R-CNN: region proposals with convolutional features

What changed

Combined bottom-up region proposals with pretrained and detection-finetuned convolutional features and class-specific SVMs, demonstrating strong object detection and transferable region representations.

Scientific scope

Combined bottom-up region proposals with pretrained and detection-finetuned convolutional features and class-specific SVMs, demonstrating strong object detection and transferable region representations. Original2013v1, not silently updated with later R-CNN performance/features. Selective search, CNN pretraining and SVMs are inherited components. Per-proposal warped-image computation and multistage training differ from Fast/Faster/Mask R-CNN already covered.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Original2013v1, not silently updated with later R-CNN performance/features. Selective search, CNN pretraining and SVMs are inherited components. Per-proposal warped-image computation and multistage training differ from Fast/Faster/Mask R-CNN already covered.

Contributors

• Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.

• Rich feature hierarchies for accurate object detection and semantic segmentation

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