Visual Question Answering (VQA) on VizWiz 2018

Metric: other (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	other▼	Extra Data	Paper	Date↕	Code
1	LXR955, No Ensemble	39	No	LXMERT: Learning Cross-Modality Encoder Represen...	2019-08-20	Code
2	fw_vqa_	37.6	No	-	-	-
3	B-Ultra	35.41	No	Decoupled Box Proposal and Featurization with Ul...	2019-09-04	-
4	DVW	34.81	No	-	-	-
5	DVizWiz	33.98	No	-	-	-
6	BAN	31.5	No	-	-	-
7	ss	26.97	No	-	-	-
8	hdhs	26.83	No	-	-	-
9	Colin	23.7	No	-	-	-

#1LXR955, No EnsembleSOTA
39
other· 2019-08-20
LXMERT: Learning Cross-Modality Encoder Representations from Transformers Code
#2fw_vqa_
37.6
other
No paper
#3B-Ultra
35.41
other· 2019-09-04
Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering
#4DVW
34.81
other
No paper
#5DVizWiz
33.98
other
No paper
#6BAN
31.5
other
No paper
#7ss
26.97
other
No paper
#8hdhs
26.83
other
No paper
#9Colin
23.7
other
No paper