 Representation Learning for Scene Graph Completion via Jointly Structural and Visual Embedding/Pasted_image_20250318162533.png)
Representation Learning for Scene Graph Completion via Jointly Structural and Visual Embedding
The architecture of RLSV is a three-layered hierarchical projection that projects a visual triple onto the attribute space, the relation space, and the visual space in order.
Representation Learning for Scene Graph Completion via Jointly Structural and Visual Embedding
