Dai and colleagues: R-FCN object detection

What changed

Proposed region-based fully convolutional detection with position-sensitive score maps to share most computation across an image.

Scientific scope

Proposed region-based fully convolutional detection with position-sensitive score maps to share most computation across an image. Scope limitation: R-FCN builds on region-proposal detection; it is distinct from Fast/Faster R-CNN and does not invent region proposals.

Evidence

The retained primary-source abstract, bibliographic record and stated review scope support this provisional assessment. No independent experimental replication by WRS is claimed. R-FCN builds on region-proposal detection; it is distinct from Fast/Faster R-CNN and does not invent region proposals.

Contributors

• The named authors listed in the linked research record · SCIENCE: Complete source byline retained in the research record; human research direction, method development and evaluation. Individual labor shares are not measured.

• Dai and colleagues: R-FCN object detection — original paper
• Dai and colleagues: R-FCN object detection — official company source

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction