ProtoHGF-Net fuses RGB and thermal features via prototype-level hypergraph propagation with teacher-mask calibration, reporting 85.9%, 88.2%, and 79.1% mAP50 on DroneVehicle, DVTOD, and FLIR.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ProtoHGF-Net: Prototype HyperGraph Fusion with Intra-modal Calibration for RGBT Object Detection
ProtoHGF-Net fuses RGB and thermal features via prototype-level hypergraph propagation with teacher-mask calibration, reporting 85.9%, 88.2%, and 79.1% mAP50 on DroneVehicle, DVTOD, and FLIR.