Statements (29)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:organization
|
| gptkbp:application |
question answering
image understanding |
| gptkbp:challenge |
VQA Challenge
|
| gptkbp:firstReleased |
2015
|
| gptkbp:hasBenchmark |
VQA v1
VQA v2 VQA-CP |
| gptkbp:hasEvaluationMetric |
accuracy
consensus score |
| gptkbp:hasTaskType |
multiple choice
open-ended |
| https://www.w3.org/2000/01/rdf-schema#label |
VQA
|
| gptkbp:language |
English
|
| gptkbp:memiliki_tugas |
answering questions about images
|
| gptkbp:organizer |
gptkb:Georgia_Institute_of_Technology
gptkb:Virginia_Tech gptkb:Allen_Institute_for_AI |
| gptkbp:paperSizeSupported |
VQA: Visual Question Answering (Antol et al., ICCV 2015)
|
| gptkbp:relatedTo |
gptkb:artificial_intelligence
computer vision natural language processing |
| gptkbp:standsFor |
gptkb:Visual_Question_Answering
|
| gptkbp:trainer |
VQA dataset
|
| gptkbp:usedIn |
deep learning
multimodal AI research |
| gptkbp:website |
https://visualqa.org/
|
| gptkbp:bfsParent |
gptkb:Visual_Question_Answering
|
| gptkbp:bfsLayer |
7
|