Statements (35)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
computer vision task
|
| gptkbp:application |
robotics
autonomous driving image captioning visual question answering |
| gptkbp:bench |
gptkb:Open_Images
gptkb:Visual_Genome |
| gptkbp:challenge |
incomplete annotations
long-tail distribution relationship ambiguity |
| gptkbp:conference |
gptkb:CVPR
gptkb:ECCV gptkb:ICCV |
| gptkbp:field |
gptkb:artificial_intelligence
computer vision |
| gptkbp:goal |
extract objects and relationships from images
|
| https://www.w3.org/2000/01/rdf-schema#label |
Scene Graph Generation
|
| gptkbp:input |
gptkb:illustrator
|
| gptkbp:notable_for |
Graph R-CNN
IMP (Iterative Message Passing) Neural Motifs RelDN VCTree |
| gptkbp:output |
scene graph
|
| gptkbp:proposedBy |
2016
|
| gptkbp:publishedIn |
gptkb:IEEE_TPAMI
IJCV |
| gptkbp:relatedTo |
object detection
image understanding relationship detection |
| gptkbp:uses |
convolutional neural networks
deep learning graph neural networks |
| gptkbp:bfsParent |
gptkb:Hari_Vedantam
|
| gptkbp:bfsLayer |
7
|