Statements (59)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:Database_Management_System
|
| gptkbp:bfsLayer |
4
|
| gptkbp:bfsParent |
gptkb:dictionary
|
| gptkbp:based_on |
graphics engines
3 D rendering techniques |
| gptkbp:composed_of |
images
questions answers |
| gptkbp:contains |
questions
synthetic images |
| gptkbp:created_by |
gptkb:Justin_Johnson
|
| gptkbp:features |
logical reasoning
3 D scenes varied object attributes |
| gptkbp:has_version |
gptkb:2.0
gptkb:3.0 1.0 |
| https://www.w3.org/2000/01/rdf-schema#label |
CLEVR Dataset
|
| gptkbp:includes |
multiple choice questions
attribute questions comparison questions counting questions spatial questions |
| gptkbp:is_available_on |
https://cs.stanford.edu/people/jcjohns/clevr/
|
| gptkbp:is_designed_for |
gptkb:Research_Institute
|
| gptkbp:is_documented_in |
research articles
technical reports theses conference papers |
| gptkbp:is_evaluated_by |
performance metrics
accuracy benchmark tests user studies |
| gptkbp:is_part_of |
AI datasets
|
| gptkbp:is_related_to |
deep learning
question answering scene understanding object recognition image understanding AI benchmarks synthetic data generation visual reasoning tasks |
| gptkbp:is_supported_by |
academic institutions
community contributions open source tools |
| gptkbp:is_used_by |
gptkb:University
gptkb:physicist gptkb:software |
| gptkbp:is_used_for |
gptkb:software_framework
computer vision |
| gptkbp:is_used_in |
research papers
competitions |
| gptkbp:length |
100000 answers
150000 questions 70000 images |
| gptkbp:purpose |
visual reasoning
|
| gptkbp:release_year |
gptkb:2017
|
| gptkbp:supports |
neural network training
visual question answering |