Tasks
SotA
Datasets
Papers
Methods
Submit
About
Datasets
/
GQA-REX
GQA-REX
Images
Texts
MIT license
Introduced 2022-03-11
A GQA-based dataset with 1,040,830 multi-modal explanations of visual reasoning processes.
Benchmarks
Explanatory Visual Question Answering
/
BLEU-4
Explanatory Visual Question Answering
/
CIDEr
Explanatory Visual Question Answering
/
GQA-test
Explanatory Visual Question Answering
/
GQA-val
Explanatory Visual Question Answering
/
Grounding
Explanatory Visual Question Answering
/
METEOR
Explanatory Visual Question Answering
/
ROUGE-L
Explanatory Visual Question Answering
/
SPICE
Visual Question Answering
/
BLEU-4
Visual Question Answering
/
CIDEr
Visual Question Answering
/
GQA-test
Visual Question Answering
/
GQA-val
Visual Question Answering
/
Grounding
Visual Question Answering
/
METEOR
Visual Question Answering
/
ROUGE-L
Visual Question Answering
/
SPICE
Visual Question Answering (VQA)
/
BLEU-4
Visual Question Answering (VQA)
/
CIDEr
Visual Question Answering (VQA)
/
GQA-test
Visual Question Answering (VQA)
/
GQA-val
Visual Question Answering (VQA)
/
Grounding
Visual Question Answering (VQA)
/
METEOR
Visual Question Answering (VQA)
/
ROUGE-L
Visual Question Answering (VQA)
/
SPICE