Search Results for author:
Found 3 papers, 1 papers with code
Rethinking of Feature Interaction for Multi-task Learning on Dense Prediction
In this work, we propose to learn a comprehensive intermediate feature globally from both task-generic and task-specific features, we reveal an important fact that this intermediate feature, namely the bridge feature, is a good solution to the above issues.
Rethinking Cross-Domain Pedestrian Detection: A Background-Focused Distribution Alignment Framework for Instance-Free One-Stage Detectors
Therefore, we focus on cross-domain background feature alignment while minimizing the influence of foreground features on the cross-domain alignment stage.
Multi-Object Manipulation via Object-Centric Neural Scattering Functions
Learned visual dynamics models have proven effective for robotic manipulation tasks.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
