COXNet proposes cross-layer fusion, dynamic alignment, and GeoShape-based label assignment for RGBT tiny object detection, reporting 3.32% mAP50 gain on the RGBTDronePerson dataset.
Focal loss for dense object detection,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
COXNet: Cross-Layer Fusion with Adaptive Alignment and Scale Integration for RGBT Tiny Object Detection
COXNet proposes cross-layer fusion, dynamic alignment, and GeoShape-based label assignment for RGBT tiny object detection, reporting 3.32% mAP50 gain on the RGBTDronePerson dataset.