Question Generation on COCO Visual Question Answering (VQA) real images 1.0 open ended

Metric: BLEU-1 (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	BLEU-1▼	Extra Data	Paper	Date↕	Code
1	MDN	65.1	No	Multimodal Differential Network for Visual Quest...	2018-08-12	Code
2	coco-Caption [[Karpathy and Li2014]]	62.5	No	Deep Visual-Semantic Alignments for Generating I...	2014-12-07	Code
3	Max(Yang,2015)	59.4	No	Neural Self Talk: Image Understanding via Contin...	2015-12-10	-
4	Sample(Yang,2015)	38.8	No	Neural Self Talk: Image Understanding via Contin...	2015-12-10	-

#1MDNSOTA
65.1
BLEU-1· 2018-08-12
Multimodal Differential Network for Visual Question Generation Code
#2coco-Caption [[Karpathy and Li2014]]SOTA
62.5
BLEU-1· 2014-12-07
Deep Visual-Semantic Alignments for Generating Image Descriptions Code
#3Max(Yang,2015)
59.4
BLEU-1· 2015-12-10
Neural Self Talk: Image Understanding via Continuous Questioning and Answering
#4Sample(Yang,2015)
38.8
BLEU-1· 2015-12-10
Neural Self Talk: Image Understanding via Continuous Questioning and Answering