Visual Commonsense in Pretrained Unimodal and Multimodal Models
21022Knowledge Triples
| Source Entity | Relationship | Target Entity |
|---|---|---|
|
Visual Commonsense Tests
Material |
covers |
Color
Task |
|
Visual Commonsense Tests
Material |
covers |
Material
Task |
|
Visual Commonsense Tests
Material |
covers |
Shape
Task |
|
Visual Commonsense Tests
Material |
covers |
Size
Task |
|
Visual Commonsense Tests
Material |
covers |
Visual Co-occurrence
Task |