Cross Modal Retrieval
task
ID: crossmodalretrieval
Outgoing Relationships
| Relationship | Target Entity | Type | Actions |
|---|---|---|---|
| proposes | Conditional Visual Semantic Embeddings | method | View |
| dependsOn | Image Caption Datasets | material | View |
| partOf | Multimodal Understanding | task | View |
| measuredBy | Efficiency | metric | View |
| measuredBy | Accuracy | metric | View |
| uses | Transformer Architecture | method | View |