severstal-steel-defect-detection: papers linking to it

Kaggle · www.kaggle.com/competitions/severstal-steel-defect-detection

← Code and data repositories cited in research papers

Research papers in the 480 tracked journals that link to severstal-steel-defect-detection (https://www.kaggle.com/competitions/severstal-steel-defect-detection), read from their Crossref records: by year, category and journal, the family tree of papers building on one another, and the linked repositories derived from it or that it derives from.

Key findings#

3 papers in the tracked journals link to the Kaggle dataset severstal-steel-defect-detection in their Crossref records, the first in 2022; most of them (2) in 2022.
By category: AI (3); the journals with the most are Neural Computing and Applications (2) and Expert Systems with Applications (1).

By year#

20222023

Papers linking to severstal-steel-defect-detection by publication year
Year	Papers
2022	2
2023	1

Journals#

Journals whose papers link to severstal-steel-defect-detection most
Journal	Papers
Neural Computing and Applications	2
Expert Systems with Applications	1

Papers linking to severstal-steel-defect-detection, most cited first
Published	Title	Journal	Authors	Citations	Link
2023-01-28	Comparative assessment of common pre-trained CNNs for vision-based surface defect detection of machined components	Expert Systems with Applications	Swarit Anand Singh, Aitha Sudheer Kumar, Kaushal A. Desai	86	cites it
2022-12-08	Automated steel surface defect detection and classification using a new deep learning-based approach	Neural Computing and Applications	Kürşat Demir, Mustafa Ay, Mehmet Çavaş et al.	61	cites it
2022-12-21	Multi-target domain-based hierarchical dynamic instance segmentation method for steel defects detection	Neural Computing and Applications	Chi Zhang, Xi Zhang	10	cites it

How this is measured#

Links are read from each paper's Crossref record as its publisher deposited it: the URLs and repository DOIs in its reference list (the software and data it cites) and its supplementary links (“is-supplemented-by”: its own code or data). A paper that gives its code only in the text, a footnote or a data availability statement is not counted, and some publishers deposit reference lists without their URLs, so every count here is a lower bound. Repository details come from the GitHub REST API (stars, forks, and the repository a fork was made from), the Hugging Face Hub API (likes, downloads, and the base model a model was derived from) and DataCite (Zenodo and other data DOIs, and the GitHub release a Zenodo record archives), read again every month.

Cite this page

Scholar4AI. (2026). severstal-steel-defect-detection: papers linking to it. Journal and Conference Research Rankings. Retrieved November 3, 2026, from https://scholar4ai.com/code/kaggle-competition-severstal-steel-defect-detection

@misc{scholar4ai-code-kaggle-competition-severstal-steel-defect-detection,
  author = {{Scholar4AI}},
  title = {severstal-steel-defect-detection: papers linking to it},
  year = {2026},
  howpublished = {\url{https://scholar4ai.com/code/kaggle-competition-severstal-steel-defect-detection}},
  urldate = {2026-11-03},
  note = {Journal and Conference Research Rankings; data from OpenAlex (CC0); licensed CC BY-NC 4.0}
}

Free to reuse for non-commercial purposes with attribution (CC BY-NC 4.0).