# rbgirshick/rcnn

R-CNN: Regions with Convolutional Neural Network Features

Repository: https://github.com/rbgirshick/rcnn
Canonical: https://ross.abutalabs.com/products/rcnn
Language: MATLAB
License: BSD-2-Clause
License Family: permissive
Last push: 2017-04-03T16:16:14+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 4556, "days_push": 3439, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2416, forks 969 (observed 2026-08-28T04:06:50.352112+00:00)

## What it is
The original R-CNN (Region-based Convolutional Neural Networks) object detection system from UC Berkeley, released as research code accompanying CVPR 2014 and PAMI papers. It combines bottom-up region proposals with CNN features for state-of-the-art object detection on PASCAL VOC and ImageNet.

## Use cases
- reproduce the original R-CNN object detection results on PASCAL VOC
- study the historical R-CNN implementation for research or education
- run region-based CNN object detection in MATLAB with Caffe
- compare classic R-CNN baselines against modern detectors
- access pretrained R-CNN models for VOC 2007/2010/2012 and ILSVRC 2013

## When to choose
- you need the exact original R-CNN code to reproduce or cite the CVPR 2014 paper
- you are studying the evolution of CNN-based object detectors
- your workflow is MATLAB-based and you need the historical implementation

## When to avoid
- you want a modern, maintained object detector - use Fast/Faster R-CNN or newer frameworks instead
- you need production-ready or actively supported code
- you cannot work with MATLAB and legacy Caffe dependencies

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, machine-learning, deep-learning
- platform: cpp
- tags: object-detection, rcnn, pascal-voc, caffe, historical, research-code, linux, matlab

## Member repositories
- rbgirshick/rcnn (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:50.352112+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:33:09.776315+00:00, confidence not recorded.
  - readme: https://github.com/rbgirshick/rcnn (fetched 2026-08-28T04:06:50.352112+00:00, sha 3664ba3f20ce)
- Data as of 2026-08-30T08:39:29.467469+00:00.