Cross-modal Coherence Modeling for Caption Generation
37393Knowledge Triples
| Source Entity | Relationship | Target Entity |
|---|---|---|
|
Annotation Protocol
OtherEntity |
appliesTo |
Image Caption Pairs
Material |
|
Coherence Aware Captioning
Method |
enhances |
Caption Quality
Metric |
|
Relation Classifiers
OtherEntity |
improves |
Coherence Aware Captioning
Method |