Search Results for author:
Found 2 papers, 1 papers with code
Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label Distillation
Extensive experiments demonstrate that our LPLD loss leads to effective adaptation by reducing false negatives and facilitating the use of domain-invariant knowledge from the source model.
Track Initialization and Re-Identification for~3D Multi-View Multi-Object Tracking
Specifically, we exploit the 2D detections and extracted features from multiple cameras to provide a better approximation of the multi-object filtering density to realize the track initiation/termination and re-identification functionalities.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
