AI RESEARCH

REACT++: Efficient Cross-Attention for Real-Time Scene Graph Generation

arXiv CS.CV

ArXi:2603.06386v1 Announce Type: new Scene Graph Generation (SGG) is a task that encodes visual relationships between objects in images as graph structures. SGG shows significant promise as a foundational component for downstream tasks, such as reasoning for embodied agents. To enable real-time applications, SGG must address the trade-off between performance and inference speed.