Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Work-level record. Its arXiv versions and any conference or journal version are listed as sources, each with its own date. A citation to the work does not identify which version the citing author read.
- Issued by
- No issuing record yet. A missing record is a gap in coverage.
- Authors credited
- Ross Girshick
- Dates
- Published 2013-11-11 authorship evidence
- Exact source
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation arXiv · published 2013-11-11 · arXiv abstract page, retrieved for the candidate pack on 2026-10-28 (SHA-256 79928b3153464d8154679ed57354a01cf34443c4a25428c47ceaf99bbe6cd2eb). Submission history as arXiv records it (UTC): v1 11 November 2013; v2 15 April 2014; v3 7 May 2014; v4 9 June 2014; v5 22 October 2014. The page serves the latest version; each version is a separate expression, and only the one a record names was read.
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation Crossref · published 2014 · Crossref record of the conference version: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 580-587 (DOI 10.1109/cvpr.2014.81), retrieved for the candidate pack on 2026-10-28. The date is the publisher-deposited date, kept at year precision; it was not checked against the issue.
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation arXiv · published 2013-11-11 · arXiv:1311.2524v1, submitted 11 November 2013 (UTC). Retrieved for the candidate pack on 2026-10-28 (SHA-256 3cb7a18aa362f810665b5becd2581649116ead4933efd133038d59d255163fc6). The author list is the byline as printed on the first page.
Appears in
No collection holds a record about this document yet.
Versions
No other versions of this document are recorded. The evidence applies to the source version listed above. Other versions, such as a preprint, working paper or journal publication, are not identified or substituted.
Issue and authorship records
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Not recorded for this document: cites · cited by · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · discusses · reports evaluation of. A missing record does not show that the relation does not exist.
What the document says it adds
The document’s own description of its contribution, quoted from the version each row names. A claim to be the first is the document’s claim; Selekoa does not assess it.
- In its own wordsThe paper presents R-CNN, an object detection system combining bottom-up region proposals with convolutional neural network features.“We call the resulting system R-CNN: Regions with CNN features.” arXiv v1, PDF p. 1, abstract2013-11-11 · publication · Stated in source · Supported Inspect claim & evidence ↗
- In its own wordsThe paper reports that a convolutional network trained for ImageNet classification can be adapted to detect objects in PASCAL, with a mean average precision of 48% on VOC 2007.“We show that the answer is yes, and that the resulting system is simple, scalable, and boosts mean average precision, relative to the venerable deformable part model, by more than 40% (achieving a final mAP of 48% on VOC 2007).” arXiv v1, PDF p. 1, abstract2013-11-11 · publication · Stated in source · Supported Inspect claim & evidence ↗