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision Code
#7FudanFVL
109.33
CIDEr
No paper
#8FudanWYZ
108.04
CIDEr
No paper
#9IEDA-LAB
100.15
CIDEr
No paper
#10firethehole
99.51
CIDEr
No paper
#11MD
95.73
CIDEr
No paper
#12vll@mk514
95.69
CIDEr
No paper
#13VinVL (Microsoft Cognitive Services + MSR)
95.16
CIDEr· 2021-01-02
VinVL: Revisiting Visual Representations in Vision-Language Models Code
#14ViTCAP-CIDEr-136.7-ENC-DEC-ViTbfocal10-test-CBS
89.87
CIDEr
No paper
#15icgp2ssi1_coco_si_0.02_5_test
87.41
CIDEr
No paper
#16evertyhing
85.89
CIDEr
No paper
#17Human
84.58
CIDEr
No paper
#18RCAL
84
CIDEr
No paper
#19Oscar
82.07
CIDEr
No paper
#20vinvl_yuan_cbs
80.21
CIDEr
No paper
#21cxy_nocaps_training
79.72
CIDEr
No paper
#22Xinyi
79.44
CIDEr
No paper
#23camel XE
79.14
CIDEr
No paper
#24MQ-UpDown-C
76.34
CIDEr
No paper
#25UpDown + ELMo + CBS
74.2
CIDEr
No paper
#26ClipCap (MLP + GPT2 tuning)
67.69
CIDEr· 2021-11-18
ClipCap: CLIP Prefix for Image Captioning Code
#27ClipCap (Transformer)
66.82
CIDEr· 2021-11-18
ClipCap: CLIP Prefix for Image Captioning Code
#287_10-7_40000_predict_test.json
63.96
CIDEr
No paper
#29Neural Baby Talk + CBS
61.98
CIDEr
No paper
#30None
58.5
CIDEr
No paper
#31nocaps_training
56.85
CIDEr
No paper
#32UpDown
56.85
CIDEr
No paper
#33Neural Baby Talk
53.21
CIDEr
No paper
#34YX
51.16
CIDEr
No paper
#35area_attention
50.34
CIDEr
No paper
#36B2
49.62
CIDEr
No paper
#37coco_all_19
47.53
CIDEr
No paper
#38Yu-Wu
46.64
CIDEr
No paper
#39CS395T
40.45
CIDEr
No paper