Statements (60)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:research
gptkb:dataset |
| gptkbp:author |
gptkb:Michael_Bernstein
gptkb:Li_Fei-Fei gptkb:Justin_Johnson gptkb:Yuke_Zhu David A. Shamma Joshua Kravitz Kenji Hata Li-Jia Li Oliver Groth Ranjay Krishna Stephanie Chen Yannis Kalantidis |
| gptkbp:citation |
numerous academic papers
|
| gptkbp:contains |
images
relationships attributes question-answer pairs object annotations region descriptions |
| gptkbp:createdBy |
gptkb:Stanford_University
|
| gptkbp:enables |
research in AI
fine-grained image understanding |
| gptkbp:focusesOn |
computer vision
scene understanding image annotation |
| gptkbp:license |
gptkb:Creative_Commons_Attribution_4.0
|
| gptkbp:memiliki_tugas |
object detection
image captioning visual question answering attribute recognition region description generation relationship detection scene graph generation |
| gptkbp:numberOfAttributes |
over 1.8 million
|
| gptkbp:numberOfQA |
over 1.4 million
|
| gptkbp:numberOfRegionDescriptions |
over 5 million
|
| gptkbp:numberOfRelationships |
over 2.8 million
|
| gptkbp:numberOfRooms |
over 1.7 million
108,077 |
| gptkbp:relatedTo |
gptkb:Open_Images_dataset
gptkb:COCO_dataset gptkb:ImageNet |
| gptkbp:releaseYear |
2016
|
| gptkbp:supportsFormat |
gptkb:JSON
CSV image files |
| gptkbp:usedBy |
AI researchers
machine learning practitioners computer vision community |
| gptkbp:usedFor |
object detection
image captioning visual question answering relationship detection scene graph generation |
| gptkbp:website |
https://visualgenome.org/
|
| gptkbp:bfsParent |
gptkb:Open_Images_Dataset
|
| gptkbp:bfsLayer |
7
|
| https://www.w3.org/2000/01/rdf-schema#label |
Visual Genome
|