1 code implementation • 23 Aug 2022 • Yang Li, Yucheng Tu, Xiaoxue Chen, Hao Zhao, Guyue Zhou
In this work, (1) we propose a novel three-decoder architecture as the infrastructure for focused attention; 2) we use the generalized intersection box prediction task to effectively guide our model to focus on occlusion-specific regions; 3) our model achieves a new state-of-the-art performance on distance-aware relationship detection.
Human-Object Interaction Detection Relationship Detection +1